WO1996030844A1 - Support system for automation of story structure preparation - Google Patents

Abstract

A support system for automation of story structure preparation prepares automatically a story structure basically in the sequence of a core story, a story and a plot on the basis of fragmentary events by a user or a partial tree and the values of story parameters. The story structure is uniformly constituted by a tree system, and the system comprises story parameters as groups of fragmentary procedures for expanding/modifying this tree, a knowledge base storing knowledge about the concepts and event combination to which reference is made by the system, a story strategy comprising groups fragmentary rules for controlling the operation of the groups of story techniques and a story preparation management mechanism for managing all these processes. Different stories can be flexibly prepared from the same input event or partial tree in accordance with the kind of the story parameters inputted by the user, and this capability is brought forth because all of the principal mechanisms for the preparation of the story structure such as the story technique, the story strategy and the knowledge base comprise the aggregate of the fragmentary information, and because the system accomplishes their versatile combinations by the consistent method described above.

Description

 Speculation damage Story structure creation automation support system

The present invention improves the human interface capability of a computer based on a mechanism for automatically creating a story outline (art line) more efficiently and diversified than a human being, thereby improving human creativity. more specifically is to M to a system that is intended to support the idea specific working process _c, the narrative structure created automated support system, descriptions of fractional one or more events (out Raikoto) And inputting the setting of multiple parameters that mean the request from the user (input by the user), referred to as core stories, stories, pros, professionals, without the need for human intervention. In three stages, the description of the conceptual structure (called Γstory structure j), which is the outline of the story, is automatically created.

 Here, a story means a form of discourse composed of an organic combination of a number of events. The story structure means the data in the description format inside the computer system of the story.

 Although the present invention is based on the basic principle of being a general-purpose mechanism that can deal with narratives of any genre, in the present specification harm, in particular, the creation of an automatic narrative mechanism for a mystery novel a narrative An example is shown. Background art

 1 Branch art background and overview

 Advances in information technology based on computer branching have had a tremendous impact on the operation of society and businesses, but this trend will be increasingly accelerated in the 21st century. It is expected that social intellect and networking will be advanced based on this. What matters is that ft information technology works cooperatively for humans, and ultimately, through the use of information branching, the ability and potential of diverse capabilities in different territories of people. It is hoped that sex search will be easier. From a macro perspective, information technology is one of the most important social and cultural books to push human civilization to a new level.

 Artificial intelligence or knowledge engineering, which plays a part in such information branching techniques, is an indispensable research area, especially for the advancement of software technology. Many achievements have been made in such fields as understanding 捃. Nowadays, the natural interface with humans; the computer as a source device, the device as a device to help the human beings, etc. A new role of β! In total is expected and required in the context of wide-ranging knowledge, such as the reputation building as a tournament. The research that seeks to open up and expand the new possibilities of branch surgery is not only traditional, intelligent, but also human-computer. Interaction, multi-tier, and dew instrument support. Collaborative work, ideas · ί | ΐ1¾ ϋ 支援 動 領

From a long-term and general perspective, the present invention is based on the background described above, and considers the extent of human creativity and the sexual factors. Communication iSK and I Cormorant is intended to contribute to the realization of the major goals _r In particular, the present invention is, usually to the culture of soft toe in the culture of the people閱;.. Focusing on the story should be called r Ma, this story ability to create computer software Touea By providing a fundamental method for realizing the goal. To contribute to the development of various industrial and branch-art fields that are self-developing in the field of “industrial applicability”. And

 The distinctive functions of narrative and human narrative generation are the aesthetic expression function that evokes catharsis or excitement. The semantic generation function through the arrangement of fragmentary thoughts, the concrete expression of abstract thoughts Emotional expression function for transmitting knowledge. There is a virtual reality function for performing simulation in a virtual world. In the present invention, a basic system for effectively utilizing and realizing these characteristics of the material is provided as one of the above-mentioned bet requirements for the future machine technology. We thought that it could be used as nuclear technology. For example, natural language interface, marriage meti-me interface, gaming & simulation, intellectual education system decision support ¾ support creation of thousands of skulls. Support for creation of scenarios and advertisements, ideas and embroidery. , Such as music and movie systems such as live-action games such as dramas, and electronic publishing systems such as drama, etc .. This is an application software for promoting the intelligentization of the advanced telecommunications business, which is one of the major key industries for the 21st century, as well as the technology field expected of the United States. From the basic nature of the story described above, it is anticipated that the role of automating support for story creation will play a significant role in the future industry.

 As described above, the present invention provides a narrative structure that can support creative activities and can be applied to various fields of application such as Humanintuff X-S, in view of the current state of the multimedia age. This is a W to create automation support system. However, the current state of computer software, including the latest technologies such as Multimetia, is that software that can achieve the specific goals (in this case, narrative structure) that human soft-to-X creators want to create. Designed and described one by one, this software cannot play any role other than the operation originally assumed. On the other hand, the present invention realizes the function of automatically creating a story structure by the user only by setting some requirements by the user, thereby realizing the conventional computer software. It is a way to further improve the way of the wear, and based on the above-mentioned zero technical background, it goes beyond the mere extension and improvement of the existing technology, and this book! It can be said that it has unique novelty.

In the present invention, a basic method that can integrate the knowledge necessary for creating a story structure into the process of creating a story as a tree structure (hereinafter referred to as a “story tree”) is used. Is presented. In this method, the creation of the story structure corresponds to the expansion or transformation of the story tree, and the mechanisms for these operations are central to the methodology. A bipartite knowledge of fragmentary hand-type knowledge to expand or transform the end of the story, and equally fragmentary rule-type knowledge to control their use. Such a structure is configured based on the structure. Of this, shouting that of the former hand * ¾-out ¾> knowledge and "The Story technique," said ^Kohi, Γ product駱that of the latter-controlled knowledge ". Furthermore, the narrative branch method requires a reference to a knowledge base that stores «minds and other knowledge» for the narrative expression. With this mechanism, the ability to use a fragmentary knowledge group to enable the flexible automatic generation of stories without having to trace the first-speed steps to create a specific story structure in advance. can get.

The technical points of the present invention are as follows. (Details in the meaning of ¾ First, the creation of the story structure was broadly divided into two aspects. One is called a story, and the other is called a "proto". Among them, a story is a structure based on the temporal I-equatorial mechanism of events, whereas Means that it is transformed according to the structure of the expression as a story.

 Next, the narrative structure was expressed using a narrative tree, and the process of creating the material structure was unified as an integrated work for the narrative tree. The creation of a story structure corresponding to the connection of the terminal nodes of the story tree in the above story and plot means such an extension or transformation of the story story. In the story-making section, the main part of the story is expanded, and in the professional / 's story-making section, the story tree is mainly transformed into a story. Narrative technique means the means to concretely execute these works.

 Next, we defined fragmentary hand-crafted information that manipulates the story tree as a narrative technique. This is mainly because each narrative technique, which performs an extension or transformation of narrative II in various styles, defines how the narrative tree is manipulated in a particular way, each of which is a fragmentary piece that performs a single task. It constitutes a simple handicraft module.

 Next, we defined a rule-based knowledge group that controls the use of the narrative branch method as a narrative strategy. This is knowledge that implies generation control to determine which part of the story tree to apply which story technique at what point in the story creation. Stories are defined in fragmentary rules and are driven by control mechanisms. With this mechanism, it is possible to determine the usefulness of fragmentary narrative techniques by referring to the value of “story parameters” required by the user, and the flexibility of narrative structure creation And diversity is easily realized.

 Finally, in creating the story, a networked knowledge base is consulted. The expansion of the story mainly creates another event or subtree that has some M factor for a specific event or subtree that constitutes the last part of the story, thereby extending the story tree as a whole. It is done through doing. Recognition of such an entity for a certain event or subtree is performed through a network-like knowledge base.

 As described above, this system divides the knowledge used in creating the narrative structure into three main parts: the narrative technique, the narrative update, and the knowledge base. Utilization is handled by the rules of the story strategy, which means the control mechanism of the entire story structure creation process, without having to write a fixed algorithm that matches the creation of a particular type of story in advance. Through the use of fragmentary narrative branch methods and knowledge-based items in a cooperative and combinatorial manner, each user has different settings for the story parameters, which are the requirements by the user. A mechanism that automatically creates a story structure is realized e2 Conventional technology

 Although there is no conventional branching technique that can be directly compared with the story structure creation method in this system, the following are some of the elementary techniques used in the present invention and the conventional techniques that are M-speed. .

In the information processing fields such as artificial intelligence and cognitive science, there have been several approaches targeting physical consultation as the most advanced form of natural language processing. For example, narrative grammar has been proposed in the United States based on the assumption that narrative knowledge structures play an important role in human cognitive mechanisms such as memory of memory and summaries. As a theoretical framework based on similar assumptions, US A call-plan has been proposed in Japan, and it has been used in some actual systems as a cornerstone of the natural language understanding system. However, the purpose of these studies is to understand natural H-words, not to create mostly narrative stories, and to make the narrative creation and motivation more advanced. It is not intended to be placed on a foundation, and is not a speedy connection with the essential tier of the present invention, which means that the characteristic functions of the object are effectively used for that purpose.

 In addition, as a conventional story generation system, the goal-plan theory described above was verified.

Several systems have been wiped out since T ale-S pin (USA) until recently. Through these systems, experiments such as episodic memory, dynamic memory, and the mechanism of loneliness, in addition to the goal-one plan, were experimented. As described above, the conventional story generation system is often positioned as an experimental system for verifying a specific ethical framework in the information processing field such as artificial intelligence. It is based on the principle of operation limited to the theoretical framework of the above, and aims to be a basic technology for constructing a new framework of computer systems by analyzing the structural characteristics of the story itself from many aspects. As a result, nothing was configured as an integrated system. In addition, these conventional systems aim at verifying the rationale in artificial intelligence through a simple simulation of human behavior in a very small story world. (The real human world is too complicated. This is a virtual realization of the world of object 1§ for the experiment), and did not bring a new architecture on the system.

On the other hand, in recent years, research has been advocated for using the characteristics of materials in a broad sense in the construction of information media technology. For example, Laurel et al., A research group seeking a new human-machine relationship through the use of multimedia and virtual reality technology, has developed stories and drama philosophies such as Alice Tortrez's poetics and Freitag's drama theory. We are studying «and considering how to introduce it as a basis for interactive user interface and drama urgi in information media. Bates and colleagues also propose an Oz project (USA) that involves an artificial reality system in which autonomous characters interact and interact with users in a narrative or dramatic virtual environment. ). However, the narrative creation function itself has been proposed in these projects, and the emphasis is on interactive multimedia. In addition, S chank et al. (USA), who proposed several narrative knowledge structures in artificial intelligence and cognitive science as described in the previous paragraph, have now integrated traditional narrative understanding research with Metia technology, It reports on the development of an educational system that is flexible and interactive. The focus of these studies is on the use of some narrative methods as a method of constructing new information media, including multimedia. No suggestions have been made. In this regard, the main motivation is to use an automatic narrative creation mechanism at the core and make it a powerful foundation for various creative and creative activities and the human interface. The present invention is different from the Abloh thousand of the present invention, which suggests an integrated branching means of the present invention. For example, in an ad-pen thousand-year game or in a role-playing-in-a-box game with a thousand incentives, for example, there are * In Tory Development The game is embedded. This shows the sprouting of a new form of s-expression, which has the remarkable characteristic of user comprehension or the possibility of user participation, divergence of word development, comprehensive artisticness through video, audio and narration. It is. In addition, a simulation system in which the progress of the learning method changes due to the difference in the setting of the condition of the user within the situation, such as the action of the user, is similar to that of the above-mentioned easy gaming system. Has features. However, in these conventional branch techniques, the diversity of the story development (divergence) is only a mere selection from several possibilities fixed by the creator in advance. Do not have the ability to create stories at all. On the other hand, the present invention realizes a completely automated mechanism for creating a story structure by introducing a story strategy based on story parameters, and in that sense, adopts a conventional approach such as simulation and simulation. On the other hand, it is an inherently different approach.

 In general, the approaches described above do not realize the technology of automatic narrative creation, but are configured as an extension of the existing computer software and multi-methia branch surgery. It can be said that the technical methods are different from these types.

 It should be noted that the S-type connection between the “marketing advertisement automation support system”, which is a type of invention previously submitted by the present inventors, and the present invention is as follows. In a marketing advertisement automation support system, based on marketing data, the system creates a series of event sequences (scenes) in which a specific segment (person type) acts, and uses it to create a complex As a knowledge organization that does this, it incorporates multiple rules for combining multiple events, but in the present invention, it uses the above K to create several types of advertising works. A fixed algorithm consisting of a combination of rules is described in advance as a normal procedural processing procedure, and the above rules are limited to a small number and have a mechanism depending on the specific field of advertisement .

 On the other hand, in the present invention, the types and mechanisms of story techniques for creating a story structure are greatly enhanced and expanded, and a unified principle of expansion and deformation processing at the end of the story is established. In this way, the types of material and techniques are classified and systematically organized. More specifically, in some narrative techniques of the present invention, some of the rules overlap with the rules in the above-mentioned marketing advertisement automation support system. The application of the technique has been strengthened and expanded compared to the conventionally proposed rules W, and many other branch methods have been added and expanded.

In addition, the most important novelty in Kibatsu BB is the creation of a story structure. The thing that controls the entire process. By elaborating the collection of rules called iSdft abbreviations. It is possible to create various types of narrative structures without having to pre-write the target argo-sum. This is a mechanism that does not exist in the conventional marketing advertisement automation support system based on the fixed draft algorithm. In other words, the creation of the story takes into account the requirements of the user at the time. The rules of the story war, or the rules of the simple story branch and the end of the story can be redeemed. The _e- equipment-and-branch method group executed by will function more effectively only in conjunction with this automated mechanism. In addition, since each moshur is composed of a set of fragmentary procedures and rules, it is easy to add and delete these rules, and they do not make the system inoperable. It also has the property of This is associated with the advantages of easy scalability and changeability of the system. These characteristics are also the characteristics that flexible automation control based on the above-mentioned story moth scheme is achieved by controlling the entire process.

 In this way, the present invention is based on the existence of a flexible control mechanism, that is, a story strategy, at the core, and speeds up compared to the method in the conventional marketers' advertisement automation support system. It has features such as expansion and systematicity, system expandability and changeability, versatility, etc., so that new functions can be realized. Invention

 1 Problems to be solved by the present invention

 Conventionally, the system automatically creates texts with a story's structure to create various types of users. A system that can be used for creative work and can be used as an advanced human interface in various computer systems. Did not exist.

 As a use situation of the present invention, for example, a scene in which a user conceives an outline of an easy-to-use or business story and an idea line can be assumed. At that time, the system is required to have the ability to create stories of various configurations in winter, but at the same time, the ability to narrow down to a small number of stories and present it to users according to the needs of users. It is necessary to have the ability to easily test different possibilities. In addition, a general purpose system that can be easily expanded or changed according to the type of story desired by the user and the purpose of use is also required. (Note that the usage status is also used in a system that requires a kind of simulation, such as education or games.) Or calculate the progress of the simulation automatically while using the system.)

 The outline of these technical sections S and the matters necessary for their solution are summarized below.

 1. Narrative structure creation * The present invention also envisages the possibility of generating a story or acting as a kind of stimulant for human creative or imaginary tasks. There is a need for a method that can easily and flexibly realize a new story. In order to solve such a technical section S, it is impossible with an algorithm limited to the creation of a story of a specific structure in advance, and many combinations can be easily realized from a set of more fragmentary elements. We need a mechanism that can create

 2. Flexible automation control method: The strategy is automatically determined based on the demands of the user at each time, without having to decide on a stumbling block in story creation, and without user intervention. One of the important technical tasks is to realize a method that can automatically succeed and complete generation. The realization of such a system is not to create a predetermined type of story. It is possible to create a different story according to the user's occasional demand, and to meet the diverse needs of the user * «: Will be able to deal with. For that purpose, a ttfll that can refer to the description expressing the user's request and determine the combined use of knowledge for the creation of the object in each case is necessary. Become.

2. 忤 用 Λ ： To meet the winter requirements of the user. Various knowledge used to create the story structure. Rather than assuming only a fixed story type, it must be a collection of fragmentary units that use techniques and knowledge commonly used in various stories. And, as mentioned above, it is necessary to flexibly create various physical structures by way of using or combining them, that is, operational intellectual arrowheads for narrative creation = narrative warfare. In addition, it must be easy to add and expand various types of knowledge. To do so, many knowledge units need to be defined in pieces.

 4. Ease of application: In relation to the above, it is required that the power can be easily customized for individual application fields according to the requirements of a specific user. To do so, as described above, it must be possible to create a library and accumulate and expand it by fragmenting individual knowledge units. In addition, there is a need for a mechanism that can easily deal with application fields based on the above-mentioned flexible automation control method without having to dictate a specific manual algorithm for the expanded part.

2 Means to Solve Lesson B

 In this section, the basic method of the present invention will be described, focusing on some of the key concepts in the automated structure creation support system.

2.1 Processing flow

 Before that, the flow of the whole process of this system is described.

 First, the user manually inputs one or more pieces of event data that are a type of initial input data to the system. This event data is referred to as Γmaterial information j here. An event is a description of an event that is composed of ginseng (moving subject, object, time, embankment). Here, assuming that the outline of the story of the fiction novel ft is created, for example, let's assume that the material information is (Kill Ichiro Kozuki 1 midnight 1 place 1). This is "Ichiro kills Kozuki at location 1 at midnight 1". This is one of the narrative structures expressing the meaning of J. Here, each element in the list is a specific narrative in each knowledge base. The system corresponds to an item, and a specific data value is stored in the item. By automatically introducing the structure of the entire story, refining it, and performing other processing, it automatically creates a structure.

 Further, the user sets values for a plurality of parameters (referred to as Γstory parameters overnight j) as a description of the required items that are used in the strategy for creating the story structure. There are multiple types, such as type *, * theme *, * theme *, * reality *, and each has multiple value candidates, so the user will select one of them. For example, you can specify values such as * type of name * = "fictional novel", * theme 殺 murder by state affairs,

 By using these two types of data as initial inputs, the system will automatically create a name from then on. The process is divided into three stages: core story one story story one story plot. The processing of these three-step swords is all realized by the same excision mechanism, but different physical structures are created depending on the amount of knowledge units used and the order of use. , Its construction is mainly caused by the achievement of the above parameters.

The system is roughly divided into four parts: the object creation management module, the object technique module, the object path module, and the knowledge base module. The basic way to create a story is The rules stored in the word strategy module determine the specific material techniques in the narrative technique module to be used by referring to the values of the narrative parameters that were initially input. This is done by repeating the cycle of executing a specific part of the story and expanding the story. The story moth road is best suited for each of the following stages: core story creation, story creation ^ pro, and story creation, and what is the value of the story parameter. Select a narrative technique and implement a specific narrative technique for any part of the story that is being developed.

For example, based on the above-mentioned Qin lumber information, ^Takahayakawa owned huge properties. Hayakawa got Ichiro as a child. Hayakawa had Kozuzu as a child. Ichiro wanted to monopolize Hayakawa's property. Ichiro killed Kozushi. Saya reveals who killed Kozushi. Police arrested Ichiro. (This is expressed in natural language for simplicity. The actual output is a story structure consisting of a hierarchical list format. The actual output by the execution system Is stated intently). A core story is the first template of a story that results from applying a single narrative technique to material information. In this case, a narrative technique that develops the minimum basic pattern of the story corresponding to the theme of "murder by heritage" is used. Thus, using different narrative techniques creates another core story from the same human power.

 Next, as a result of further developing this core story, for example, the following story is created. "Hayakawa owned a huge amount of property. Hayakawa had Ichiro as a child. Hayakawa had a child, Kozuki. Ichiro wanted to monopolize Hayakawa's property. Ichiro killed Kozushi. Ichiro robbed Koizuna of money, Saya exposed who killed Kozuka, police searched for -ro, police confirmed Ichiro, and c. Police handcuffed Ichiro, Police arrested Ichiro, Police detained Ichiro. "Here, Storiichi means an era based on the chronological order of events. In other words, in the above example, time progresses straight from the first event to the ft 事 象 event. The story is created by repeatedly applying several narrative techniques to each event in the core story, and is an art line that follows the time sculpture of the entire story. Means

Further, this story is developed as a plot, for example, as follows. ^ΓHayakawa got Kozushi as a child. Later, when his wife arrived quietly, he inherited his property, and was pleased to own it. Hayakawa's wife gave birth to Ichiro, so Hayakawa had Ichiro as a child. Ichiro killed Kozuki. When one person told another,

—Hiro wants to monopolize the property, killing Kozushi and treating the corpse. Police arrested and detained Ichiro because one person told 811 that Saya had revealed who killed Kozushi. j This project begins where the tranquility is born, goes back to the past, proceeds to the murder of the tranquility again, then goes back to the past, tells the reason, and the time proceeds again, In this way, hour M is zigzagging back and forth between pass and present. The time order in the story is a story, but in the expression of the real R material, it is often said that it is not told as it is, but is transformed in various ways according to the viewpoint of the rider. Therefore, a plot means the developmental mechanism of an event in an actual story.

 In this way, based on this system, based on Junichi's fragmentary event group (one in this case),

-6- It is structured as a successful and poor narrative structure based on a particular theme. As a process, a story structure is created from a single event group based on the differences in story parameters in the order of core story, story, pro, and story.

 Are the stories created to be greatly expanded by the winter building of the narrative techniques, each of which is a piece of narrative knowledge of story making? It is mainly recruited to the story parameter boxes provided by the user. To a single story structure.

2.2 Outline of Method

 In the automated structure creation support system, the knowledge processing required to create a story structure is integrated into the process of creating a story structure as a tree structure (hereinafter referred to as a “story tree”). It is constructed in an integrated manner, focusing on techniques that can be embedded. In this method, the creation of the story structure corresponds to the expansion or transformation of the story tree, and the mechanisms for these operations are at the center of the method wheel. Such a mechanism is constructed based on two types of knowledge structures: manual knowledge for expanding or transforming the story tree in a convenient way, and rule-based knowledge for controlling its use. . Of these, the former style-type knowledge is referred to as the "story branch method" as described above, and the latter rule-type knowledge is referred to as the "product-strategy j" as described above. Handicraft requires a knowledge base that stores concepts and other knowledge for the narrative expression.

 The process of creating a story structure can be roughly divided into two parts: the creation of the conceptual structure (herein called the story structure) and the creation of the surface s-words. Corresponds to the process of what to say and how to say in language generation, where the story structure means the internal representation of the intentional structure in the story within the computer. The invention treats the term narrative as follows: e. Narrative simply means not only the narrative as a surface natural language level, but in a broader sense, including its structural aspects. The story in the meaning is used in correspondence with the English word N a. Rr Ά tive そ し て And the whole story in such a broad sense is divided into several structural levels and considered. Each story , Professional, '/ Bok, co-Nsu Torakushiyon, are to be referred to by use of special ^ that Tex me.).

 Figure 1 shows the basic method of creating a tank structure. The technical points of this method can be summarized in the following five items.

 1. Divide the conceptual structure of the story into two parts: Divide the conceptual structure of the story into two parts, story and plot. Among these, a story is a structure based on the temporal pyogenesis of an event, while a plot means a structure that is transformed according to the structure of an expression as a story.

2. The process of creating a story structure as a physical tree and its work: The conceptual structure of a story is expressed as a story tree with one vertex at all levels. The terminal nodes of the story tree correspond to individual events. The other nodes correspond to the relationships that control the lower nodes. Stories and stories are a quick link between the end nodes of this story. Creating a story structure is an extension or transformation of such a thing. The main part is to expand the story tree, and in the part of creating the project, the _c- story technique, which mainly performs the transformation of the developed narrative as a story, It means a specific action to be taken.

3. Make things from the end of the work »ϋ 抟 ϋ 抟 に に 太 太 太 太 太 太 太 手 手 手 We call this a narrative technique. Each narrative branch method defines a specific way of manipulating the end of a narrative, each of which constitutes a fragmentary handicraft module responsible for a single task. ing. The main narrative technique for expanding narrative II is to use various types of relational concepts that can serve as nodes in the narrative tree, and to use events and partial segments in the narrative tree (hereinafter referred to as “partial end” in the narrative tree). Is called). On the other hand, the narrative technique for transforming botanical trees is based on a story tree that has been composed once. Using a viewpoint of a specific appearance or a pattern of development of a specific genre, etc. Add operations.

 4. A story moth scheme that controls the use of narrative techniques: narrative knowledge that means control to determine at what point in the story tree to apply which narrative technique to which part of the narrative tree Call. Narrative strategies are defined in fragmentary rules and are driven by control mechanisms. The description of the main rules refers to the story parameter j and the current state of the story tree that specify the characteristics of the story to be created in the condition section, and specifies the story technique to be executed in the conclusion section. As long as the user only sets a certain number of story parameters in advance, the system will automatically create a story based on those requirements. The story structure of the form desired by the user is flexibly created.

5. Creating a story structure using a network-like knowledge base: The expansion of a story is mainly based on a specific event that dazzles a part of a story tree or another event or subtree that has some relation to the subtree. This is done through the creation of a story tree, thereby extending the story tree as a whole. Recognition of such relationships for certain events or capital-ary tree, the value is performed through ⁷ Bok work-like knowledge base. In other words, each element (event, thing, thing, etc.) that constitutes the knowledge base has multiple characteristics, and this component and the description of another component that has a specific M The narrative technique creates events and subtrees that have some kind of M-factor with the events that were the target of the work, through the imaginary W-factor of the nature of the character.

2.3 Story structure creation process

 Creating a narrative structure consists of the following three tasks (Figure 2).

 1. Create Core Story: Create ft's first story tree from a set of one or more fragmentary input events. A fragmentary event set means a set of events that do not constitute the end of the story. The story tree first constructed in the story creation described below is especially called the core story in the sense that it is the first unit of ft in the creation of the contradictory structure. Same as creation.

 2. Create a story one by one: Expand the input story tree along with the time progress. This is the creation of the content aspects of the story.

 3. Pro, creator: Transforms a story tree that follows the temporal progress of human interaction into a sculpture that follows the composition of the sculpture, or text, of the narrative. Therefore, it corresponds to the creation of the expressive aspect of the story with respect to the creation of the story content.

These tasks do not necessarily stipulate the schedule of processing in which the processing of each task must be completely completed before moving to the next task. For this reason, we use task B leaves instead of g leaves. For example, the story to be processed is made into a story, and the processing of that part is handed over to the next project / creation, and when that is done, the task returns to the story creation task again. It is assumed that a pass is also possible. Or, first, conceive the thing ^ expression, that is, the professional ", u, and * f It is possible to create a good story content, story ¹ / one.

2. Narita-Expression of the conceptual structure of the story

 The conceptual structure of the story is expressed as a story tree at all levels. The terminal nodes of the story tree correspond to events, and the other nodes control lower nodes by some M factor. This is called the “r-relationship”. In the story tree created by each task shown in the previous section, basically, the sequence of events from left to right at the end of the story is equivalent to the core story, story, pro, and book, respectively. As will be explained, the target tree takes the form of a hierarchical list. First, each event is expressed as a list containing several pairs of sexes and sex values, with the verb concept (called the r-event concept j) first as follows: (For the notation, the following example shows one example. If the above conditions are satisfied, other methods may be used.)厲 Characters include characters, time, places, objects, etc. e The factors that can be the IS nature of these events are called r-story-off'sect.

 1. (<event concept> ((<attribute 1> <value 1>) <<property 2> <value 2>)

 <<Property n> <value n>)))

 Entities are high-order nodes for one or more low-order M or low-level events, as follows. This is shown in FIG.

 2. (<Relation 1> <Event 1> (<| »| Relation 2> <Event 2> <Event 3>))

 Combining events and M-persons in various ways creates a rich variety of story trees, or variations of the story created. The following list creates a new event, <Event 2 ′>, with 2 events, 2 events, and an M agent, <M agent 3>, and creates a partial tree controlled by <Relation 3>. This is an example of expanding the first story tree by using the following (Fig. 4). The partial tree that constitutes the main part of the story tree as a whole is called a “subtree”.

 3. (<M Section 1> <Event 1>

 (<Relation 2> (<| «Relation 3> <Event 2> <Event 2 '>) <Event 3>))

 —One event can be made into a different story tree using a few different relationships. For example, (Eat ((subject Taro) (target breakfast) (time morning) (place home)) ("Taro eats breakfast at home in the morning. J) A different tree is formed by combining with the events and sub-ends of the M that make up the M-factor.

 4. (Cause-Result

 (Suku ((Taro Tsubaki) (target belly) (time period) (place home))

 (Eat (subject Taro) (target breakfast) (time morning) (place home))〉〉

 5. (Cause-Consequence (Eat ((Taro)) (Target food) (Time morning)

 (Place Home)))

 (Satisfied (Taro Taro) (Target breakfast) (Time Morning)

 (Place Home)〉))

 6. (Sequence (Eat ((Taro Tani> (Breakfast)) (Morning) (Home))

 (Polish ((Taro) (target tooth) (time morning) (place home)))>

7.

 (Cause 1 Result (Eat ((Taro), (Breakfast)) (Time)

(Place Home))) (Satisfied (Taro Taro) (Target breakfast) (Time Morning)

 (Place Home))))

 (Cause-result (to

 ((Taro Taro) (Subjects, /, car) (Time #) (Place School))) (Suku

 ((Taro) (target belly) (time noon) (place school))))) In this way, the diversity of the narrative tree will be caused by the difference in the engagement applied to a certain event or subtree. .

 In many cases, the attribute of the event concept and other attribute values that make up the event have corresponding items in the knowledge base, and specific values are described in them. For example, the name of each item of the character knowledge pace, the object knowledge arrow base, the place knowledge base, and the time knowledge base is described as the gender value of the subject, subject, place, time, etc. that constitute the event. . In the case of Taro in the above example, attribute values such as date of birth and gender are described in the item “Taro” in the character knowledge base.

 2.5 Basic method of creating story structure

Story making is done through such expansion and transformation of the story tree. A skirting tree is expanded by combining a particular event or branch tree in the story tree with another event or tree that has some M factor. The transformation of a physical tree is performed by reorganizing the narrative tree or subtree from a specific viewpoint. Story expansion is basically possible for any node in the story tree. An extension of a story tree to a node other than the terminal node means an extension to a subtree of the story below that node. On the other hand, story transformation is basically possible for terminal nodes, that is, for any node other than a single event (ie, a subtree of a story). As described above, the intuitive knowledge for expanding or transforming a story tree is called "story technique j. A story technique is basically a single task. For example, if the narrative branch method is a type that extends a narrative tree, it is defined as one physical technique for each type of relationship that is valid for a certain event. The narrative techniques include not only the type that creates such a narrative tree, but also the elements that change the character of the narrative object, that is, the components of characters and objects used in the end of the narrative. In the end, any kind of intellectual knowledge used in the creation of a narrative structure, centered on narrative tree operations. Each of them is basically a narrative technique that performs a single task. The story structure as a whole On the other hand, the process of making a story shall be performed by a combination of the use of narrative techniques, but in the practice of using narrative techniques, it is natural that the strategy differs depending on the type of story to be created. Different kinds of knowledge are required to control the use of the narrative branch method, for example, the question B, which narrative technique is used for which nodes in the disjunction tree, is solved in the actual creation. need to come out. referred to as such ^Γ story iS shown the knowledge to make a decision process in the control for the story branch method ". As described above, the storyline iS must be used. The basic policy of what kind of object you want to create needs to be determined, and it is expressed as r object parameter j. . Therefore, the story SS stands for knowledge to control the specific use of the story branch method according to a specific story parameter combination. Ss »Abbreviation is a † d report that shows the story of each story and the current status of the end of the wis. It is expressed in the form of rules with the conclusion of the story technique to be specified, and has a separate controller for executing rules and resolving conflicts.

 The method of creating a story structure is thus composed mainly of two concepts, story technique and story strategy, but a knowledge base is also an essential component. For example, if a particular narrative technique creates another event that has some relation to one event in the object-reception tree, refer to the sex information of the components, including the concept of events in the knowledge base. When you change the nature of a component in an event, you actually do so for the corresponding component in the knowledge base linked to the event in the physical tree. In this way, the knowledge base exists mainly as a means for narrative techniques to provide basic data for expanding and transforming story trees.

 As described above, each narrative technique is not a technique that defines knowledge for a specific type of story, but a fragmentary technique that defines general narrative structure creation knowledge, albeit with different degrees of abstraction. It is a flexible method with versatility and extensibility, as it constitutes a framework that can be added and defined and added in combination. . For example, defining a narrative schema specific to a particular type of story. This is possible not only through narrative techniques but also through narrative moth schemes. For example, in a case where a story with a shorter and simpler structure or a story with a remarkably impressive structure is required, setting values for the length and complexity of the story parameters and defining rules that reflect them are necessary. You can knot. Thus, the method of wood invention solves the technical problems mentioned above *. In natural s-word generation research, tactical knowledge corresponds to knowledge for the task of creating a deep conceptual structure, while branching or tactical knowledge corresponds to knowledge for the task of creating a superficial natural B word. Often used. On the other hand, in the present invention, each level of the story tree, ie, story creation, and story expression, ie, “pro”, and story creation in the creation of the IS structure, is actually manipulated in some way to manipulate the story tree. We consider a hand-knotted weir to be a forensic knowledge, and we consider the knowledge for controlling the use of this forked weir to be a strategic knot.

 Below, I will explain the basic concepts of the story branch method and the story strategy.

 2.6 Concept of story branch method

2.6.1 Basic method

 The tactics applied to event trees in narrative trees to extend and transform them are called material techniques, which are based on one or more of the following events: Or it is awarded as an M number with a subtree as an argument.

 (<Name> <argument 1> · · · <argument n> <keyword value>)

The argument of the object technique for expansion is an event or a subtree. A new event or tree having this argument and some IWI relation is created, and a tree in which the user is connected by this M relation is returned. On the other hand, the transformation-object branch method uses the following: object: *: The whole or part of the argument is returned as an argument. Other types are those that combine or tie together multiple arguments, and those that change the attribute value of a particular narrative oashect contained in a tutor. Keyword is used, for example, if you want to specify a special case divided into _β

Usually, in the cycle of the story structure creation, the object 1§branch method is applied to a specific node of the story tree as an argument, and returns a new value obtained by expanding or changing the node. And update the end of the story as a whole by replacing it with this new value. For example, assuming that the story tree as a whole is now (R 1 E 1 E 2), as a result of applying the story technique as (TECHE 1) to event E 1 in this, (R 2 E 1 E If the value 1 '> is returned from the narrative branch method, the result is replaced with the original argument E1 to update the updated narrative tree (R1 (R2E 1 E 1 *) E 2) By repeating this, the story tree is gradually expanded or transformed, and the image of the story tree update (extension in this case) via the story branch method is shown in the figure. See Figure 5.

 One of the major advantages of using narrative techniques is that the ability to use multiple narrative branch methods for the same object allows the entire narrative structure to be created according to the diversity of its definitions. Is the diversity of This method does not predetermine which narrative technique to use for a node. Therefore, by applying various types of object-branch methods to each node that constitutes an object | §end, any node in one story tree is expanded and deformed in various ways, and as a whole It is possible to realize a variety of story structures. Figure 6 shows how several developments are possible by applying different narrative techniques to the same input. The definition of narrative techniques can use a variety of forms and methods that are bound by certain theories and methods. Many conventional story generation systems generate stories by reusing the same logic and techniques recurrently, but this method uses arbitrary methods in the story tree at any time. It is more flexible and dynamic in that it can be expanded and transformed in any way (narrative technique).

 Another advantage is that additions, extensions, changes or combinations are optional. This is basically a modular approach where each material technique performs one task, and the interference with other material S techniques or with the 1W surface of story making. Based on the feature of not having. Also, algorithms for creating story structures specific to particular story types are not fixedly defined, but libraries of material techniques are merely a collection of general and fragmentary definitions. However, depending on how well it is used, it can be adapted to the creation of various types of stories.

In addition to this, the application of the narrative technique is not necessarily determined at the terminal nodes of the narrative story, but may be at other nodes, that is, subtrees. There is also a feature that it becomes possible. While the terminal nodes in the story tree are progressively refined, it is possible to create them manually, but on the other hand, the story to the node of the story tree '.' If you apply the technique repeatedly, the story tree will gradually grow upward. If the former corresponds to the story of the story, .'butown generation (Fig. 7>), the viewer corresponds to a kind of bottom-up (Fig. 8>). The choice of nodes to use a certain _e- story technique is done through the execution of a story moth scheme.

 2.6.2 Classification of story techniques

 * The system is divided into the following types based on the differences in knowledge * used.

1. Narrative technique using a local cabinet between concepts: Create another event or a branch tree with a specific local relationship with the event or part end of the argument, and return a value that combines the two. For example, there is a narrative branching method that uses knowledge that is used as a local relation between concepts such as “reason” or “cause” relation, and “result” relation. The definition of this kind of local M-factor it is mainly described in the context of the event concept in the arrowhead base. 2. Narrative techniques for creating narrative objects x-cuts: characters, objects, places. Time-of-day narratives that appear during events, such as changing the attribute values of r. Or create a new instance of a story object. For example: A. Change the age of a person or set the character's current occupation. This is done for the corresponding climb in the knowledge base linked by the link.

 3. Narrative techniques using the method of the narrative of the narrative: Extensions aimed at impressing the narrative-There are physical techniques that use the art of the initiative for transformation. For example, reconstructing a story or a part of it from the viewpoint of a specific character who climbs there; There are narrative techniques.

 4. Physical techniques using the macro structure of the story: This is a story technique based on a special M-organization that controls more concepts rather than a local M-organization between two concepts such as 1. For example, “scripting”, which is a process that expresses a specific event in the form of a process composed of a small number of sub-events with a smaller number of granularities and forms a sequence of sub-events, a narrative technique using an M-person, The event is regarded as the main building for the subject, and is developed by the rapid chain of farming acts to speed it up. In addition, there is a “tema pattern” that supervises the entire theme of the story, a “plot pattern” that defines a story pattern unique to the genre, and a story branching method that uses the composite story M section.

 5. Narrative techniques as the definition of a narrative schema: For some types of narratives, certain narrative techniques can be applied at a fixed location. In such a case, a plurality of narrative branch methods can be combined into one independent object S technique, which is a framework that defines the method of narrative. Call.

 2.7 Concept of story strategy

2.7.1. Basic method

 In using the narrative technique, it is necessary to determine which narrative technique applies to which node in the object advisory tree at each point of its creation. The knowledge used to determine the specific use of such narrative techniques is called “story narrative”. In other words, the article advisory strategy includes the next node in the current story tree to be expanded or transformed (this is called the “story branch method application point” or “growth point”), and There are two types: those that determine the narrative technique to be applied to the node.

The narrative PS consists of a set of these two types of rules and a control mechanism for controlling these rule groups. Each rule in the story strategy consists of a conditional city and an execution unit. The condition capital is mainly composed of parameters that define the betting characteristics of the story to be created, and these parameters are called r story parameters. On the other hand, in the execution unit, there is a K predicate of a node that can be used in a feasible proof technique or a word branch method, that is, a point for a story technique. The story parameters used in the condition part of the rule include * theme *, * length *, * character uniqueness *, * »article *, * view *, * poma * other species There is an amount, and the value is set by the user at the beginning of the story creation. Each story parameter has a plurality of value candidates. For example, * length * is long / medium / short, * character unique figure * is 図 Z medium / low. Accordance connexion, as such sets created story in such a way as to满足the value of the story parameters is performed, there are necessary things ¾戰略rule is configured _e The first type of narrative strategy, the method of determining the point of application of narrative techniques, can be any of the following concrete implementation methods, from simple balance to more complex control.

 1. Simple formal method: This is a method of determining the application point of the story technique by changing the nodes in the story tree in a formal manner at a certain level. For example, move the narrative branch method point from the terminal node (event) at the left end of the story tree to the right with I-spurt, and when it reaches the right end, repeat the same processing for the newly created event (Figure 9) (Similar processing may be performed from the right pheasant tree to the left.) It is possible to use the method as a point of use (Fig. 10) or a combination of the two methods. There is a method of intensively processing only the terminal node of.

 2. Focusing method: It is a method to set the focus to be expanded intensively in the skirting tree. For example, it is conceivable to set a particular character as the focus, and to focus on the event in which it appears as the application point of the physical IS technique. By switching the focus during the creation, you can create a story part centered on another character or other story object.

 3. More complex strategic method: This method refers to multiple story parameters, the current story tree shape, etc., and determines the optimal story branch method point for each point in the creation. The above two methods can also be regarded as two alternatives in such an IftBS-like determination method.

 Next, the narrative to drive the narrative technique is based on the value of the narrative parameter, the amount of the current task such as story creation, pro, and zol, the type of the target node (event or part). Information such as the node that controls the branch tree) or the position of the target node in the story tree (mainly the depth repertoire) is required. For example, if there is some * theme *, and the * theme * is a story, it is thought that the whole story needs to be supported by this * ema *. It is desirable to use the theme pattern at the top level of the IS tree. In this case, it is necessary to use the theme pattern at the node of the story tree or at the node of the story. Also, in this case, if the theme pattern was used at the stage of core story creation, the subsequent narrative composition would have to be done exclusively for nodes other than the top-level nodes. Because this type of information may be needed, the conclusion of the narrative strategy rule should specify a specific narrative technique and be able to describe information that will serve as constraint knowledge for subsequent creation. I will need it.

The physical parameters are classified into those related to physical structure, those that apply M to the world structure (characters, space, and time), and those that apply M to expression. The parameters that are categorized into the story structure are directly related to the composition of the box tree itself! Echoes. In addition, we are in charge of WI, which is the main part of the story. For example, the * theme * mentioned above implies the use of a particular theme pattern, and the * narrative * controls the use of knowledge to develop events specific to the IS, such as entities. On the other hand, the expression strategy is a parameter that is more strongly related to the narrative of the narrative expression. For example, * viewpoint * is a specification of the type of viewpoint that is the main subject of expression of the object, and this affects the structure of the professional ". The world structure, on the other hand, specifies the types of narrative objects and other characteristics of the narrative composed of events. However, if W example there are also parameters on the saturation »the opportunity ¾ at the end of the story * registered person ^ -. 3R 0忤* eyes in W铕末." - plan M engagement and M Hayashi and are _r 3.2.7.2 Story structure creation cycle

 The creation of a story structure based on story strategies and techniques is basically accomplished by repetition of cycles as shown in Fig. 11. The first type of narrative, ¾, then applies some narrative techniques to determine the nodes to be expanded and deformed, that is, the application points of the narrative techniques, and then the second type of narrative strategies Determine and execute the story branch method to be applied to this. Then, the execution result is combined with the story tree as a whole, and the cycle ends. This is repeated until the termination condition is dropped. Basically, this process is performed from the creation of the core story to No. I. (In this case, we decided on the point of the material technique and the technique, and then decided the narrative technique to be used quickly. However, there must be a reverse sculpture in which the next narrative technique or candidate to be executed is determined first, and then the applicable point of the narrative technique is determined. It is also possible that the selection of the story is also determined by the story strategy.There is a great deal of freedom in controlling the story creation, including that the creation of the story structure does not necessarily have to be done step by step from the creation of the cores story. The method is structured to allow for these degrees of freedom.) The processing of the story strategy includes resolving conflicts between executable rules, processing rules that have been used once (reusable, unusable or priority processing, etc.), and end conditions for each task of creation. Some questions II need to be resolved.

2.8 Summary

 1. Process of creating IS structure: The process of creating a story structure is defined as consisting of three tasks: core story, story creation, and plot creation. Of these, the former two are responsible for the creation of the story contents, while the professional and zoto are responsible for the creation of physical expressions. All of these are treated as a unitary process of expanding or transforming the story tree.

 2. Narrative expression-Narrative tree: A narrative is expressed as a narrative tree in which the event is the final contraction node and the subordinate nodes are the other nodes. Each event consists of a list of attribute-values of event concepts and other narrative object concepts, and the event concepts and attribute values are linked to the knowledge base components *.

 3. Physical structure creation method: Physical structure creation is performed through expansion and transformation of the story tree. The expansion of the object tree corresponds to the creation of the content of the story, while the transformation of the story tree corresponds to the creation of the object box representation. These processes are performed by a narrative technique, which is a set of fragmentary handicrafts defined for performing operations on the object a tree. In doing so, an object consisting of fragmentary rules and their control mechanisms controls the use of narrative techniques. The narrative structure is created by repeating a cycle in which the narrative warfare determines the point of the narrative technique in the bargaining tree, executes a specific narrative technique, and combines the result into the narrative tree as a whole. Done.

 4. The method of the object-branch method: The function of the narrative technique is as described above, but it is a technique that uses the local relationship between concepts. The technique of creating a narrative object, the rhetorical branch of a narrative It can be divided into five types: techniques using techniques, techniques using macro structures of «» », and techniques as narrative schemas. The article advisory law can be freely defined and added.

5. «J» lfe abbreviation method: In order for the narrative ift abbreviation to work, it is necessary to set a value to a material parameter that defines the characteristics of the side of the narrative to be created. Mono瑭parameters. Compounds ¾ at the end of «I elephant M bad guys. Which M the characters and time on the structure of the beginning of the story world, minute, such as the IWI the bad guys in the representation of Mono梧» _c that can be One or more fragmentary phenomena are human-powered by the above-mentioned zero means for constructing an automated story structure creation support system. Based on that, the conceptual structure of the story is basically converted to a core cost. A system that can be created for each stage of the tree, store, store, professional, and software is realized. This output gives the input fragmentary phenomena meanings such as causality, refinement, and context, and also provides the user's request in the form of story parameters. By specifying, the story structure of the tie corresponding to them is automatically created. Users can use this output story machine as a basic data. It can be further converted to a detailed surface expression such as natural language, or used as a hint for creating various stories. It can be used to support ideas. It is also possible to use this system as a narrative human interface for educational systems. By simply changing the settings of the material parameters, different types of narrative structures are automatically created, so that it is possible to repeat the work * for each of these various purposes in a short period of time. It contributes to improving the efficiency of use, supporting creativity and imagination abilities, and making the interface friendly. BRIEF DESCRIPTION OF THE FIGURES

 Figure 1 is a diagram showing the outline of the method of the story structure creation automation support system.

 Fig. 2 is a diagram showing the process of creating a story structure in the automated story structure creation support system. Figure 3 is P1 showing an example of a story tree format.

 FIG. 4 is a diagram showing another example of a story tree format.

 Figure 5 is a diagram showing an extended form of a story tree.

 Figure 6 shows how story trees of different formats are created from the same input.

is there.

 FIG. 7 is a diagram showing a state in which the story tree is expanded in the lower direction.

 FIG. 8 is a diagram showing a state in which the story tree is expanded in the upper direction.

 FIG. 9 is a diagram showing, as an example of a technique for determining the application point of the story branch method, a method in which only the terminal node is used as the application point first.

 FIG. 10 is a diagram showing another example of a technique for determining a point of application of a story technique, in which a top-level node is used as an application point in a track number.

 Fig. 11 is a diagram showing an outline of a story structure creation cycle in the object structure creation automation support system.

 Figure 12 is a diagram related to the system configuration and the processing flow, showing the system configuration and input / output relationships in the port structure creation automation support system.

 Figure 13 shows the operation style of narrative thick by the combined narrative branch method for one event.

 Figure 14 shows an inclusive narrative branching method for events in a basin! Is the operation format at the end.

 Figure 15 is a diagram showing a narrative operation format using the element-substitution type-branch method for a single event.

 Figure 16 is a diagram showing the operational form of an object | § 术 by an argument-replacement type narrative technique for a single event.

-1B- 1 || 17 is a diagram showing a narrative type of narrative operation based on an introductory narrative branching method for phenomena.

 Figure 18 is a diagram showing the operation style of story tree by (1) deformation for one event, (2) story technique.

1 9, _c Figure 2 0 shows an operation form of the story wood by-linked story technique intended for the subtree, the揀作format story wood by-contained story technique intended for the subtree FIG. Fig. 21 is a diagram showing the operation format of a story tree by an element replacement type story technique targeting a subtree.

 Fig. 22 is a diagram showing the operation format of a story tree by the argument substitution type story branch method for a city tree.

 Figure 23 is a processing flow diagram showing the procedure for generating a story by the automated story structure creation support system.

 Figure 24 is a diagram in which the opening scene in the novel of the analysis example is composed of a story tree.

 0 25 is the first figure in which the novels of the analysis examples are constructed as professionals and / or trees.

 Fig. 26 is a second diagram in which the novel of the analysis example is similarly configured as a professional's tree.

 Fig. 27 is the third figure, which is also composed of the novels of the analysis example as professional and ト trees.

 Fig. 28 is the fourth diagram in which the novel of the analysis example is similarly constructed as a plot.

 Fig. 29 is the fifth diagram in which the novel of the analysis example is similarly constructed as a professional and a sot tree.

 Fig. 30 is the sixth diagram, which is also composed of the novel of the analysis example as the end of the program.

 Figure 31 is the seventh diagram, which is also composed of the novel of the analysis example as a professional, ',' tree.

 Fig. 32 is the eighth diagram, which is also composed of the novel of the analysis example as a professional.

 Figure 33 is the ninth diagram in which the novel of the analysis example is similarly constructed as a plot tree.

 Figure 34 is the 10th figure, which is also composed of the novel of the analysis example as a professional tree.

 Fig. 35 is the first diagram in which the novel of the analysis example is similarly constructed as a plot tree.

 Figure 36 is the first figure in which the novel in the analysis example was configured as story thick.

 Figure 37 is the second diagram in which the novel in the analysis example is configured as a story tree.

 Figure 38 is the third diagram in which the novel of the analysis example is configured as a story tree.

 Figure 39 is the fourth diagram in which the novel in the analysis example is configured as a story tree.

 Figure 40 is the fifth diagram in which the novel of the analysis example is configured as story II.

 Figure 41 is a diagram showing the deformation relationship between the plot tree and the story tree.

 Fig. 42 is a diagram describing, in a physical tree format, an example of a core story, that is, an example of a core story 1> created by the material structure creating execution.

 Fig. 43 is a horizontal view showing the process of creating a physical structure by using the real K.

 Table 1 shows the main species 18 of the story branch method and their functions! ! This is the first table arranged as follows. Table 2 is a second table that lists the main naming methods ««! And their respective functions.

 Table 3 is the third table that also sorts the seed value of the main β-branch method and each function as one R.

Table 4 is the first ft table that lists the story parameters »and the main items | §Parameter seeds and their specifications» as a list. Table 5 is a second table that lists the story parameters, the types of the main story parameters, and their definitions.

 Table 6 is the first ft table to show the analysis results (summary at the plot level) of the plots and plot structures of novel works taken as analysis examples.

 Table 7 is the second table illustrating the analysis results of plot structures (summary at the level of the box 'and the box) in a novel work also taken as an analysis example.

 Table 8 is the third table that illustrates the analysis results of the professional structure of the novel work, which was also taken as an example of analysis.

 Table 9 is the first table that illustrates the analysis results (summary at the story level) of the story-by-story structure of a novel work taken as an example of analysis.

 Table 10 is the second table illustrating the results of the story-by-story structure analysis ("summary at the story-level") of a novel that was also taken as an example of analysis.

 Table 11 is the third table illustrating the analysis results (summary at the story level) of the story structure in the novel work also taken as an analysis example.

 Table 12 is the fourth table that illustrates the results of story-structure analysis (summary at the story level) in a novel that was also taken as an example of analysis. BEST MODE FOR CARRYING OUT THE INVENTION

 In this section, we describe a system construction method of a story structure creation automation support system, and an experiment of creating an article advisory structure using a real K system.

 In this system, the story technique expands or transforms the story tree in whole or in whole under the control of the story ift, against the background of a network-like knowledge base, and the story creation management module summarizes the result as a whole. Create a narrative structure by repeating the cycle of integrating with the thing advisory tree. Here, we will first show the configuration of a system based on the above-mentioned problem solving means, and explain in detail the mechanism of each of its components, namely, the knowledge base, the story technique, and the story moth scheme. Next, we give an overview of the story creation process in the system, using an example of creating a story structure in the style of a novel.

 1 System configuration

 As shown in Fig. 12, the automated system for creating a story structure is composed of the following four main modules.

 1. Story creation management module: First, set the initial values required for the core story, story, and plot creation tasks. Then, a story tree or a fragmentary event group that is currently being processed is given, and the processing is delegated to the name moth abbreviation module and the story technique module. When a merchant is returned by the rain module, it usually expands or transforms the object IS tree by replacing this ancestor with the nodes in the current narrative tree that have become points for the narrative technique. This process is repeated until the end condition of each task is satisfied.

2. Physical strategy module: Includes physical strategy rules and their control mechanism (physical strategy control mechanism). Once the point of narrative technique success and the narrative branch method to be executed are determined, the execution of the object branching method is entrusted to this narrative technique in the narrative technique module. This module realizes automation of story structure creation. 3. Story branch method: Contains a library of story techniques. At the point where the narrative technique is determined by the Compensation Law strategic rules, the material techniques in this library also determined by that are used.

4. Knowledge base module: Seven types of concept arrowhead base of each concept of event, thing, thing, condition, person, place, and time, script, causal M, goal total, Ββ, mental It consists of a rule-based knowledge base for reactions and theme structures. The latter type of knowledge base is referred to herein as the "story knowledge base." The concept knowledge base is a set of frame-form concepts, and the link between the concepts is a network. It is stretched. On the other hand, the narrative knowledge arrow pace is a set of rules for creating a concept with a particular concept and another concept with a specific relationship with it. This rule name is mainly described as the slot value of the event concept in the concept knowledge pace. The experimental system is described in the programming language IfCommonLisp. C ommon L isp language Ri beneficial languages der for list processing, such as. Strings, but _c are used often in artificial intelligence research, the present algorithm is rather a language-dependent, the other programming Nge Language It is of course possible to realize it.

 The notation of each component in the system is agreed as follows. First, the name of each branching method is expressed as tech <proper name>. The notation for the name of each story strategy rule is str & <unique name>. A frame in the conceptual knowledge base (the name of an abstract type, such as "station") is, for example, objS! Beer. The symbol that represents the type of concept (here, obj) and the unique name are Ϊ symbols. On the other hand, instances (names of concrete values, such as “Kyuko DT” for the above “ku”) use the two connected with an & symbol, such as ob.j & beer1 .

2 Outline of story making process

 Human power into the system is (1) a set of values for the story parameters and (2) a set of one or more fragmentary events, ie, events that do not form a tree structure. These are entered first by the user. (2) means the material that first triggers the creation of the system's narrative, rather than the semantic content that should be spoken by the system, and is referred to here as "" material information "". Based on these, more and more core stories are created, and then stories and pros are created. In the current implementation, these are processed step by step with this tongue. However, looking at each task unit does not necessarily mean that the story is elaborated from the top down. As noted in the previous chapter, when expanding or transforming a story as a story tree, it has the characteristic that any node in the story tree can be processed equally. Therefore, for example, it is possible to create a structure in which this is gradually refined in the lower direction based on the core story, and at the same time, the tree is gradually extended in the upper direction using the core story as a lower node of the story tree. It is possible to create in the direction of going. Nonetheless, there is a degree of freedom that allows not only one-way creation but also creation in various directions based on various nodes.

The heels of story creation in each task are as follows. First, when the user manually inputs the material information and the value of the story parameter through the plow of the story creation management module, the control is transferred to the material 捂 & brief controller «and the core task, which is the first task of ft, is created. . Here. Story | Outline The rules of the story branch method to be applied to the material information are determined by the rules, and the _e -coast story creation task that executes this task. Processing ends once the story end is constructed. . In the task of story creation and brochure creation, the variables required by the story creation management module are used. After the value is set, control is transferred to the story strategy control mechanism. When the application point of the story technique and the story technique to be accepted are determined, the story technique in the story technique library is executed, and the result value is again processed by the story creation management module in the story tree as a whole. By replacing the target subtree, the story tree as a whole is expanded or transformed. Again, the cycle of the narrative determining the application point and the narrative technique by the narrative is repeated until the end condition is satisfied. In this way, in each task, the processing of determining the application point of the story branch method, determining the story technique, executing the story technique, and expanding and transforming the entire story tree are performed in common.

3 Knowledge base and conceptual network

 The knowledge base is broadly divided into a concept knowledge base and a narrative knowledge base. The concept knowledge base is used to store the attributes and values of various concepts used as components of events in a story.Each concept is a set of lists consisting of sex / value pairs. Defined. There are two types of concepts, those that mean the generic name of a class and those that mean its concrete substance. Here, the former is called a frame and the latter is called an instance. Conceptual knowledge bases are categorized into the following types.

 1. Event concept knowledge base: A knowledge base that stores verb concepts. The concept of events is an essential element in the composition of all events, and is the most basic purple essential for the development of a story.

 2. Knowledge Conceptual Knowledge Base: This is a knowledge base for the concept of a physically existing thing, that is, a substance. In many cases, the concept of a thing and the concept of a thing represent two aspects of the same concept (for example, a school as a building and a school as a matter). Include in knowledge base. Equivalent to a noun with physical mass.

 3. Thing concept knowledge base: A knowledge base for abstract things (things) that do not physically exist. It is represented by the noun form of the verb concept.

 4. Modified Concept Knowledge Base: A knowledge base of concepts for modifying other concepts, and is equivalent to adjectives and adjective verbs.

 5. Person concept knowledge base: Knowledge base that stores instance information of characters. Each instance sweeps into an occupational frame on a knowledge-based basis.

 6. Time concept knowledge base: A knowledge base that stores time instance information. The information that is used for time divisions such as morning and noon is included in the concept knowledge base.

 7. Space concept knowledge pace: This is a knowledge base that stores instance information on spaces such as specific lands and shops.

 The format of the concept definition is explained below using actual examples in the system.

Establishing the concept of an event

 (defFraae evcX male; korosu name

 '(Kill view

 ((type (frame)) distinction between frame and instance

 (naie (evcX kill))

 (agt ()) subject

 (obj ()) Object

(l oc ()) location (tin ()) time

 (res (rule§inga-korosu)) result 閱 the name of the corresponding rule in the knowledge base

 (cau (cau! korosu)) Name of the corresponding rule in the reason-related knowledge base

 (tme (rule ^ smen-karosu)) Name of the corresponding rule in the mental reaction knowledge base

 (gpl (pin! karasu)) Eye Building -Keisumi ¾Name of the corresponding rule in the base

(scr (scr! shimekorosu) ^ Name of the corresponding rule in the Suzuri knowledge base

(the (thm! isari-sauzoku-niyoru-satsujin)) ；； ： Pair in the theme pattern knowledge base

 The name of the corresponding rule

 (up (evc 赏 punishment / crime)) ;;;

 (ako-dn (evc¾ strangle to kill evcX, beat to kill evc, kill to death, evc to assassinate, kill evcX, kill))

: ;; Event concept showing a specific method

 (con (evc¾ revive))) ::: Concept of control event

This is a. ^R be "ί column of the definition of the frame of the gutter ό event concept. evc kill is the name of this frame, where "kill" means the form displayed during the event ^ :. From the third line, attribute-value pairs are described. Of these, each of the properties from agt to tim can be used as the required purple when an event is created. For example, an event force, such as (kill (agt agt & ota-nobimaga) (ob.j agtisuzuki-yusule) (timt & asal) (loc loc & suzuk u ke)) is composed. As the malleability value below res, the names of rules and other event concepts in the narrative knowledge base associated with this event concept are described. This means a link indicating the W staff between event concepts. The narrative technique expands and transforms events and subtrees that include this event concept, using the rules of these rules and concepts.

<Example 1 of definition of person concept>

^ def Instance agt & suzuki-yusuke

 '(Yusuke Suzuki

 ((type (instance))

 (nane (agt & suzuld-yusuke))

 (Return (th child)); Frame name to which this instance returns

 (Last name (Suzuki)); attribute value is constant

 (First name (Yusuke))

 (Occupation (thX elementary school student)); Attribute values are frames in the concept knowledge pace

 (Age (9))

 (Sex (thX male))

 (Income nil)

 (Study IS nil)

 (Family size (4))

 (Father (agt & suzukto shigeo))

 (Mother (agt & suzukto yuriko))

 (Brothers (Keiko Suzuki))

 (Grandfather nil)

(Grandmother nil) (Residence (Midori Ward, Yokohama City))

 (Honmakuchi (Midori Elementary School))

 (Personality nil)

 (State (raodX empty «)))))

<Example 2 of the definition of the concept of a person>

(def Instance agt & ota-nobunaga

 '' (ota-nobunaga

 ((type (instance)

 (name (agt & ota-nobunaga))

 (Return (agt¾ new employee).)

 (Last name (Ota))

 (First name (Nobunaga))

 (Occupation (t Sarah Riman))

 (Age (18))

 (Gender (th¾ male))

 (Income (3000000))

 (Study S (obj¾ 离 school))

 (Family size (D)

 (Father nil)

 (Mother nil)

 (Brother nil)

 (Grandfather nil)

 (Grandmother nil)

 (Residence (Uji City, Kyoto Prefecture))

 (Work location (Kyoto Kogyo))

 (Personality nil)

 (State mod busy)))))

 The previous example is an instance of the instance of the person to be killed, named agt & siizuki-yusuke. This is equivalent to the instance of the frame named thX child included in the concept knowledge base. Each) »The value described for gender may be the name of another component in the knowledge base (for example, thX elementary school) or a simple constant (for example, Suzuki).

<Example of definition of time concept>

'(Morning

 ((type (instance))

 (naiie (tin & asal))

 (K morning)

 (Year (1994))

 (Mon (September))

 (Day (2nd))

■ Α- (Time (7 o'clock))

 (Minutes (30 minutes))

 (Seconds ())

 (Division-—day (th¾morning

 (Season is 11¾ 晚 summer))

 (Event ( ) ) ) )

<Example of the definition of the concept of space>

(def I nstan ce obj & suzuki-ke

 '' (Suzuki family

 ((type (instance))

 (name (abj & suzuki-ke))

 (Return (ab, private house l oc¾locat ion))

 (Location (Midori Ward, ^^ City)))))

 As described in the description of the event concept above, by referring to the attribute value of the event concept, it is possible to directly search for an event concept based on a relatively simple relationship such as the opposite concept or a similar concept. For example, in the above example of the concept of events, "killing" is a method of realizing the concrete way of realizing "killing", such as "killing", "hitting", "killing", "assassinating". It is defined that "j which kills" is defined, and "resurrection" is the target concept of "killing". To describe as an attribute value of a general concept knowledge base, such as the successor to the event, the causal M, and the general concept knowledge base. This is described as a rule in the base. For example, if the definition of an event concept that is causally related to a certain event concept, it is necessary to create different event concepts depending on the difference in attribute values in the vehicle phenomena including the event concept, and this must be created in the event concept knowledge base. If it is directly expressed as the attribute value in, it becomes popular. Therefore, the base of the definition of such a complex relational concept, the attribute value of a specific concept describes the name of a specific item in the word knowledge base, and by referring to it, Let's create the concept of M-person. For example, in the example above, the causal M (result and reason clerk). The specific components in the narrative knowledge base of each of the mental reactions, the metropolitan one-planning W clerk, and the scrib theme pattern are "kill j" Each item in the narrative knowledge base is expressed in the form of rules, and the condition part of this rule describes the items that need to be referred to in the relevant concept. Conclusion To be able to output the concept of Part 11. There are the following types of narrative knowledge bases.

1. Script Knowledge Base: Includes rules for creating scripts that develop target events as sales of lower-level abstract events. The script, if _t e is supervised by a succession w engagement, "" strangle to death "that event, pouncing r, strangle, suffer, choking to. To氕艳, are deployed on the speed chain that is the script of the event of death".

 2. Causal M-knowledge base: Contains rules for estimating the cause of an event or the consequences of it. For example, "The reason for the arrogant J is r working J, the business is" successful ", etc. The result of the throat r drying j is" drinking "a drink.

3. Goal Total B «¾Pace: For the purpose of a certain elephant. Includes a sleep line ¾HI 'to make a' final * 'to fit it. For example. ^Γ «? In order to "get", you must "work" in your heart ^ As a result, if you succeed, you will not make money if you fail.

 4. Theme pattern knowledge base: Contains the rules for creating main patterns that include certain events. For example: "One version of the theme, Murder by Succession J, owns a Γparent or 荑 large property, and one of the children kills his brother to monopolize it or the murder is exposed. He is arrested. "

5. Story-related knowledge base: Contains rules that create a bank of events based on a story and developed from the story. The story W engagement, "prohibition - ^violation", Γ perpetrators - Fixed "," instruction - compliance "," Problem One solution ^", Γ desire - sufficiency", and the like. The above-mentioned “r-building-plan” relation can be considered as a kind of story M section. For example, `` In one example of the offense-elimination j relationship,

A pattern is created that consists of “recovering” (dissolving) the (perpetrated) object and awarding the reward.

 6. Compound story-related knowledge base: Based on an event, it contains rules that create a quick chain of events developed by the compound story M section.

 7. Mental reaction knowledge base: Contains rules for creating mental reactions that occur with the occurrence of events as external actions. Mental reactions are expressed as a concept of modification. For example, a “broken” event may result in a mental reaction such as “pain”, “painful”, or “discomfort J”.

 The collection of concepts in the conceptual knowledge base constitutes a network of frames / instances / networks. As mentioned earlier, each concept has some properties that define its properties, but in many cases these properties are linked to other concepts. In particular, the attributes of the event concept may describe the name of this concept and other ideas that have a specific M role, or the name of a rule in the narrative knowledge base . This makes it possible to directly search for other concepts that have a specific relationship with this creed, or indirectly obtain related concepts through the rules in the narrative knowledge base. In the latter case, other event concepts having some relationship with the original event concept and the sequence thereof are calculated on condition that the original event concept has a value. The nature of the M family in such event concepts is used in the definition of narrative techniques.

 4 Narrative techniques

 4.1 Definition of story technique

 The narrative branch method is defined as an I »! Number that returns an event or tree with one or more elephants or narrative parts of the narrative as arguments. As mentioned above, many narrative techniques perform calculations by using the link M between components in the knowledge base. Each component in the conceptual knowledge base is represented in the form of a frame with multiple attributes-values 衬, and the attribute value is often the other component in the conceptual knowledge base * or a specific rule in the narrative knowledge base. Linked to. The main type of the object 1§branch method is to create a new output W report by taking this link and searching for other concepts that have a specific relation to the argument. The argument of the narrative technique in the narrative creation cycle is the application point of the particular narrative technique in the narrative tale, which is the current sweater, and this node is disguised as the inclination given by the narrative technique. The whole story tree is expanded or transformed.

 4.2 Story-based techniques based on tree construction «

 The following four kinds of $ 8 are available for the <br> method.

. 1 was a specific event an argument in捃太it衬line operations to _O..: 2. Take a specific subtree in the story tree as an argument and operate on it.

 3. Take the number of events or subtrees as arguments and combine them.

 4. Take a specific story object as an argument, and perform an opponent's work on it.

 Of these, 3 is the case of the “synthesis” group of the narrative branch method, and 4 is the case of adding and updating the character of a specific narrative forefact. The difference between 1 and 2 is that the argument is only a single event or a partial bold, and from the difference in the way bold is made. Both can be divided into the following six types. The pattern is shown in Fig. 13 to Fig. 18 and that of type 2 is shown in Fig. 9 to Fig. 22

1. Combined type: newly created events and subtrees are joined before and after the argument, and the two are bundled by a relation. O Narrative technique “contrast”, “parallel”, “description”, “description”, “reason j, "Repetition" corresponds to this. For example, the narrative technique ^Γ contrast creates an event with an event concept that is the value of the slot 対 照 contrast 'of the event concept frame in the argument event, joins it after the argument event, and joins the two. The narrative technique "reason j" refers to a specific rule in the narrative knowledge base, which is the opening of the frame of the event concept in the event of the argument, and the value of the "reason". By doing so, we create an event of 别 that constitutes “reason j” for the event of the argument, combine it with the event of the argument, and bundle the two by a “reason” relationship.

2. Containment type: Returns a subtree containing the event or subtree of the argument as part of a larger tree. Story technique ¹ "main S of: ^inclusion", Γ eye building - Planning: inclusion ", r script: inclusion" such as corresponds to this. For example, the narrative branch method “Script: Inclusion” retrieves a script that contains the event of the argument in the script knowledge base in the narrative knowledge base, and outputs this script.

 3. Kasuga replacement type: One of the elements of the Kasuga required to be replaced with another. For example, instantiation of a frame during an event, instantiation of an instance, implementation of the concept of an event, and abstraction. The narrative techniques “embodiment”, “abstraction”, “case”, “classification j”, etc. are equivalent to this. For example, the story branch method “case J” is any component of the argument event. With its instance.

 4. Argument substitution type: Replaces a newly created event or subtree with an argument event or subtree. Narrative techniques such as “script: development j” and “goal-plan: development” correspond to this. For example, by referring to the rules in the knowledge base, which is the value of the narrative branch method “Script: Evolution j, the slot of the concept of the event in the argument event, the script,” Creates a first-speed event chain that composes the script for the event, and replaces it with the event of the argument.

 5. Insertion type: Insert a newly created event or subtree in the middle of the argument part. The story-branch method import J group corresponds to this. For example, the narrative technique rKase J inserts one or more events in between the events given as arguments to prevent the arrest of subsequent events.

 6. Modification type: Modifies the ellipse at the end of the argument, that is, the way events are combined. The narrative branch method r deformation from the viewpoint "corresponds to this. For example, the story technique r deformation from viewpoint '' is to rearrange the structure of this capital based on the viewpoint of a specific character appearing in the argument.

4.3 Fixed items | § Branch method Tables 1 to 3 show one of the main branch methods. Otherwise, the following narrative techniques are defined.

Desire-satisfaction (development): An event of an argument is regarded as a hope, an event sequence for satisfying it is generated, and both are connected by a stupid-satisfaction relation. Similarity) 蹶 望 充 充 包含 包含））））））））））））））））））））））））））））））））））））））））））））））））））））））） '） 蹶 蹶）））））））））））））））））））））））））)） 蹶 蹶）））））. Include an event or city tree in this sequence of events (similar to the Goal-Plan (Include) method.>

Problem-Solution (Expansion): Generates a sequence of events to solve the problem of the argument and solves the problem. Similar to the goal-planning (deployment) method. > Interrogation-Solution (Inclusion): A problem in which the event or subtree of the argument is included in the sequence of events for solving the problem. Is included in this sequence of events. (Similar to the goal-total (include) method.)

Prohibition-Violation (Inclusion): Searches the knowledge base for a sequence of prohibited ones that includes the argument event or subtree in the sequence of violations against prohibition, and searches the event or subtree of the argument in this event sequence. (Similar to the Goal-Plan (Inclusion) method.)

Instruction-Compliance (Include): An instruction that includes the event or subtree of the argument in the event sequence for complying with the instruction. The event sequence of compliance is searched from the knowledge base, and the event or subtree of the argument is searched for this event. Include in a row. (Similar to the Goal-Plan (Inclusion) method.)

Damage-elimination (containment): Search the knowledge base for the damage-elimination event sequence that includes the argument event or subtree in the event sequence for eliminating the damage, and find the argument event or subtree as this event. Include in a row. (Similar to the goal-total (include) method.)

Reaction: A second event or subtree that occurs as a reaction to the first event or subtree is connected by a reaction relationship.

Succession: Succession of a second event or subtree temporally succeeding the first event or subtree

Combine with M. A bond M that does not have semantic properties such as control, parallel, and reaction. Question-Response: The M-person oversees the process in which one asks the other about what is in the other and the latter responds to it.

f Fixed-incident: When the scene setting for the second event or city tree is explicitly indicated. In other words, this is a case where the current situation is indicated by closing characters or other objects before any event starts. (Similar to the map method.) Reasoning: Creates an estimated past event sequence for some target in the current situation. The event sequence may be an event sequence that actually occurred in passing or an event sequence that is not.

Recollection: Creates a sequence of recollected past events for any object in the current situation. aThe event sequence must have actually occurred.

Movement: Transform a story structure by moving a specific event or subtree in a subtree. The event or source of the move is marked with an “omitted” symbol _e

 4.4 Specific examples of narrative techniques

 The following shows specific examples of the syntax and input / output of major physical techniques. In the description method, the left side means (object-branch method input type) and the right side means (output list). See Tables 1 to 3 above for definitions of these narrative branch methods.

-2Θ- <Control (event)>

 (teche control event 0>)-> ($ control event Q> event 1>)

 Xtechetaishai! '(AGT AGT &) (TIM T1M & Time 1) (LOC L0C & Location!)>): EVENT); This key: EVENT specifies the contrast of the event concept. In addition, it is possible to specify the character and the object;

 ($ Control (瘦 AGT AGT & X) (TIM TIM & Time 1) (LOC L0C & Location 1).))

 (Fat ((AGT AGT & X) (LOC #: G961) (TIM #: G960))))

 <Parallel (event)>

 (teche parallel event 0>)-> ($ parallel event 0> <event)

 Xtecheheiretsu '(瘦 ((AGT AGT & X) (TIM Time 1) (LOC LGC & Location 1)))): EVENT) ($ Parallel (瘦 ((AGT AGT & X) (TIM TIM & Time I) (LGC L0C & Location 1)) )

 (Hyoro Hiroshiro ((AGT AGT & X) (LOC l: G969) (TIM «: G968))))

Depiction>

 (teche depictions of creatures ()>,-'depictions of phenomena 事 象> creatures of elephants ...

<Description>

 (teche depiction subtree 0>)-> ($ depiction subtree 0> development ... <event n>))

<Description>

 (teche description <event 0>)-> ($ description <event 0> <event ... <event n>))

Xtechisetsumei '(Kill ((AGT AGT & X) (AIT AGT & Kozushi)) (TIM time 1)

 (LOC L0C & Location 1))): CHARACTER)

($ Description (Kill ((AGT AGT & X) (AIT AGT & Small)) (T1H time (LOC L0C & Location I)))

 (Yes ("GT AGT & X) (Last name (Sugino))))) (Yes ((AGT AGT & X) (First name (Jiro)>))

 (Yes ((AGT AGT & X (occupation (TH @ salaryman))))

 (Yes ((AGT AGT & X) (age (36)))), (Yes ((AGT AGT & X) (Gender (TH male))), (Yes ((AGT AGT & X) (Residence (Tokyo.

 (A (AGT AGT & X) (Hometown (Nagano:

 (Yes ((AGT AGT & X) (Mamo-life (live))))

 (Yes ((AGT AGT & Kozuki) (Family name IL)))

 (Yes ((AGT AGT & Kozuki) (Name NIL)))

 (Yes ((AGT AGT & Kozuki)) (TH Maiko))))

 (Yes ((AGT AGT & Small) (age (18))))

 (Yes ((AGT AGT & Kozushi) (Sex (TH¾ woman))

 (Yes ((AGT AGT & Kozuki) (Residence (Kyoto))))

 (Yes (GT AGT & Small Jing (Hometown))))

 (Yes ((AGT AGT & Small)

Description>

 (teche explanation kutobunta 0-> part end 0> kuin ft .. event n>))

 <Reason>

 (tech reason reason event 0>)-> ($ reason reason event 0>)

'<t'<AGT AGT &X> (OBJ AGT & Kozuki, 'TIH T1H & (LQC LOC & Location 1))))

 Reason (I hate ((AGT AGT & X) (OBJ AGT & Kozei)) (TIH <t: G972) (LOC #: G973))>

 (Kill ((AGT AGT & X) (QBJ AGT & Kozushi)) (TIM TIM & Time 1) (LOC LOC & Location 1)))))

 (teche result <event>-> event 事 象> event)

 > (techekekka

 '(Paku ((AGT AGT & Kozuzu)) (TIM TIM & Time 1) (LOC LOC & Location 1) (OBJ OBJX throat)))))) ($ Reason (Hakuku ((AGT AGT & Kozuzu) (TIH ΠΜ & Time I)) (LOC LOC & Location 1) (OBJ OBJ throat)))

(Drink ((AGT AGT & Kozhizu) (TIH #: G908, (LOC #: G909) (QBJ OBJ Wed))))

 (teche specific event 0>)-> <event 1>

 Xtechigutaika '(Eat ((AGT AGT ¾ children) (OBJ OBJX cuisine) (TIM TH 時 snack time))): event)

 (Eat snacks ((AGT AG children) (OBJ 0B ^ dishes) (TIH THX snack time))))

<Specification>

 (Teche materialization Ku partial tree 0>)-> Ku partial tree 0 '>

Abstraction>

 (techS abstraction ku event 0>)-> ku event

 > (tech # chuu8hauka

 '(Eat snacks ((AGT AGT¾ children) (OBJ 0BJ3; cooking) (TIM TH¾ snack time)))): event) (eat ((AGT AGTX children) (OBJ 0BJ¾ cooking) (TIM TH¾ snack time)))

Abstraction>

 (teche abstraction Ku partial tree 0>)-> Ku partial tree 0 '>

Case study>

 (Example of techS event 0>)-> Event 1>

 > (tech @ .jireika-all '(Snack to eat ((AGT AGT & X) (TIM Time 1) (LOC L0C & Location 1)

 (OBJ 0BJ¾ cuisine)))

 (Eat snacks

 ((AGT AGT & X) (TIM TIM & Time 1) (LOC L0C & Location 1) (OBJ 0BJ & Tempura 1)))

Case study>

 (Teche case example Ku-subtree 0>)-> Ku-subtree 0 '>

Grow>

 (teche categorization event 0>)-> event

 Xtechiruika-all '(Snack eating ((AGT AGT & X) (TIM TIM & Time 1) (LOC L0C & Location 1)

 (OBJ 0BJ & Tenbura 1)))

(Snack to eat ((AGT AGT & X) (TIM TIM & Time 1) (LOC L0C & Location 1) (OBJ 0BJX cuisine)))) <Classification>

 (TecW categorization <Tokyo tree 0>)-> Kumo partial tree 0 '>

Summary>

(teche result <鄘 tree 0>)-> <Creating a mental map>

 (teche mental state map creation event))-> mental state>

X tech§make-men

 '(Drunk ((AGT AGT & X (TIM TIK & Time 1) (LOC L0C & Location 1) (OBJ 0BJ¾liquor)))))

 (X ((TYPE (INSTANCE)) (NAME (AGT & X))

 (MEN (MODX pleasant satisfaction MODX dream feeling M0D enchanted)) ： 心 的 状

 (Surname NI (name NI (occupation (TH salaryman))) (age NI (sex (TH¾ male))

 (Residential Area NI (Hometown HI (State-Life and Death (AG CHARACTER))))

 (Event creation by techS mental state)

Goal One Plan (Development)>

 (teche target-plan (deployment) phenomena 0>)

 -> ($ Target-plan ($ target-build-event 0 '>) ($ plan-build-event ... <event n>) ($ effect-build-event 0'>) ') X tech§goal-plan-exp

 '(Specify ((agt agt & x) (tim tiin & time | W | 1) (loc ioc & location I) (obj obj¾gold))))

($ Target-Total

 ($ Target ($ W Section-Purpose (Want ((AGT AGT & X) (TIM NIL) (LOC NIL))))

 (Profit ((AGT AGT & X) (TIM TIM & Time 1)

 (LOC L0C & Location 1) (OBJ 0BJ¾))))))

 ($ Plan (Work ((AGT AGT &) (TIM TIM & Time (LOC L0C & Location 1)))))

 (<< Effect (AGT AGT & X) (TIM TIM & Time 1) (LOC L0C & Location 1) (OBJ 0BJ¾ 金)))))

 If the argument is an event. "Containment j is a method of outputting a mechanism that includes an argument as one element in the output. Therefore, the narrative technique of the same item often uses" expansion j form and "containment" There are two different types of formats.

(techS target-plan (include) phenomena 0>)

 -> ($ Goal-one-plan ($ goal <event)

 ($ Plan <event 2>. <Event 0> event n>)

 ($ Effect 事 象>))

> (tech§goal-plan-inc

 '(Get pregnant ((AGT AGT & X) (TIM TIH & Time 閱 1) (LOC L0C & Location 1))))

($ Goal-plan

 Goal ($ Relationship-Purpose (Want ((AGT AGT & X) (TIM NIL) (LOC NIL)))

 (Birth ((AGT AGT & X) (OBJ 0BJ5S Child) (TIM NIL) (LOC NI I)))), (Plan (Pregnant ((AGT AGT & X) (TIH TIK & Time 1) (LOC L0C & Location I))))

 (ίEffect (Birth ((AGT AGT & X) (OBJ 0BJ3! Child) (TIM NIL) (LOC NIL))))))

<Total goal 1 (included)>

Similarly in case of inclusion, but the argument is not an event but a binary tree. The structure containing this subtree as an element is output. Therefore, in many cases, the argument form is an event or a partial argument. (tech metro-plan (included)

 -> Building-Plan Goal Goal Event 1>) ($ Plan Goal Event 2> .. Go partial tree 0> .Go Goal π>)

 ($ Effect 事 象>))

> (tech ^ goal-plan-inc

 ($ Sequence (Enter ((AGT AGT & X) (TIM TIM & Time 1) (LOC TH¾ Bank)))

 (<S Kas ((AGT AGT & X) (AIT TH¾ bank clerk) (TIM time 1) (LOC TH¾ bank)))) ($ M section-purpose

 (Command

 (CAGT AGT & X) CAIT THX Bank clerk) (TIM TIM & Time 1> (LOC TH¾ bank))) (Open

 ((AIT ΤΗ5ί Bank Shell) (TIM TIH & Time 1) (LOC TH3! Bank) (OBJ 0BJ¾K))))) (Puku ((AIT TH¾ Bank Employee) (TIM Time 1) (LOC TH¾ Bank) (OBJ (^^ safe)))) ($ Section-Purpose

 (Command

 ((AGT AGT & X) (AIT TH¾ Bank Hing) (TIM TIM & Time)) (LOC TH¾ Bank)), (Pack

 ((AGT TH¾ Banker) (OBJ 0BJ5; Fri) (TIM TIH & Tokikaku 1) (LOC THX Bank)))) (Packing ((AGT AGT & X) (TIK TIM & Time 1) (LOC TH¾ Bank)

 (OBJ 0BJ¾Fri) (TO 0BJ% | g))

 (Hand over ((AGT TfU Bank clerk) (AIT AGT & X) (OBJ 0BJ¾IS)

 (TIM TIH & Time 1) (LOC THX Bank)))

 (Receive ((AGT AGT & X) (AIT THX Bank employee)) (OBJ 0BJ% IS)

 (TIH TIM & Time 1) (LOC @ Bank)))

 (Exit ((AGT AGT & X) (TIM Time 1) (LOC TH¾ Bank)))

 (Escape ((AGT AGT & X) (TIM Time 1) (LOC Τ1ΠBank)))))

($ Goal-plan

 ($ Goal ($ (W Section-Purpose (Want ((AGT AGT & X) (TIM NIL) (LOC NIL))))

 (Own ((AGT AGT & X) (OBJ 0BJ¾Fri) (LOC NIL) (TIM NIL))))) ($ Plan Succession (People ((AGT AGT & X) (TIM Time 閱 1) (LOC TH¾Bank)))

 (Pikasu ((AGT AGT & X) (AIT TH¾ Bank employee)) (TIM TIM & Time 1)

 (LOC THX Bank)))

 ($ 閱 Section-Purpose

 (Order ((AGT AGT & X) (AIT T1U Banking Tool)) (TIM TIM & Time 1)

 (LOC TH¾ Bank)))

 (Open ((AIT THX Bank clerk) (TIH TIM & Time 1) (LOC TH¾ Bank)

 (OBJ OBJX Safe)))))

 (Seki ((AIT THX Bank clerk) (TIH TIH & Time 1) (LOC TH! L Bank)

 (OBJ 0BJ¾i Kim It))))

 ($ M Section-Purpose

(Order ((AGT AGT & X) (AIT ΤΗΪBank R) (TIM T1M & Time (LOC TH¾ Bank)))

 (Pack ((AGT TH¾Bank R) (OBJ OBJ¾Fri)) (TIM TIM & Time 1)

 (LOC THX Bank))))

 (Pack ((AGT AGT & X) (TIM Time 1) (LOC TH¾ Bank)

 (OBJ OBJ¾Fri) (TO OBJ% ½)))

 (Pass ((AGT THX Banker) (AIT AGT & X) (OBJ OBJ¾fg>

 (TIM TIH & Time 1) (LOC THX Bank)))

 (Receive ((AGT AGT & X) (AIT TH¾ Bank employee) (OBJ OBJXlg)

 (TIH T1H & Time 1) (LOC TH Bank)))

 (Exit ((AGT AGT & X) (TIM Time 1) (LOC TH¾ Bank)))

 (Escape ((AGT AGT & X) (TIM TIM & Time 1) (LOC TH Bank)))))

 (Effect (Own ((AGT AGT & X) (OBJ OBJ¾ 金) (LOC NIL) (TIM NIL)))))

Script (expand)>

 (teche script (deployment) event 0>)-> ($ event occurring ... <event n>)

X techiscript-exp

 '(Strangle and kill ((AGT AGT & X) (TIH Time 1) (LOC LOC & Location 1) (OBJ AGT & Kozuzu: ($ sequence ((AGT AGT & X) fQBJ AGT & Kozutsu) (TIM TIH & Time 1) (LOC LOC & Location 1))) (Tighten ((AGT AGT & X) (TIK TIM & Time 1) (LOC LOC & Location 1) (OBJ OBJX neck)))) (Suffer (((AGT AGT & Kozushi)) (TIM TIH & Time 1) (LOC LOC & Location 1)))

 (Suffocate ((AGT AGT & Kozushi)) (TIM TIM & Time 1) (LOC LOC & Place 1)))

 (芄 艳 Yes ((AGT AGT & Kozushi)) (TIM TIM & Time 1) (LOC LOC & Location 1)))

 (Die ((AGT AGT & Small)) (TIM TIM & Time 1) (LOC LOC & Location 1))))

<Script (include)>

 Inclusion format when the argument is an event.

(teche script (included) <event 0>)-> succession <event .. <event 0>. <event n>)

> (tech§script-inc

 '(Eat ((AGT AG children) (OBJ OBJ & OCHAZUKE) (TIM THX snack time))))

(S Succession (Cooking ((AGT AGTX Children)) (OBJ OBJ & OCHAZUKE) (LOC OBJX Izakaya)

 (At time of TIM THX snack>))

 (Sell ((AGT AGTX children) (OBJ OBJ & OCHAZUKE) (TO OBJ¾ tableware)

 (LOC OBJX sake)! ) (At the time of TIH THX snack)))

 (Carry ((AGT AGT¾Child)) (OBJ OBJ & OCHAZUKE) (TO OBJX table)

 (LOC OBJX Izurei) (at the time of TIH THX snack)

 (Sit down ((AGT AGTX children) (TO OBJX tail) (LOC OBJX izakaya)

 (At TIM THX snack)))

 (M Section-Purpose (Start ((AGT AGTX Children) (LOC OBJX Izakaya Ji) (TIM THX Snack Time)))

 (Eat ((AGT AGTX children) (OBJ OBJ & OCHAZUKE)

 (LOC OBJi liquor g) (TIM THX snack time)))))

 (Eat ((AGT AG Children)) (OBJ OBJ & OCHAZUKE) (LOC OBJX

(At TIM THX snack))) (Laugh) ((AGT AGT ¾ children, (LOC 0BJ Izak 歷) (TIM TH snack time))))

 (Person-Purpose (End ((AGT AGT ¾ Children) (LOC 0BJ ¾ Izak 鼴) (TIM TH TIM Snack Time)))

 (Eat ((AGT TH¾ Serving)) (OBJ 0BJ & 0CHAZU E)

 (LQC 0BJ¾Sake 歷) (TIM TH¾Snack time)))))

 (Standing ((AGT 'AG children) (F GM 0BJ table)) (LOC 0BJ¾ izakaya)

 'T1H TH time)))

 (Attached ((AGT AGT ¾ children) (OBJ 08J ¾ tableware) (LGC 0B ¾ sake)

 (TIM TH snack time))))

Scripts (Included)>

 Inclusion format when the argument is a subtree.

(techS script (included) ku partial thick 0>)-> ($ sequence <event 1> .. <sub tree 0> ·. ku event n>)> ctech @ script-inc

 ($ Sequence

 (Preparing ((AGT TH¾ cook) (OBJ 0BJX sake) (LOC L0C & Location & (TIM TIM & Time 1)))) (Preparing ((AGT TH¾ cook) (OBJ 0BJ cooking) (LOC L0C & Location 1) ( TIM TIH & Time 1))) (Michibu ((AGT TH5! Waiter) (OBJ 0BJ¾Sake) (OBJ 0BJ¾ table, CLOC L0C & Location 1)

 (TIM leap 1)))

 (Pub ((AGT TH¾ serving) (OBJ 0BJ dish) (OBJ 0BJ table)

 (LQC L0C & Location 1) (TIM TIM & Time 1)))

 (Sit down ((AGT AGT & X) (OBJ 0BJ2 table) (LOC L0C & Location 1) (TIM TIM & Time 1))) (Cheers ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIM & Time 1)))

 Person in charge-purpose

 (Start ((AGT AGT & X) (LQC L0C & Location 1) (TIK TIM & Time 1)))

 (Drink ((AGT AGT & X) fQBJ 0BJ¾ sake) (LQC LOC & fll place 1) (TIM TIM & Time 1)))

 ($ Μ Section-Purpose

 (Start ((AGT AGT & X) (LOC L0C & Location Π (TIK ΤΙΜ & Time 1)))

 (Eat AGT AGT & X) (OBJ 0BJ cuisine) (LOC L0C & Location 1) ίΤΙΚ ΤΙΜ & Time I))))

(Eat ((AGT AGT & X) (OBJ 0BJ cuisine) (LOC L0C & Location 1) (TIK time

 (Drink ((AGT AGT & X) (OBJ 0BJ2 Sake) (LOC L0C & Location 1) (TIM Time 1)))

 (Talk ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIH & Time 1)))

 (Drunk ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIM & Time WI)))

 (Fight ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIK & Time 1)))

 ($ M Section-Purpose (End ((AGT AGT & X) (LOC L0C & Location Π (TIM TIM & Time 1))))

 (Eat ((AGT AGT & X) (OBJ OBJX cuisine) (LOC L0C & Location 1)

 (TIM TIH & Time 1))))

 ($ 閱 Section-Purpose (End ((AGT AGT & X) (LOC L0C & Location 1) (TIK TIM & Time Ml))))

 (Drink ((AGT AGT & X) (OBJ OBJXS) (LOC L0C & Place 1)

 (TIH TIM & Time 1))))

(Stand ((AGT AGT & X) (OBJ OBJX table) (LOC L0C & Location 1) (TIM time)) ((AGT TH serving) (OBJ 0BJ tableware) (LOC L0C & Location 1) (TIM time I)))))))

($ Sequence

 (Au ((AGT AGT & X (OBJ AGT% CHARACTE) (LOC L0C & Location 1) (T1H & Time 閱)))) (Walk ((AGT AGT & X) (QBJ AGTXCHA ACTER)) (LOC LC1C & Location Π (TI Time 1) )) (Play ((AGT AGT & X) (GBJ AGT¾CHARACTER) (LOC LOC & Location 1) (T1H TIK & Time 1))> (Discuss ((AGT AGT & X) (OBJ AGT% CHARACTER) (LOC LOC & Location 1) (TIM TIM & Time) )))) Succession

 (Preparing ((AGT TH¾ cook) (OBJ OBJ%} S) (LOC LOC & Location 1> (TIM TIM & Time 1)))) (Preparing ((AGT THX cook) (OBJ OBJ¾ cooking) (LOC LOC & Location) 1)

 (TIM TIH & Time 1)))

 (Carrying ((AGT TH¾ waiter)) (OBJ OBJX sake) (OBJ 0BJ5! Table)

 (LOC LOC & Location 1) (TIM TIM & Time 1)))

 (Carry ((AGT TH¾ waiter) (OBJ 0BJ¾ dish) (OBJ 0BJ¾ table)

 (LOC L0C & Location 1) (TIK TIM & Time 1)))

 (Sit down ((AGT AGT & X) (OBJ 08 <1 bulldog)) (LOC LOCSi location 1)

 (TIH time 1)))

 (Toast ((AGT AGT & X) (LOC L0C & Location 1> (TIM time 1)))

 ($ Clerk-purpose

 (Start ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIM & Time 1)))

 (Drink ((AGT AGT & X) (OBJ 0BJX Sake) (LOC L0C & 埸 1) (TIM T1M & Tokikaku 1))))

 ($ M Section-Purpose

 (Start ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIM & Time 1)))

 (Eat ((AGT AGT & X) (0BJ 0Β Cooking) (LOC L0C & Location 1) (TIM TIM & Time 1)) Ri (Eat ((AGT AGT & X) (OBJ 0BJX Cuisine) (LOC L0C & Location 1) (T1H TIM & Time 閱 1 ))) (Drink ((AGT AGT & X) (OBJ 0BJ Sake) (LOC L0C & Location 1) (TIM TIM & Time 1))) (Talk ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIM & Time 1)) )

 (Drunk ((AGT AGT & X) (LGC L0C & Place 1) (TIK TIM & Tokaku 1)))

 (Fight (AGT AGT & X) (LGC L0C & Location 1) (TIM TIM & Tokikaku 1)))

 Person in charge-purpose

 (End ((AGT AGT & X) (LOC L0C & Location 1) (TIM TIM & Time 1)))

 (Eat ((AGT AGT & X) COBJ OBJ)! Cooking) (LOC L0C & Location 1) (TIM TIM & Time 1)))) Section-Purpose

 (End ((AGT AGT & X) (LOC L0C & Babasho 1) (TIK TIM & Time 1)))

 (Drink ((AGT AGT & X) (OBJ OBJX sake) (LOC L0C & Location Π (TIM time 1))

(stand

 ((AGT AGT & X) (OBJ 0BJ2 1,000 al) (LGC L0C & Location 1) (TIK TIH &

 (Clean

 ((AGT THX serving) (OBJ 0BJX tableware) (LOC L0C & Location 1) (TIM TIM & Time!)))))

((AGT AGT & X) (OBJ AGT2CHA ACTER) (LOC L0C & Location 1) (TIM time 1)))) <Prohibition one violation (development)>

 (Prohibition of teche—violation (expansion)

 -> Prohibition -Violation ($ Prohibition / Event 0 '>) ($ Violation / Event 0>) ($ Effect / Event 1>))

X tech @ kinshi-ihan-exp

 '(Eat ((AGT AG Children) (OBJ OBJ & OCHAZUKE) (TIM TH¾Snack time)))))

($ Prohibition-Violation

 ($ Ban ($ relation-purpose

 (Ban

 ((AGT AG stranger) (OBJ AG child) (TIMΤΗ5 snack time) (LOC NIL)))

 (Eat ((AGT AGT¾Child) (OBJ OBJ & OCHAZUKE) (TIM TH¾Snack time))))))) Datong (Eat ((AGT AG Child) (OBJ OBJ & OCHAZUKE) (TIK TH¾Snack time))))) ($ Result

 (Transform ((AGT AGT¾ child) (OBJ OBJX animal) (TIM TH snack time) (LOC NIL)))))

 Inclusion format when the argument is an event.

(techS prohibition-violation (inclusion) <event 0>)

 -> ^ Prohibition -Violation ($ prohibited event) ($ observed event .. <event 0> .. <event n>))

<Prohibited series (inclusion)>

 Inclusion format when the argument is a subtree.

(teche ban-violation (inclusion) ku partial tree 0>)

 -> ($ Prohibition-Repetition (ίProhibition <Event> ($ Violation <Event 2> .. <Tokyo Tree 0> .. <Event η>))

Guilty Order Compliance (Development)>

(teche order-compliance (deployment) <event 0>)

 -) ($ Order-one-order-order-event-0 '>) (1;

X techimeirei-.iunshu-exp

 '(Eat ((AGT AG Children) (OBJ 0BJ & QCHAZUKE) (TIM @Snack)))

 Order-Compliance

 ($ Instruction (1 relation-purpose

 (Command

 ((AGT ΤΗΧ alien) (TO AGT5; child) (OBJ OBJ & OCHAZUKE) (TIM TH 時 snack time) (LOC NIL)))

 (Give ((AGT AGT¾Child)) (TO THX Alien '(OBJ OBJ & OCHAZUKE)

 (TIM NIL) (LOC NIL)))))

 ($ Compliance (Give ((AGT AGT Child) (TO THX Ijin)) (OBJ OBJ & OCHAZUKE)

 (TIK TH! T snack time) (LOC NIL))))

 ($ Result (Eat ((AGT THX stranger) (OBJ OBJ & OCHAZUKE) (TIM THX snack time)) (LOC HI good (Apologize ((AGT ΤΗΪ stranger) (OBJ AG child) (TIM TH2 snack time) (LOC NIL) ) '(Give ((AGT ΤΗΪ stranger) (TO AGTX children) (OBJ OBJX drink)

 (TIM THX snack time) (LOC NIL)))))

<Comply with Order 1 (Inclusive)> Inclusion format when the argument is an event.

(teche order-compliance (inclusion) <event 0>)

 -> ^ Command -Compliance ($ Command + Event) ($ Compliant <Event2> .. <Event0> .. <Eventn>))

 <Comply with Order 1 (Inclusive)>

 Inclusion format when the argument is a subtree.

(teche rune-compliance (inclusive) <subtree 0>,

 -> ($ Order -Compliance Order 事 象 遵守) ($ Compliance <Event 2,... 部分 Partial Thick 0> .. Ku nn>))

(Satisfaction of techS's desire (development)

 -> ($ Desired-satisfied ($ ness <event 0 '>) ($ planned event 1> due n>) <$ ¾desirable event 0>))) <desired-satisfied (inclusive)>

 Inclusion format when the argument is an event.

(techS 騸 hope-fulfillment (inclusion) <event 0>)

 -> ($ Nabo-satisfied ^ transformation sufficiency) Satisfied event 2> .. <event 0> .. <event n>))

 Inclusion format when the argument is a subtree.

(techS desire-satisfaction (included)

 -> ($ Request-satisfaction) ($ satisfaction <event2> .. <subtree 0> .. <event η »)

(teche question Β-resolution (development) <event 0>)

 -> ($ Question) 8-Solution ^ Question phenomena 0 '>) ^ Plan phenomena 1> phenomena n>) ^ Resolution phenomena 0>))

 Inclusion format when the argument is an event.

(teche question S-solve (include) phenomena 0>)

 -> ($ Question H -Solution ($ Problem) <Solution <Event 2> .. Cue 0> .. Cue n>)) Q B -Solution (Inclusive)>

 Inclusion format when the argument is a city tree.

(teche question fi-solution (containment) subtree 0>)

 -> ($ Question-resolution ($ problem-event) ($ resolution-event2> .. <subtree Q> .. <eventn>))

 Inclusion format when the argument is an event.

(techS injuries-resolved (included) phenomena 0>)

 -> ($ Harm-resolved ($ harm-resolved event) ($ resolve-resolved-event 2> .. <event 0> .. <event n>))

<Attack-Elimination (Inclusion)>

 Inclusion format when the argument is ffi.

(teche harm-elimination (containment) new branch 0>)

 -> ($ Harm-elimination ($ harm <event>) elimination <event 2> .. ku part end C> .. ku event n>)) <main 题 (inclusive)>

 The argument is the inclusion form of the event.

(tecW main 包含 (inclusive) く event 0 >>-> ($ main B <event record event 0 · .. <event n >> (tech ^ theme-inc '(kill f (agt ft & x) (ai t afft & small | S> (Ura tim & time))

 (loc loc & location 1))))

($ Subject (Own ((AGT AGT & HAYAKA A) (TIM «: G954)) (LOC LOC & Location 1)

 f OBJ TH & heritage) (DEG MOD¾Huge Man)),

 (Make ((AGT AGT & HAYAKAWA)) (TIM #: G952) (LOC LOC & Place 1)

 (OBJ AGT & X (ΑΓΤ TH children)))

 (Make "AGT AGT & HAYAKAWA) (TIM #: G950) (LOC LOC & Location Π

 (OBJ AGT & Kozushi) (AIT TH children))))

 ($ Goal-plan

 ($ Goal

 (I want ((AGT AGT & X) (TIM #: G948) (LOC LOC & Location 1)))

 (Exclusive ((AGT AGT & X (OBJ TH & Production) (TIM NIL) (LOC NIL))))))) ($ Plan (Kill ((AGT AGT & X) (AIT AGT & Small)) (TIM TIM & Time))

 (LOC LOC & Location 1))))

 ($ Effect ^ reason ($ person-purpose

 (Exposed

 ((AGT AGT & SAYA) (TIM #: G956) (LOC LOC & Place I)))> (Kill ((AGT NIL) (AIT AGT & Kozushi))

 (TIM «: G956) (LOC LOC & Location 1))))

 (Arrested ((AGT TH¾ Police Officer (OBJ AGT & X)

 (TIM #: G958 (LOC LOC & Location 1)))))))

 <Primary «(inclusive)>

 Inclusion format when the argument is partial bold.

(teche subject (included) <tree 0>)-> ($ main event. <subtree D> .. <event n>)

<Sequence>

 (teche successive events 0>)-> ($ sequence events 0> next events 1>)

<Sequence>

 (end of techS part Q>)-> ($ part of partial tree Q> many events 1>)

<Reaction>

 (teche reaction event 0>)-> ($ sequence event 0> event)

<Reaction>

 (techS reaction subtree Q>)-> ($ sequence subtree 0> <event 1>)

<Reasoning>

 (techS reasoning event 0>)-> ($ reasoning event 0> event 1> ... <event π>)

<Recollection>

 (techS recall event 0>)-> recall event 0> recall event .. <event n>)

<Move>

 (teche move <city tree 0>)-> ($ move <city tree 0 '>)

 -(ίΜRelation? <Event <Event 2>)-(ίMove <Event> Omitted) <Event (Event)

<Gumi from viewpoints> ⁽ Organization from teche's point of view 0>)-> 1)

 Transform the structure at the end of the part, not expand it.

 > * Viewpoint * = partial knowledge

 > * current- narrati e *

 ($ Main super (Own ((AGT AGT & Hayakawa)) (TIM #: G1093) (LOC #: G1099)

 (OBJ TH & Property) (DEG MODS!

 ^ Parallel

 (Gain ((AGT AGT & Hayakawa) (TIM #: G1091) (LOC #: G1100) (OBJ AGT & —Chiro))) (Gain ((AGT AGT & Hayakawa) (TIM «: G1089) (LOC #: G1101) (OBJ AGT & Kozushi))))) ($ eyes building-plan

 ($ Goal ($ 閱 Relationship-Purpose) (I want ((AGT AGT & -Chiro) (TIM #: G1087) (LOC #: G1102)))

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property)

 (TIM NIL) (LOC NIL)))))

 ($ Plan

 (Kill ((AGT AGT & -Chiro) (OBJ AGT & Small) (TIM TIM & Time 1) (LOC <t: G1103))))) ($ Effect ($ Reason ($ Relation-Purpose)

 (Exposed ((AGT AGT & SAYA) (TIM «: G1095) (LOC #: G1104))) (Kill ((AGT NIL) (OBJ AGT & Kozushi)) (TIM #: G1095)

 (LOC L0C & Location 1))))

 (Arrested ((AGT TH¾ Police Officer) (OBJ AGT & -ro)) (TIH #: G1097)

 (LOC #: G1105)))))))))

X techS lot-by-view * current-narrative *)

 Select: (Π (AGT & Hayakawa.))) (2 (AGT & —ro)) (. (AGT & SAYA))) 1

($ Lord ffi (Own ((AGT AGT & Hayakawa)) (TIH TIM & Tokaku I) (LOC L0C & Location 1)

 (OBJ TH & Property) (DEG M0DX Huge Man)))

 ($ Parallel (Make ((AGT AGT & Hayakawa)) (TIH TIM & Time 1) (LOC L0C & Location 1)

 (OBJ AGT & -ro)))

 (Make ((AGT AGT & Hayakawa)) (TIM TIM & Time 1) (LOC L0C & Location 1)

 (OBJ AGT & Kozhi)))))

 ^ Goal-Plan

 ($ Eyes building ($ M section-purpose

 (I want ((AGT AGT & -ro) (TIM Time 1) (LOC L0C & Location 1))>

 (Exclusive ((AGT AGT & -ro) (OBJ TH & Property) (TIH NIL

 (LOC NIL))) omitted))

 Sleep

 (Kill ((AGT AGT & —Chiro)) (OBJ AGT & Kozei) (TIM ΠΜ & Time 1)

 (LOC L0C & Location 1) Ministry ¾)))

 Effect (ί Reason ($ WI Section-Purpose)

 (Exposed ((AGT AGT & SAYA) (TIM TIM & Time 1)

(LOC L0C & Location 1))) (Kill ((AGT NIL) (OBJ AGT & Small))

 (TIM TIMSt Time 1) (LOC LOC & Location 1))) Omitted)) ($ Move (Arrest ((AGT TH¾ Police Officer) (OBJ AGT & -ro))

 (TI TIH & time (LOC L0C & location 1) omitted))> ($ discourse (say ((AGT AGTXCHA ACTE (QBJ N1L))

 ($ Sequence ($ relation-purpose

 (I want "AGT AGT & -ro") (TIM T1M & Time 1)

(LOC L0C & Location 1)

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property :)

 (TIM NIL) (LOC NIL))))) (Kill ((AGT AGT & —Chiro)) (OBJ AGT & Kozushi)

CTIM TIM & Time 1> (LOC L0C & Location 1))> Relation-Purpose

 (Exposed ((AGT AGT & SAYA)

 CTIM TIM & time I)

 (LOC L0C & Location 1)))

 (Kill ((AGT NIL) (OBJ AGT & Kozuzu))

 (TIK time 1)

 (LQC LGC & Location 1))))

 (Arrested ((AGT TIU police officer)

 (QBJ AGT & -ro)

 (TIM TIM & Time 1)

 (LOC L0C & Location 1))))))))))

(teche repetition: event 0>)-> ($ sequence 0> ... <event n>)

<Shackles>

 (technical event 2>) ·> (event 1> <3> ... event 3n> event 2>)

> (tech8kase

 '(Reason (Monk ((AGT AGT & Sugino) (TIM time l) (LOC L0C & Location 1) (OBJ AGT & Kosuzu))) (Kill ((AGT AGT & Sugino) (TIM TIH & Time 2) (LOC L0C & Location 2)

 (OBJ AGT & Kouzuru)))))

 ($ Reason

 (Kasumu ((AGT AGT & Sugino) (TIM Time 1) (LOC L0C & Place 1) (OBJ AGT & Kosuzu))

 ($ Sequence

 Reason (Escape ((AGT AGT & Kosuzu)) (TIM «: 1079) (L0C *: 1081)))

 (Catch ((AGT AGT & Sugino) (TIM «: 1083) (L0C #: 1085)) (AGT AGT & Small) (Kill AGT AGT & Sugino) (TIM Tokimino 2) (LOC L0C & Location 2) (OBJ AGT & Small) ))) <Ground one>

 (techS ground map Kudu tree>)-> ($ ground-map Kudu tree> ')

> (tech? chi-zu ((AGT AGT & OTA-NOBUNAGA) (AIT AGT & YAMADA-KUNl KO)

 (TIM TIH & YONAKAl) (LQC OBJ & UENO-OIJEN)))

 (Tighten ((AG? AGT & OTA-NOBUNAGA) (AIT AGT & YAHADA-KUN1 KO)

 (TIM TIM & Y0NAKA1) (LOC OB J & UENO-KOURN) (OBJ OBJ¾ 首)

 (Suffer (GT AGT & YAMADA-KUN1K0) (TIM TIM & YAKADA) (LOC QBJ & UENO-KOUEN)))) (Suffocate ((AGT AGT & YAMADA-KUNIKO) (TIM T1M & YGNA A1))

 (LOC OBJ & UENO-KOUEN)))

 (Stun ((AGT AGT & YAKADA- UNIKO) (TIM TI & YONAKAl)

 (LOC OBJ & UENO-KOUEN)))

 (Die ((AGT AGT & YAMADA-KUNI O) (TIM TIM & YONAKAl) (LOC OBJ & UENO-KOUEN)))) Ground-map ($ ground ($ reason instruction ($ W-person-purpose

 (Order ((AGT AGTX stranger)) (OBJ AGT CHARACTE)

 (TIM TIMXJIKAN) (LQC NIL)))

 (Story ((AGT AGT¾CHA ACTE)) (OBJ AGTXCHARACTER)

 (TIM TIM% JI AN) (LQC NIL)))))

 (Start ((AGT AGTXCHARACTE) (OBJ TH¾ Story)

 (TIM TIMXJIKAN) (LOC NIL)))))

 ($ Figure ($ sequence ((AGT AGT & OTA-NOBUNAGA) (AIT AGT & yAMADA- UNIKO)

 (TIM TIH & YONAKAl) (LOC OBJ & UENO-KOUEN)))

 (Tighten ((AGT AGT & OTA-NOBUNAGA) (AIT AGT & YAMADA-KUNIKO)

 (TIH TIM & YONAKAl) (LOC OBJ & UENO-KOUEN)

 (OBJ OBJ¾ 首)))

 (Suffer ((AGT AGT & YAWADA-KUNIKO)) (TIM TIM & YONAKAI)

 (LQC OBJ & UENG-OUEN)))

 (Suffocate ((AGT AGT & VAMADA-KUNIKO)) (TIM TIM & YONAKAl)

 (LOC OBJ & UENO-KOUEN)))

 (Stun ((AGT AGT & YAMADA-KUNIKO)) (TIM TIM & YONAKAl)

 (LOC OBJ & UENO-KOUEN)))

 (Die ((AGT AGT & YAMADA-KUNIKO) (TIM TIM & YONAKAl)

 (LOC OBJ & UENO-KOUEN)))))

 ($ 地 (End ((AGT AGHCHA ACTE)) (OBJ THX Story) (TIH TIM¾JIKAN)

 (LQC NIL)))

 Reason (I'm impressed ((AGT AGHCHARACTER) (TIM TIMXJIKAN) (LOC NIL))) (Give ((AGT AGHCHARACTER) (OBJ AGT2CHA ACTER)

 (OBJ OBJX Reward) (TI TIMXJIKAN) (LOC NIL))))))

 (techSlJ fixed one case branch tree>)-> ^ Settings-case Ku Kubunta> ')

5 Article

 5.1 Definition of iK abbreviation rules

There are two types of narrative strategies: the narrative technique passing point determination strategy and the narrative branch method determination strategy. Previous Is defined as a set of rules for determining the nodes in the story tree to which the narrative technique is to be applied next, and the latter is defined as a set of rules for determining the accepted technique that should actually apply to that node. Then

¾ The rules of these two types of bran and the mechanism that controls them are collectively called a story. In particular, the former is called a story strategy rule, and the latter is called a story strategy control mechanism. According to the above classification, story wartime rules may be referred to as story technique application point decision strategy rules and story technique decision strategies rules, respectively. Each rail has in its conditional part story parameters and other information that define the characteristics of the story to be created, and a conclusion about the application points or story branching methods of the candidate story techniques. The story parameters are basically given to the system by the user at the beginning of ft, but the value of the story parameters is set to a global variable, and the system refers to the story parameters in each cycle of story creation, so the value can be changed at any time. Even if it is changed, it is possible to operate and train as it is based on the changed story parameters. Therefore, the story parameters can be arbitrarily changed during the creation of the material.

 Depending on the set of values of the story parameters, the system has the ability to create stories with different structures at any time.

 In the previous chapter, it was noted that there are several methods from simple methods to complex methods to determine the application point of the story technique. In this method, the terminal node is set as the application point # from left to right, and the same process is repeated for the terminal node of the newly added subtree.

 The following is an example of the Narrative Technique Decision Battle B§ Rule.

<Example 1 of story strategy rule (story technique decision lift rule)>

(def Str-tech str- tech ^ theme- inc3 '

 (if (and (equal * narrative type * 'novel) (equal * theme * low)

 (equal * narrative * 'low) (equal * character-intent *' low)

 (equal * detailed * low) (equal * logical * low)

 (equal * contrast * 'low) (equal * parallelism *' low)

(equal * phase * ^: narrative- planning))

 (progn (set-gp-const 'all nodes) (techPtheme- inc * growth-list *))))

<Example 2 of Strategic Rules for Strategic Techniques>

(defStr-tech str-techigoal-plan-ex l '

 (if (and (equal * story of the story * 'novel) (equal * character-intention *)'

 (or (equal * theme * 'no) (equal * theme * * medium)

 (equal * teamer * 'low))

 (or (equal * narrative * 'medium) (equal * narrative *' low))

 (equal phase * 'narrative- lanning))

 (progn (set-gp-const 'except for top) (tech ^ Koal-plan-exp * growth-list *))))) <Example 3 of story narrative rules>

(defStr-tech str-tech @ goal-plan-exp4 '

 (if (and (equal * story type * 'novel) (equal * character-intentionality *' S)

 (equal * phase *, story-feneration ")

(or (equal 'rel (check-gp- type growth- 1 ist (equal 'eve (check--type * gro th-list *))))

 (not (equal 0 (check-gp-level *? rowth-] ist *))))

 (progn (set-gp-const ', below zop) (tech @ goal-plan-inc * growth-list *)))>) <Example 4 of Story Strategy Rule (Material Technique Decision Strategy Rule)>

(defStr-tech str-tech © riyuu8,

 (if (and (equal * narrative type * 'novel) (equal * logical *' low)

 (equal * phase * 'story-generation)

 (or (equal 'rel (check-gp- type * growth- 1 ist *)))

 (equal 'eve (check-Rp-type * ^ rowth- 1 ist *))))

 (<= 2 (check-gp-) evel * growth-list *)))

 (roKD (set-gp-canst 'all nodes) (tech ^ ri vim * gro th-list *))))

<Example of a story moth W rule (story branching method) /

(defStr-tech str-tech @ taishoul '

 (if (and (equal * story type * 'advertisement) (equal * contrast *' high)

 (equal * phase * 'narrative-planning)

 (or (equal 'rel (check-gp- type * growth- list *)))

 (equal 'eve (check-gp- type * growth-list *))))

 (not (equal 0 (check-gp- level * growth-list *)))))

 (pragn (set-gp-const 'all nodes) (techetaishou * growth-list *))))

 Each rule consists of a condition part and a conclusion part.

(♦ Phase *), story parameters and their values, and information such as the current story tree shape are described. The story parameter * story type * specifies the type of story, such as "novel", and includes the story of advertisement j and "scenario". The M number check-gp-type determines the type of application point of the parent-parent technique, that is, whether the terminal node is an event or the other nodes are subtrees. Similarly, the W-number check-gp-level checks the position of the current application point of the story technique in the story tree as a level. 0 corresponds to the,, / pre-level node, and one less is added. The M-number set-gp-const used in the conclusion describes the constraints on nodes that can be applied to the story technique in the subsequent expansion of the story tree. Is another ride scan I executable story branch method described in the conclusion part, * frowth- list * is _e example is Ξ one eye of the rules are stored or story technique-class point as a argument in the , * Story of eve * power ^r novel j. Place person-intention * value is ¹ "high". Task is ^r story creation ", argument type is arbitrary and S and L bells are" The platform of ',' pre-level narrative technique techegaa plart-inr 'connecting plan:' including '^ the name defined in the capital of the technique program). At lower levels, excluding the level nodes. "-5.2 Story parameters

 The relationship between the story parameters and the strategy for determining the application point of the story branch method is described below. (Tables 4 and 5 show the story parameter parameters * | and the main story parameters.)

1. * Story type *: "Specify the type of story, such as novel j or ^Γ scenario j. Such a story type creation is mainly based on a framework that can be realized through the way of constructing story narratives. Has become. 2. * ma *: Instruct the use of a specific pattern provided in the system. For example, a theme pattern such as "遗 Murder by inheritance J." ing.

3. * Poma property * _: Each of the above theme patterns constitutes a kind of schema by the chain of events, but specifies the strength of dominance over the whole story. For example, if * theme * is the strongest .. It is required to use theme patterns at the highest level that controls the whole story, but the weak platform is the lower level in the story tree. The theme pattern will be used.

 4. * Length Specify the length of story, professional, and / or video. This is currently determined by the number of events contained in each, and the relationship between length and structure has not yet been specifically examined.

 5. * Logic *: Specifies whether the development of the story is logical. In the SS-reasonable case, it is necessary to develop events with as clear a causal relationship as possible. This does not necessarily correspond to the degree of fantasy in the story. Strict or common sense · There are fantastic stories that develop through everyday causation.

 6. * Specificity *: Specifies whether the story object or event that appears in the story is concrete. For example, if the story objects are concrete, they must be represented as instances. Conversely, if they are abstract, they may be represented as frames. Also, when the event development is concrete, a highly granular event, that is, a scripted expression as much as possible is required.

 7. * Character-Intention *: Specify the color of the character's intentional action that affects the structure of the story. This is a strong stand, and the story tends to be developed by the planning action based on the character's goal.

 8. * Character-Psychological *: Specify the importance of the character's mental state in the story.

9. * Point of View *: Specify the viewpoint to tell the story. The types of viewpoints can be broadly classified into omnidirectional viewpoints and partial viewpoints. The former is a kind of divine point of view that knows all the characters and situations in the story. Conversely, the latter is the intimate point of view of a particular character. This is especially effective at reorganizing the once created narrative content into narrative expressions. In a story developed from a partial viewpoint, events that a particular character does not know directly need to be indirectly introduced into the story by communication based on discourse or recollection.

 10. * Repeatability *: Specifies the degree to which an event or its repetition, characters with similar characteristics, etc. are repeated.

 1 1. * Details *: This is a specification of the details of event development. If the details are high, the event must be reduced to the lowest possible level, and the use of a script is required. Can be

 5.3 Story making cycle based on story strategy

 The system proceeds with story creation by repeating the cycle of determining the point of passing on the story technique, determining and executing the story branch method, and expanding or changing the story tree as a whole. Figure 23 shows such a | § production cycle. The determination and execution of the narrative technique is performed by the following procedure I 犋.

1. Rule that determines the condition part of the narrative technique determination rules = Collect all the rules that can be passed You.

 2. If there is more than one, calculate the priority of the applicable rule based on the importance given by the user to each parameter.

 3. Execute only one rule with the highest priority.

 4. When a specific narrative technique is activated and the end of the narrative is updated, the priority of the executed rule is reduced. The process returns to 1 to reflect the change of the state of the end of the story, and repeats this process until the end condition is satisfied.

 The rule for determining the narrative technique is as follows: the condition part is the current face ', the value of the narrative parameter, the type of applicable narrative technique application point (event or subtree), the position of the narrative technique application point in the narrative tree (story 术, Etc.) are described. The user sets the importance of each story parameter in advance, and the addition of this importance determines the priority of the applicable rule. Performed on application points. This is one cycle of executing the language technique. Note that the priority of a rule once executed is decremented at a fixed rate. At the end of this, a new cycle starts with the collection of available rules again until the termination conditions in each phase are satisfied. Currently, the end conditions are determined by applying one story technique for the creation of a core story, creating a professional story, and creating a story, and judging the story creation by the value of the story parameter * length *. I have.

In this construction cycle, the narrative technique is given the power to be given an event or subtree as an argument, as described above, which corresponds to any node or part in the narrative tree. The resulting event or subtree returned by the end of the story replaces this part of the argument, thereby forming the story as a whole. In other words, the story tree is expanded or transformed by replacing the new subtree created by applying the story technique to the points where the story branch method is applied in the story tree with the points for the compost. This replacement is done simply Te L isp W the subst of l¾ was use Rere following structure-expander (Koyo' _β

(defun structure- ex pander (new-el emen t old-e lement l is)

 (subst new-el enen t o ld-el ement l is: test # 'equal))

6 Examples of story structure analysis

 Before showing an actual example of story creation by the above system, the method »of the present invention will be supplemented by showing the analysis results of a real reasoning novel for reference. Based on this analysis, the basic method of creating a narrative structure in this system, which is the creation of a narrative structure as a five-word tree, and the speed between both the story and the plot, using the M section as a node, However, the legitimacy based on practical examples becomes clear.

 In the following analysis, first, a story tree is constructed at several levels from the target story text, and the characteristics of the story tree and the relationships used in the story tree are described with reference to the various backgrounds described above. organize. The process of creating the story can be assumed as a process to reverse this, and at this time, it is shown that the story branch method as described above is used. The subject of analysis is short story fiction f by Maisa Yamamura f Maiko Murder Case J.

The following analysis is performed along the following hand jet. Increasingly, the sentences that make up the superficial text of the story are divided into phrase levels, and each phrase becomes a single elephant, and the entire _e WIS that composes a story based on the speed of events is swiftly. It is difficult to bundle a single story. The word tree is basically made up of "scenes" that follow. Next, each scene is considered as one event, and the whole structure of the story is formed into one tree. The above is equivalent to the pro / exposure analysis. Furthermore, the events in the narrative composed here are not necessarily arranged according to the order of time in the narrative world. A new story tree is constructed by restoring the engagement. This story tree corresponds to the story level.

6.1 From text to scene

First, all the sentences that make up the novel's text are divided at the phrase level, and each is an event. For example, Sawaki澗Ichiro of ^Γ painter of S head, Gion Maiko, if know that Kogiku Tsutano, was last fall. Is considered to be an event of the form (Ranichiro Sawaki met Kogiku last fall). In this way, one event shall be established based on one event concept (acquaintance), person (Junichiro Sawaki, Kogiku), time (last fall), and other places that do not appear here. It should be noted that descriptions of sexual characteristics such as “painter's” and “Maiko J in Gion” are assumed to be included as attribute values in the information of objects including persons, and It shall not be included in the expression.

 Next, these phenomena are semantically kneaded by a sexual relationship. This relationship applies not only to the connection of two events, but also to partial segments of the narrative tree. In this way, a hierarchical story tree is constructed in which the terminal node is an event and the other nodes are related. These relationships correspond to those formulated as being made by narrative techniques in the present invention.

 However, it is difficult to structure all the phenomena included in the story as one story tree at a time, and scenes have been introduced as a unit that bundles a tree of a certain size. A scene is a group of semantic units in a narrative determined by the same characters, timeliness and location. Therefore, a plurality of such story-unit story trees are configured. This is called an “r scene tree”. The level of the fast chain of events at the terminal node in the scene tree is called "construction". Since a story is a unique form of discourse that revolves around a chain of events based on a time cabinet, it is useful to introduce such a unit of scene defined by time and space. (However, there is no criterion for the continuity of the time and the identity of the place. For example, some scenes are converted at the second level, while others are longer-term. Figure 24 shows an example in which the following S-head scene is represented by a story tree.

a. Painter Junichiro Sawaki The last time I met Kogiku, a maiko from the surrounding area, last fall.

b. Sawaki leaves the studio,

c While strolling around Egano,

d. On the roadside, there was a girl painting.

 e. Puku. Long hair; a girl like a school student.

f. If you take a peek,

g. It is pale, but the autumn Sagano is really well painted.

h. It was new whether the pure Japanese a view was drawn with a sharp feeling like Matisse and Picasso.

i. Although young, Sawaki, who is a well-known B family, is a member of Jen S, j. Rarely did you get interested in amateur paintings,

k. At that time, what?

 1. I was staring at the picture.

m. A girl who pretends to be a person

n.'s face had no makeup,

o. The long eyelashes and long eyes were impressive.

 P. Lips are pale pink, like a peach blossom.

q. "It's pretty good.

 Γ. I suppose, Sawaki called out.

s.r, but the mountain color is fast.

t. The girl replied,

u. After that, I was absorbed in painting,

 V. I no longer see Sawaki.

 W. I don't think that girls don't like to pull with a stranger,

X. Sawaki gently left the place.

 6.2 Scene speed and prototype structure

 Tables 6 to 8 summarize the narratives composed of scenes as basic units. When a scene cannot be represented by one event, the scene is represented as a succession of several events. In these tables, this is indicated as “Scene 內 Event”.

 This is a text summarized at the speed level of the scene. The text is developed according to the typical sequence of a mystery novel, "A murder has occurred, and police and public figures have investigated and inferred, and the culprit has been arrested." In order to recognize such an abstract structure, it is necessary to assume the existence of an intellectual arrowhead unit that organizes a text structure (plot) consisting of the intertwining of various disturbed events at a higher level. . Here, such a knowledge unit is named “professional '/ automatic pattern”. In other words, the professional's / automatic pattern is an intelligent unit for more abstractly structuring the level of the fast chain of the scene in the story expression. In this example, a plot pattern of “investigation of incidents—inference-detection of culprit” is used, and this plot pattern is considered to be typical in an inference novel. (However, in this case, there is a part that introduces the protagonists before the occurrence of the crime, and the occurrence of the incident is repeated twice. The leader j appears frequently in many stories. So, we can extend the above-mentioned professionals, such as r * 一 一 一 事件 · · · 調査 調査 "" ま た "" ま た "" "" "反復 反復 反復It is possible to think of it as if the scene organizes and organizes the events at the lowest level, some scenes come together to bridge the higher-level semantic units, '/ Is governed by each component of the pattern.

 Here, we include the pro pattern as a set of nodes below the vertices in the story tree, leading to a chain of events that correspond to the scene or the sub-events needed to create the scene. The thing 捃 tree is called “pro” / to tree j. Then, the story summarized at the level of the terminal node of the professional ', / tota, that is, at the level of the scene or its lower event, is referred to as "pro', / to j. Is divided into Figure 25 and Figure 35.

In the 'Lepert of Proto', the cause of the murder, which led to it. It is first revealed to the person through guesses, interviews, and discourse of the characters. In a scene chain, there are cases where several scenes are embedded in one scene. This pattern indicates that the scene in which the scene is unfolded by the character is introduced in the space-time of Table 6 through Table 8, which are denoted as `` embedded scenes ''. ing. For example, in scene 2 of scene 25, a past scene based on Kogiku's recollection is embedded, which is the key to unraveling the mystery of the killing case. Here, an expression like 1 (1) represents a lower event that composes a scene, while an expression like 1 indicates that another scene is embedded in the embedded scene. Is represented. Embedded scenes may not always be real (for a story), but they may be fictional scenes, false guesses, predictions / estimations, etc. (a kind of possible world). The temporal non-linearity of the development of such cases is most pronounced in reasoning novels, or similar structures are frequently found in many other stories. For example, in the middle of the story, the character may go back to the childhood reminiscence, or in some parts of the story, past episodes may be recollected as flashba's. The reader understands the story as a whole by restoring these intricate times into a series of lines. In the case of a mystery novel. When the culprit and his motive are known, the mystery is resolved when the story is restored along a single time axis, and the story ends. Here, the narrative that evolves along the time axis, that is, the narrative content, is called “ ^r story for a program”. Therefore, the structure of the narrative content must then be clarified by restoring the story as another structural level based on professionals.

6.3 Restoration of story contents and theme patterns

The structure of the story can be restored by rearranging the end of the pro ',.' The professional tree is governed by an abstract knowledge unit of professional, y-patterns. The story's story is called “story. To be more precise, a story is (This refers to the chain of terminal nodes in the story tree.) Γ is considered to be controlled by a knowledge unit called theme pattern j. In the case of this example. Dg Property Acquisition Assuming that one of the bars is used, it is assumed that the heir is used. The emergence of-genuine killing (losing) "and ^Γ investigation, reasoning-arrest (success) J are interposed between them (and the introduction of the detective role is added). "A detective who picks up a boss and a real detective appears-a real appearance-a real killing (failure)-an investigation and a reasoning-an arrest = a property acquisition (failure)". "Killing (failure)" and "investigation · reasoning" are repeated twice, so ^r pick up-detective appearance-genuine appearance-genuine killing (failure)-inquiries-reasoning -Genuine killing (failure)-鉀 Investigation and reasoning-arrest = property acquisition (failure) " It is.

This puma pattern is a different concept from the above-mentioned professional pattern, and the same story created using a certain theme pattern can be expressed by various different plot patterns. The plot tree and the story tree are governed by different principles, as shown in Tables 9 to 12. Table 9 to Table 12 show the fast chain of the scene or its constituent elements. The plots from Table 6 to Table 8 were transformed into a story. 2 means the embedding scene, and the number in the brackets "/" also means the lower event. For example--46 25-1-1 indicates the embedded scene 1 of the scene 25 in the professional game. Table 9 Power and Tables 12 show that professionals, as a representation of objects, are organized according to the order of narrative of the time mechanism in the narrative world. . This is shown in Fig. 36 through Fig. 40, which is a story story structured based on the theme pattern.

 Fig. 41 shows the relationship between the professional tree and the tree; the tree has the following responsive relationship.

 <Pro ',, pattern> <Components in theme pattern>

Introduction Detective appearance

Incident (1) Murder exposure Π)

Investigation · Reasoning (Π Real killing Π), Translating · Reasoning (1)

Occurrence (2, Murder Exposure (2)

Investigation · Reasoning (2) Flirting of the two scholars, genuine killing (1), genuine appearance,

 Genuine killing (2), investigation · reasoning (2>

Solution Real killing (1), real killing (2), arrest-property acquisition (pastoralization) Is the progress of the theme panel as follows? Is this a professional, ', It is thought that the editing of this story constitutes the professional and software of this story, that is, the story expression <,

 ΓMake-up of the false heir -Detective appearance -Real appearance -Real killing (1) One homicide exposure (1) -Investigation • Reasoning Π) -Real killing (2) -Homicide exposure (2) -Investigation · Reasoning 2) -Arrest = property acquisition (failure) j Based on the progression of such a theme pattern, the following response W section is established.

<Theme pattern> <Components in the plot pattern>

* Investigation and reasoning (2)

 Detective appearance introduced

* Real appearance investigation · Reasoning (2), solution

* Genuine killing (1) Incident occurred (1). Investigation · Reasoning (]), Investigation · Reasoning (2), Resolved Murder exposure (1) Incident occurred (1)

 Silk · Reasoning (1) Translator · Reasoning (Π

* Genuine killing (2) Investigation · Reasoning (2), Resolution

 Murder Exposure (2) Case Occurrence (2)

 Survey · Reasoning (2) Survey · Reasoning (2)

 Arrest-Settled

By the way, this theme pattern is dazzling in such a way that the development centered on the murderer (Niro Sugino) and the development centered on the detective roles (Kogiku, Sawaki) are mixed. I get stuck. The * marked above is the development of Murderer II. And, mainly in the professional "/ r pattern pattern | r | · · 寰 推 及^{Γ Γ Γ} 、 、 、 、 、 、 、 、 、 、 、 、" Appearance j, r Real killing (】> j, r * Killing of objects (2 or embedded to make professional '·.'. The pattern of “pro” is based on the development centered on the detective role. «! The development of the detectives in the theme patterns is almost the same as each« component in the professional ',' pattern, that is, 'Detective appearance introduction, murder

Fl (ι '一 情 生 （い. Iffls ■ 椎】 (])-tone? R · Shiri (1), murder? 5¾ (2 事件 玍). Isj Investigation. Reasoning (2>-Investigation, reasoning (2), arrest-resolution) is established. The murderer's component of the component, "The birth of a heir, the appearance of the real, the real killing (1), the real killing (2) j has been introduced in pieces. In the early stages of the professional / academic event, the events in the story were not introduced in detail, or incorrect inferences were made. Or as the professionals progress, more detailed and accurate descriptions will be made, ultimately elucidating all remaining questions in the story at the stage of (\ dg resolution) Leads to.

 To be specific, the "make up of false heirs" in the poma pattern is a professional, through a speech based on Kogiku's recollections and inferences in "investigation and reasoning (2)" in the professional pattern, (25-1-~ 25-1-5, 28-1). "Genuine appearance" is based on Kogiku's inference in "key S. reasoning" (25-1 (!) ~ 25-1 (5) Oihiro Utterance based on the recollection of Kariya (35-5 -1 to 35-5-2) in "Solution" and utterance based on Kogiku's reasoning (36-2 Through (2)), “real killing Π)” is based on Kogiku's inferences in “Survey 'Reasoning (2)” (25-3 (1)-25-3 (2)) and “Solution j. The utterance based on the inference of Kariya and Kogiku (35-4 (~ 36-2 (3, "Real killing (2)" is the utterance based on the inference of Kariya in Solution j (35-2 ～ 35- 3> and Kogiku's inference 発 (36-ΐΠ) -36-3)) and . Survey reasoning (2> _ | through the speech (22-1～22-3 based on the reasoning of Kogiku in), have been introduced in each plot in me.

 In conclusion, in a mystery novel composed of a killer and a detective role, in a plot composed mainly of the detective role as in this example, the killer who constitutes a story through recollections and reasoning We can assume that there is a general rule that the development of the case on the side will be revealed gradually.

7.5 Model of story making process

 Considering story making as a process that reverses the story analysis as described above, the legitimacy of the story making process dealt with in the present invention is proved.

 1. From theme to story: The theme that governs the story is embodied as a story. In the example of the story, based on the theme of "Niseko's spouse's pick-up-property acquisition (failure)", the fake spouse's pick-up and murder and its exposure were revealed. The story content was assembled.

 2. From a story to a professional, to a story: The development of the story according to the time sculpture is converted into a story expression as the text I. In the example story, the murder case and its investigation and reasoning are performed in a way that the passing scene is introduced fragmentarily into the current scene mainly by the utterance of recollection and reasoning by the characters. The flow of the whole story was summarized and shown in a limited process.

 All this is done through the extension or refinement process of the product IS and its conversion or transformation process. Creating a story from a theme is an extension of the theme pattern that expresses the theme to a story tree. Creating a story from a story, and creating a story from a story as a narrative that expresses the contents of the story. This section describes the structural transformation from one story tree to a plot tree, which is the end of the story for expressing the story.

In this case, the analysis was limited to a specific type of substance called a mystery novel. It is clear that the structural features revealed are not only unique in the detective novel, but are also common in other stories. Therefore, the result of this analysis can be used as an indication of the validity as a model for story creation in the present invention.

 7 Experimental example of story structure creation

 Here, an experiment example of creating a story structure using an experimental system constructed based on the system construction method will be described. The input to the European system is one or more fragmentary events, but here we have an example (kill ((agt agt &-ro) (ob.iagt & small)) (tim tim & midnight 1) (loc loc & Place 1))) as input. An event concept such as "kill" is put at the top, followed by a number of character pairs such as subject (agt), object (0 bj), time (tim), and location (loc>) and their value pairs. The list is called an “event.” Each value is the name of a component in the knowledge base, and the & symbol is used in the value to indicate an instance in the knowledge base. In this example, agt &-ro, agt & small, tim & midnight 1, lac & location 1 are instances, whereas in the case of a frame, the ¾ symbol is like an agtY dancer. Each instance contains some specific characteristics: "Ichiro kills Kozuzu at midnight 1 at location 1 J .

7.1 Example of creating a core story story structure

 From this input, the following "core story" is created: As mentioned above, the core story is a form of ft.'S first story tree format that converts a fragmentary event of input into a story tree format.

<Example 1 of creating a Koasutori>

($ Lord B (own

 ((AGT AGT & Hayakawa) (TIM #: G1093) (LOC #: G1099) (OBJ TH & Property)

 (DEG MOD << millions)); a

 ($ Parallel (Make ((AGT AGT & Hayakawa)) (TIM #: G1091) (LOC #: G1100)

 (OBJ AGT & -ro))): b

 (Make ((AGT AGT & Hayakawa)) (TIH «: G10B9) (LOC *: G110D

 (OBJ AGT & Kozei)))) ； c

 (ίGoal-Plan

 ($ Goal Stakeholder-Purpose (I want ((AGT AGT & -Chiro)) (TIM #: G1087)

 (LOC »: G1102))) ； d

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property)

 (TIH NIL) (LOC NIL))))) ； e

 ($ Plan (Kill ((AGT AGT & -ro)) (OBJ AGT & Kozuzumi) (TIM TIM & Time 1)

 (LOC L0C & Location 1)))) ； f

 ($ Effect ^ reason ^ relationship-purpose

 (Exposed ((AGT AGT4SAYA) (TIM #: G1095)

 (LOC l: G1104)));; g

 (Kill ((AGT NIL) (OBJ AGT & Kozun)) (TIH »: G1095)

 (LOC and 0C & «place 1))): h

(Arrested ((AGT THX Police Officer)) (OBJ AGT & -ro) (TIM #: G1097) (LOC Gl 105))))))); i For simple understanding, each event is simply expressed in natural B language as follows. However, all descriptions should be based on the passing tense.

ΓHayakawa owned huge properties. Hayakawa got Ichiro. Hayakawa has a calm calm. _—Rod wanted to monopolize Hayakawa's property. _—Rod killed _Kozushi . saya revealed who killed Kozushi. Police arrested Ichiro. ".

 As shown in the above example, the object is a hierarchical tree with the event as the terminal node and the cabinet member as the other node. The name of the M department is preceded by a $ sign. This is illustrated in FIG. The fast starvation of events in this story tree is the core story. this is,

^This is a pattern in which the input event is included in a contextually consistent manner in the expression of the subject that often appears in reasoning novels, “murder for the purpose of acquiring property and its exposure”. Other than this, it is possible to create a coarse bets one ¹ 'one different forms from the same input. In principle, core stories can be created for the number of narrative techniques applicable to material information.

<Example of creating a caste 2>

($ Goal-plan

 Goal ($ Relation-Purpose (I want ((AGT AGT & -Chiro) (TIM NIL) (LOC NIL.)))

 (Kill ((AGT AGT & —Chiro)) (OBJ AGT & Kozushi)

 (TIM TIM & Time 1) (LOC L0C & Location 1)))))

 ($ Plan (Strangle and kill ((AGT AGT & -Jiro)) (OBJ AGT & Kozun) (TIM Time 1)

 (LOC L0C & Location 1))>)

 ($ Effect (Die ((AGT AGT & -Chiro)) (OBJ AGT & Kozuzu) (TIM TIM & Time 1)

 (LOC L0C & Location])))))

<Example 3 of making a caste>

 ($ Sequence (jumps ((AGT AGT & -ro)) (OBJ AGT & Kozushi) (TIM TIH & time 1)

 (LOC L0C & Location〗)))

 (Tighten ((AGT AGT & -Chiro) (ΤΙΚTime l) (LOC LCJC & Location 1) (OBJ 0BJX neck))) (Pain (((AGT AGT & -Chiro) (TIM TIM & Time 1) (LOC L0C & Location 1)))

 (Suffocate ((AGT AGT & -ro) (TIM TIM & Time 1) (LOC L0C & Location 1)))

 (氕 艳 Yes ((AGT AGT & —Chiro)) (TIH Time 1) (LOC L0C & Location 1)))

 (Die ((AGT AGT & -IB) (TIM TIM & Time 1) (LQC L0C & Location 1))))

<Cost 1 '(Example 1 of creation 4)

 Iki (Kill ((AGT AGT & -Chiro) (OBJ AGT & Chozu)) (TIM TIM & Time 1) (LOC L0C & Location 1)))) (Stealing ((AGT AGT & Choro) (FRM AGT & Chozu)) (OBJ 0BJ5S )

 (TIM TIM & Time 1) (LOC L0C & Location 1))))

<Example of core story creation 5>

 ($ Reason (I hate ((AGT AGT & -SR) (OBJ AGT & Kozutsu (TIM *: G888) (LOC «: G889)))

 (Kill ((AGT AGT & -Chiro) (OBJ AGT & Small)) (TIM T1M & Time (LOC L0C & Location 1) <Coast tory creation example 6>

($ Reason (Kill ((AGT AGT & -IR) (OBJ AGT & Small)) (TIM TIK & Time 1) (LOC L0C & Toshiro 1)))峥) (TIM »: G890) (LOC«: G89I))) ' A plurality of stories are created from all these stories. Here, the story creation from core story creation example 1> is shown. Core stories and stories basically form a narrative tree that follows the progression of temporal events. Extending a story tree extends a particular node. It is done by repeatedly embedding it into the end of the story as a whole, 7.2 Examples of story structure creation

<Example of story creation 1>

 ΓHayakawa owned huge properties. Hayakawa got Ichiro. Hayakawa made Kozuki. —Long wanted to monopolize Hayakawa's property. Ichiro killed Kozuki. Ichiro robbed Kozushi of money. Sava reveals who killed Kozushi. Police officers searched for Ichiro. Police arrested Ichiro. Police confirmed Ichiro. Police officers displayed a police handbook in Ichiro. Police officers handcuffed Ichiro. Police detained Ichiro for police. "

($ Subject (own

 C (AGT AGT & Hayakawa) (TIM #: G903) (LOC *: G909) (OBJ TH & Property)

 (DEG M0D ¾ million)))

 ($ Parallel (Make ((AGT AGT & Hayakawa)) (TIM #: G901) (LOC #: G910

 (OBJ AGT & -ro)))

 (Make it ((AGT AGT & Hayakawa) (TIM <t: G899) (LOC #: G911)

 (OBJ AGT & Kozhi)))))

 ($ Goal-plan

 ($ Goal ($ Relationship-Purpose (AGT AGT & -Chiro) (TIH <t: G897)

 (LOC #: G912)))

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property)

 (TIM NIL) (LOC NIL)))))

 Plan ($ sequence (Kill ((AGT AGT & -Jiro)) (OBJ AGT & Kozuzu)

 (TIK time 1) (LOC L0C & location 1)))

 (Take away ((AGT AGT & -ro)) (FRH AGT & Kozuzu)

 (OBJ 0BJ¾Money) (TIM TIM & Time 1)

 (LOC #: G913)))))

 ($ Effect ($ reason ($ person-purpose

 (Violent 15 ((AGT AGT & SAYA) (TIH «: G905)

 (LOC #: G914)))

 (Kill ((AGT NIL) (OBJ AGT & Kozuzu))

 (TIM #: G905) (LOC L0C & »location 1))))

 ($ Sequence

 (Search ((AGT ΤΗ¾ί Police Officer)

 (OBJ AGT & —ro) (TIH «: G907)

 (LOC #: G915)))

 (Capture ((AGT THX Police Officer) (OBJ AGT & -ro)

 (TIH #: G907) (LOC *: G9I5)),

(Verify ((AGT ΤΗ5! »Inspector) (OBJ AGT & —ro) (TIM #: G907)

 (LOC #: G915)))

 (Show ((AGT TH¾ Police Officer) (TO AGT & -ro)

 (QBJ OBJ¾ Police Handbook) (TIM *: G907) (LOC #: G915)))

 (Yes ((AGT TH¾g Inspector) (TO AGT & -ro)

 (OBJ QBJ¾ handcuffs) (TIM #: G907)

 (LOC #: G915)))

 (To be detained ((AGT TH¾ police officer)) (OBJ AGT & -ro)

 (TO TH¾ Police) (TIM #: G907)

 (LOC j »: G915)))))))))

 Performing the tasks of narrative techniques or the extension of this particular node, the narrative technique to be executed at each point in the creation is determined through a flurry of narrative strategies that refer to narrative parameters such as.

 <Story parameters of story creation example 1>

 ((* Puma * Murder by the Minister of Industry) (* Theme * High) (* Genre * NIL) (* Length * Short) (* Redundancy * High) (* Narrative * High) (* (* Characteristics * *) (* Character-Intention * High) (* Character-Psychicity * Medium) (* Viewpoint * Tokichichi) (* Repeatability * Medium) (* Details Degree * high)

 (* Story type * novel))

Therefore, the Itarui configuration of the story parameters, different scan WINCH one Lee as shown below from the same coarse Torrey is to be automatically created _β

<Example 2 of story creation>

"Hayakawa wanted to own a huge property. Hayakawa made a huge property. Hayakawa owned a huge property. Hayakawa wanted to have children. Hayakawa had children for agtJ! Character. was Mase produced Hayakawa was earned Ichiro Hayakawa wanted to earn the children Hayakawa _e阜川that was sired their children to agt¾charac ter is c earned a small static -... Ichiro is to monopolize the property of Hayakawa Wanted: —Ichiro wanted to kill Kozushi, Ichiro slaughtered Kozushi, Kozada was dead, and saya wanted to violate who killed Kozashi. Guessed who killed Shizuka, saya ascertained who killed Shizuka, saya revealed who killed Shizuka, and a police officer wanted to arrest Ichiro. A police officer arrested Ichiro.

(Theme * Murder by Minister of Industry.) (* Theme * ¾) (* Chanl * NIL) (* Length * Short)

(* Redundancy * medium) (* narrative * medium) (* reality * medium) (* concrete * medium) (* character-intention * me)

(* Character-Psychological * Medium) (* Viewpoint * Partial knowledge) (* Repeatability * Medium) (* Details * Medium)

 (* Skirt type novel *))

($ Main Β ($ goal-plan

 Goal ($ ΜRelation-Purpose (I want ((AGT AGT & Hayakawa) (TIM NIL) (LOC NIL)))

 (Own ((AGT AGT & Hayakawa) (TIH #: G903)

 (LOC «: G90g> (OBJ TH & Property)

(DEG HODX Huge Man: ($ Total sleep (Profit ((AGT AGT & Haya ΠΠ (TIM #: G90 ^) (LOC #: G909)

 (OBJ TH & Property) (DEG H0D

 <$ Effect (Own ((AGT AGT & Hayakawa) (TIM «: G903) (LOC«: G909

 (OBJ TH & Property) (DEG M0D ¾ million)))

 Parallel ($ goal-plan

 ($ Megure ($ W Section-Purpose (I want ((AGT AGT & Hayakawa)) (TIM NIL) (LOC NIL)))

 (Make ((AGT AGT & Haya Π |> (TIM #: G901))

 (LOC #: G910) (OBJ TH¾Child))))) ($ Plan (Birth ((AGT AGT & Haya ΙίΠ CTIM #: G901) (LOC #: G910)

 (OBJ TH¾ child) (MED AGT¾CHARACTER))))

 ($ Effect ((AGT AGT & Hayakawa) (TIM #: G901)

 (LOC #: G910) (OBJ AGT & —ro))))))

 ($ Eye Building-Plan

 ($ Goal ($ relationship-purpose (desired ((AGT AGT & Hayakawa) (TIM NIL) (LOC NIL)))

 (Make ((AGT AGT & Hayakawa)) (TIM #: G899)

 (LOC #: G911) (OBJ TH¾ child))))

 Plan (Give ((AGT AGT & Hayakawa) (TIM *: G899) (LOC #: G911)

 (OBJ TH children) (MED AGHCHA ACTE))))

 ($ Effect (Make "AGT AGT & Hayakawa") (TIM «: G899)

 CLOC <t: G911) (OBJ AGT & Kozuzu))))))

 ($ Goal-plan

 ($ Goal relationship-purpose (desired ((AGT AGT & -ro) (TIM #: G897) (LOC #: G912))>

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property)

 (TIM NIL) (LOC NIL)))

 ($ Plan ^ goal-plan

 ($ Eyes building ($ person-purpose (desired ((AGT AGT & -ro) (TIM NIL) (LOC NIL))))

 (Kill ((AGT AGT & —Chiro)) (OBJ AGT & Kozuzu :)

 (TIK time 1) (LOC *: G913)))))) ($ Plan (It kills ((AGT AGT & —Chiro)) (OBJ AGT & Kozushi)

 (TIM TIM & Time 1) (LOC L0C & Location 1))))

 ($ Effect

 (Die ((AGT AGT & Small) (TIM TIM & Time CLOC L0C & Location 1))))))

 目 棵 ($ M section-purpose

 (I want ((AGT AGT & SAYA) (TIH NIL) (LOC NIL))))

 (Violent ((AGT AGT & SAYA) (TIM #: G905)

 (LOC #: G914)))

(Kill ((AGT NIL) (OBJ AGT & Kozu *) (TIM «: G905) (LOC LOC & fllFFfl)))))) ($ Planner -Purpose

 Shishi Kanashiru ((AGT AGT & SAYA) (TIM * t: G905>

 (LOC #: G914)))

 (Kill ((AGT NIL) (OBJ AGT & Kozushi)

 (TIK #: G905) (LOC LOC & Location 1))))

 ($ Clerk-purpose

 (Check ((AGT AGT & SAYA) (TIM #: G905)

 (LOC #: G914)))

 ($ Relation-Purpose

 (Guess ((AGT AGT & SAYA) (TIM #: G905)

 (LOC «: G914)))

 (Kill ((AGT NIL) (OBJ AGT & Kozushi))

 (TIM #: G905)

 (LOC LOC & Location 1)))))〉

 ($ Effect ($ 閱 Relation-Purpose

 (Exposed ((AGT AGT & SAYA) (TIM <t: G905)

 (LOC »: G914)))

 (Kill ((AGT NIL) (OBJ AGT & Kozuzu))

 (TIM <t: G905) (LOC LOC & Location 1))))))

 ($ Goal-plan

 ($ Goal ($ M Section-Purpose

 (I want ((AGT THX police officer) (TIM NIL)

 (LOC NIL)))

 (Arrested ((AGT TIU Police Officer) (OBJ AGT & -ro)

 (TIM «: G907) (LOC #: G915))))) ($ Sleep (Capture ((AGT TH¾ Police Officer) (OBJ AGT & -Chiro)

 (TIM *: G907) (LOC #: G915))))

 ($ Effect (Arrested ((AGT TH5S Police Officer)) (OBJ AGT & -ro)

 (TIM #: G907)

 (LOC »: G915)))))))))

 In the example of the following story, the theme parameter * of the story parameter is set to a large value, so the theme of "murder by the Minister of State and Government" is used at the end of the story, The example of story creation 4>, which is one of the stories that are detailed in the downward direction, is an extension of the example 3> of story creation. This is a radical story that does not rely on a specific pattern. (In this experimental example, are all the "sense novels" 1L stories connected? Enable the value setting of other types of stories in the story parameters and create typical patterns of other types of stories. If Alcoholicism is registered as the narrative branch method, it will be possible to automatically create Eve's stories other than inferential novels.)

<Example 3 of story creation>

Hayakawa stole gold and owned a huge fortune. agt character is Ichiro Since giving birth, Hayakawa got Ichiro (as a child), Hayakawa also got Kozuki (as a child), and Ichiro wanted to monopolize his property, killed Kozushi, and Agt \ ¾saya revealed who killed Kozushi, and a police officer arrested Ichiro and detained him. "((* Theme * murder by heritage heir) (* theme *) (* Genre * NIL) (* Length * Short)

(* Redundancy * medium) (* narrative * medium) (* logic * high) (* concrete * low) (* character-intention * medium) (* character-psychological * medium) (* Story type novel "(* viewpoint * partial knowledge) (* repeatability * low) (* detailed * low))

 ($ Subject ($ reason ($ reason (steal ((AGT AGT & Hayashi)) (OBJ 0BJ¾gold)) (TIM #: G934)

 (LOG #: G935))

 (Own ((AGT AGT & Hayakawa) (TIM #: G903) (LOC #: G909)

 COBJ TH & Property) (DEG M0D ¾ million))))

 (Rejoice ((AGT AGT & Hayakawa) (TIM «: G918) (LOC #: G919))))

 ($ Parallel ($ Reason (Birth ((AGT AGT & CHARACTE)) (TIM U: G922)

 (LOC tt: G923> (OBJ AGT &-ro))))

 (Make ((AGT AGT & Hayakawa)) (TIM #: G901)

 (LOC «: G910) (OBJ AGT &-ro))))

 ("Make ((AGT AGT & Hayakawa) (TIM #: G899) (LOC *: G911)

 (OBJ AGT & Kozhi)))))

 Goal-Plan

 ($ Goal ($ 閱

 (I want ((AGT AGT & -Chiro) (TIM «: G897) (LOC #: G912)))

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property) (TIM NIL)

 (LOC NIL)))))

 Plan ($ Reason (Kill ((AGT AGT & -Jiro)) (OBJ AGT & Kozuzu)

 (TIM TIM & Time 1) (LOC L0C & Location 1)))

 (Treat ((AGT AGT & -ro)) (OBJ AGT & Small)

 (TIM 4t: G926) (LOC »: G927)))))

 ($ Effect ($ reason ($ relation-purpose

 (Violent S ((AGT AGT & SAYA) (TIM #: G905) (LOC »: G914)) (Kill ((AGT NIL) (OBJ AGT & Kozushi)) (TIH #: G905)

 (LOC L0C & Location 1))))

 ($ Reason (AGT TH¾ Tao to be arrested) (OBJ AGT & -Sli)

 (TIM #: G907) (LOC #: G915)))

 (Detain ((AGT TH¾ Police Officer) (OBJ AGT & -ro,

 (TIM «: G930) (LOC *: G931)))))));

 <Example of story one 4>

Peichiro wanted to kill Small W. Ichiro wanted to strangle her. Ichiro jumped into a small hatch, and _t . Small W, who wore her neck, suffered. Xiao has died and died. j

((* 烊 Fineness * «) (* Anti« Sex * Medium, "Visibility * Partial knowledge") (* Character-Psychological * Medium)

<Intentions of the * * Specificity * S ;, (* 1 § property * Ά) ⁽ * redundant * SS ' (* Length * Short) Genre * KID (* Unique * Low) (* Puma * NIL)

 (* Story type * novel))

 Main Building-Planning

 ($ Goal ($ relation-purpose (desired UAGT AGT & -ro) (TIM NIL) (LOC NIL)))

 (Kill ((AGT AGT & —Chiro)) (ΟΒ,] AGT & Kozei)

 (TIM TIH & Time 1) (LOC L0C & Location 1)))))

 ($ Plan Goal-Plan

 ($ Eyes building!

 (I want ((AGT AGT & -ro) (TIM NIL) (LOC NIL)))

 (Strangle and kill ((AGT AGT & -ro)) (OBJ AGT & Kozushi)

 (TIH TIM & Time 1) (LOC L0C & Location 1)))))

 ($ Plan

 ($ Sequence (jumping (CAGT AGT & -ro)) (OBJ AGT & -ro)

 (TIM TIM & Time 1) (LOC L0C & Location 1)))

 (Cotton ((AGT AGT & —Chiro)) (TIM TIM & Time 1)

 (LOC L0C & Location 1) (OBJ 0BJ¾head)))

 (Suffer ((AGT AGT & Small)) (TIM TIM & Time 1)

 (LOC L0C & Location 1)))

 (Suffocate ((AGT AGT & Kozushi)) (TIM TIM & Time 1)

 (LOC L0C & Location 1)))

 (Be fainted ((AGT AGT & Kozushi)) (TIM TIM & time 1)

 (LOC L0C & Location 1)))

 (Die ((AGT AGT & Kozushi) (TIM TIM & Time 1)

 (LOC L0C & Location 1)))))

 ($ Effect (Die ((AGT AGT & Kozushi)) (TIH TIM & Time I)

 (LOC L0C & Location 1)))))))

 Next, the following plots are created based on <Example 1 of story creation> (Originally, multiple plots are automatically created from each story.). It is constructed based on the viewpoint of one of the characters, agt & Hayakawa (the viewpoint is also specified as a setting for the story parameter.) In other words, events that this person does not know directly are included in the story tree. An “abbreviation” symbol is added and this event is introduced into the story at a later point in time through the discourse of another person, so the storyline develops differently from the cubism in which the event occurred In this way, the story tree expressing the story, which is the progress of events based on temporal progression, is transformed into a story tree expressing a plot that indicates the progress of events as stories. (In the Japanese language, It expresses the possession person of the point as "I".>

7.3 Example of plot structure creation

<Plot creation example 1>

ΓI stole the money. I owned a huge fortune. I was pleased. ag «character gave birth to Ichiro. I got Ichiro. I got a calm. agtXcharacter told me: Ichiro wanted to monopolize my property. Ichiro killed Kozushi. Ichiro puts a small W 50; _f saya revealed who killed Kozushi. Officer Tie arrested Ichiro. Police detained Ichiro. J

 ($ Subject Reason Reason (Stealing [(AGT AGT & Hayakawa) (OBJ 0BJX Fri)) (TIM #: G934)

 (LOC #: G935))

 (Own ((AGT AGT & Hayakawa) (TIM *: G903) (LOC »: G909)

 (OBJ TH & Property) (DEG H0D ¾ million))))

 (Rejoice ((AGT AGT & Hayakawa) (TIM *: G918) (LOC #: G919)))))) ($ Parallel Reason (Birth (((AGT AGTXCHARACTE) (TIM #: G922)

 (LOC #: G923) (OBJ AGT & —ro)))

 (Make ((AGT AGT & Hayakawa)) (TIM »: G901) (LOC»: G910)

 (QBJ AGT & -ro))))

 (Make ((AGT AGT & Hayakawa)) (TIH #: G899) (LOC #: G911)

 (OBJ AGT & Kozushi))))

 ($ Goal-plan

 ($ Goal ($ relation-purpose

 (Desired ((AGT AGT & —ro) (TIM #: G897) (LOC #: G912)))

 (Exclusive ((AGT AGT & -ro)) (OBJ TH & Property) (TIM NIL)

 (LOC NIL))) omitted))

 ($ Plan ($ reason (kill ((AGT AGT & -Jiro)) (OBJ AGT & Kozuzu))

 (TIM TIM & Time 1) (LOC #: G913)) omitted)

 (Treat ((AGT AGT & —Chiro)) (OBJ AGT & Kozuzu)

 (TIM <t: G926 (LOC «: G927)) omitted)))

 (ίEffect ($ Reason ($ W Section-Purpose

 (Exposed ((AGT AGT & SAYA) (TIM »: G905)

 (LOC #: G914)))

 (Kill ((AGT NIL) (OBJ AGT & Kozuzu))

 (TIM *: G905) (LOC L0C & Location 1))) omitted)

 ($ Reason (Arrested ((AGT THX police officer)) (OBJ AGT & -ro)

 (TIM #: G907) (LOC #: G915)) Omitted) ($ Move (to be detained ((AGT THX Police Officer) (OBJ AGT & -ro)

 (TIM #: G930) (LOC #: G93D) omitted)

($ 锬

 (Say ((AGT2CHA ACTE) (OBJ AGT & Hayakawa)))) ($ sequence

 ($ M Section-Purpose

 (I want ((AGT AGT & —Chiro)) (TIM #: G897)

(LOC *: G912)))

 (Exclusive ((AGT AGT & —Chiro))

 (OBJ TH & Property)

(TIM NIL; (LOC NIL))) (kill

 ((AGT AGT & -ro) (OBJ AGT & Kozushi)

 (TIM TIM & Time 1) (LOC *: G913)))

 (Treat

 ((AGT AGT & -ro) (OBJ AGT & Kozuzu)

 (TIM #: G926) (LOC #: G927)))

 ($ Clerk-purpose

 (Exposed ((AGT AGT & SAYA) (TIM i: G905)

 (LOC #: G914)))

 (Kill ((AGT NIL) (OBJ AGT & Kozuzu))

 (TIM i: G905) (LOC L0C & Location 1)))> (Arrest

 ((AGT TH Police Officer) (OBJ AGT & -ro) (TIM i: G907) (LOC #: G915)))

 (To be detained

 ((AGT TH¾ Police Officer) (OBJ AGT & -ro)

 (TIM #: G930)

 (LOC l: G931))))))))))))

 On the other hand, the following professional ',' is an example of a story tree transformation from the same story based on the viewpoint of another character agt & saya.

<Example of creating a professional / '

^Γ I revealed who killed Kozushi. agt¾character told me. Hayakawa inherited his property. Hayakawa owned a huge fortune. Hayakawa was relieved. Hayakawa got Ichiro. Hayakawa made Kozuki. Ichiro was hoping to monopolize the property of Hayakawa _e - wax killed a small static. Ichiro treated Kozuki. (After that) the agt¾character told me. Police arrested Ichiro. Police detained Ichiro. j

 ($ Primary S ($ reason ($ reason (inherited AGT AGT & Hayakawa)) (OBJ TH¾ property)

 (TIM «: G958) (LOC»: G959)) omitted)

 (Own ((AGT AGT & Hayakawa) (TIM #: G927) (LOC «: G933)

 (OBJ TH & Property) (DEG H0D ¾ million)) omitted))

 (Relieved ((AGT AGT & Hayakawa) (TIM «: G942 (LOC«: G943) omitted)))

 ($ Parallel ($ Reason ((AGT AGTXCHARACTER) (TIM #: G946)

 (LOC #: G947) (OBJ AGT & -ro) (AIT TH .Child) Ministry of Bft) '(Make ((AGT AGT & Hayakawa) (TIM *: G925) (LOC #: G934)

 (OBJ AGT & -ro) omitted) "

 (Make ((AGT AGT & Hayakawa)) (T1H #: G923) (LOC *: G935

 (OBJ AGT & small hatch) omitted)))

 ($ Eye Building-Total Sleep

 ($ Goal ($ M Section-Purpose

(I want ((AGT AGT & -ro) (TIM #: G921) (LOC *: G936))) (Exclusive ((AGT AGT & -ro) (OBJ TH & Property) (TIM NIL) (LOC NIL))) Omitted))

($ Plan Reason (Kill ((AGT AGT & -Jiro)) (OBJ AGT & Kozushi)

 (TIM Time (LOC L0C & Location Π) omitted) (Treat ((AGT AGT & —Chiro)) (OBJ AGT & Kozuzu)

 (TIM #: G950) (LQC #: G951) Omitted)))) ($ Effect ($ Reason ($ Move ($ 閱 Relation-Purpose)

 (Exposed ((AGT AGT & SAYA) (TIM #: G929 ^

 (LQC #: G938)))

 (Kill ((AGT NIL) (OBJ AGT & Kozushi))

 (TIM #: G929 (LOC L0C & Location 1))))) ($ Ken (say ((AGT AGT% CHA ACTE)

 (OBJ AGT & SAYA)))

 ($ Sequence (inherit

 ((AGT AGT & Hayakawa) (OBJ THX Property) (TIM #: G958) (LOC #: G959))> (Own

 ((AGT AGT & Hayakawa) (TIM #: G927) (LQC #: G933) (OBJ TH & Property) (DEG H0D¾ Huge Man)))

 (feel relieved

 ((AGT AGT & Hayakawa) (TIH #: G942) (LOC #: G943)))

 (Make money

 ((AGT AGT & Hayakawa) (TIM *: G925) (LOC #: G934) (OBJ AGT & -ro))))

 ((AGT AGT & Hayakawa) (TIM #: G923) (LOC «: G935) (OBJ AGT & Kozuzu)))

 (I want

 ((AGT AGT & -ro) (TIM «: G921) (LOC *: G936)))

 (Monopolize

 ((AGT AGT & -ro) (OBJ TH & Property) (TIM NIL) (LOC NIL))))

 («

((AGT AGT & -IB) (OBJ AGT & Small) (TIM T1M & Time 1) (LOC L0C & Location 1)))) (Treat ((AGT AGT & -ro) (OBJ AGT & Kozuzu)

 (TIM #: G950) (LOC #: G951)))))) ($ Reason (Arrested ((AGT TH¾ police officer)

 (OBJ AGT & —ro) (TIM #: G931)

 (LOC #: G939)) omitted)

 (J5 move (to be detained

 ((AGT THX Police Officer) (OBJ AGT & -ro)

 (TIM #: G954) (LOC «: G955)) omitted) Discourse

 (To tell

 ((.AGT AGT¾CHAHACTE) (OBJ AGT & SAYA))) ($

 (arrest

 ((AGT T1U Police Officer) (OBJ AGT & -Chiro) (TIH it: G931) (LOC #: G939)))

 (To be detained

 ((AGT THX Police Officer) (OBJ AGT & -RO) (TIM *: G954)

 (LOC: G955)))))))))))

 <Professional example 3> uses Kozuki as the viewpoint person, and <Example 4> uses Ichiro as the viewpoint person. Since the latter is based on the point of view of the murderer λ itself, the jip leading up to the case is apparent to the gunner from the beginning (thus, it has a different structure than a normal reasoning novel). Example 3>

^ΓHayakawa got me (as a child). (After that) What the agtXcharacter told me was glad he owned the property because he ruled the property.

 (And) agt haracter gave birth to Ichiro, so Hayakawa gave Ichiro (as a child). Ichiro killed me. The agt¾character told the agt 郎 character that Ichiro wanted to monopolize property. Ichiro treated my (corpse). (Afterwards) Where the agtXcharacter crossed the agtXcharacter, a police officer arrested and detained Ichiro because saya revealed who killed me.

X techPplot-by-view * story *)

 Select: (U (AGT & Hayakawa)) (2 (AGT & Shozu)) (3 (AGT & SAYA)) (4 (AGT & -ro))) 2

($ Main reason ($ reason (inherited ((AGT AGT & Hayakawa)) (OBJ TH5! Property)

 (TIM * t: G1016) (LOC <t: G1017)) omitted)

 (Own ((AGT AGT & Hayakawa) (TIM *: G985 (LOC *: G991)

 (OBJ TH & Property) (DEG M0D ¾ million)) omitted))

 (S-F ((AGT Hayakawa) (TIM #: GI000) (LOC #: G1001) omitted))))

 ($ Average (S reason (Birth ((AGT AGTXCHA ACTE)) (TIM «: G1004)

 (LOC i: G1005) (OBJ AGT & -6R omitted))

(Make ((AGT AGT & Hayakawa)) (TIM #: G983) (LOC <t: G992) (OBJ AGT & —ro.) Omitted)))

($ Move (Make ((AGT AGT & Hayakawa)) (TIM «: G981) (LOC #: G993)

 (OBJ AGT & Kozuki)))

 ($ Discourse (say ((AGT AGT% CHA ACTER) (OBJ AGT & Kozuzu))))

 Succession (inherit

 ((AGT AGT & Hayakawa) (OBJ TH¾ property)

 (TIM #: G1016) (LOC «: G1017)))

 (Own

 ((AGT AGT & Hayakawa) (TIM #: G985) (LOC #: G991) (OBJ TH & Property) (DEG H0D0 Huge Man)))

 (Rejoice ((AGT AGT & Hayakawa)) (TIM #: G1000)

 (LOC #: G1001)))

 (Birth ((AGT AGHCHA ACTER)

 (TIM T¾T¾ «: GI 004) (LOC #: G1005)))) (Make ((AGT AGT & Hayakawa) (TIM #: G983)

 (LOC #: G992) (GBJ AGT & -ro))))))

 (I want ((AGT AGT & -Chiro) (TIM «: G979) (LOC«: G994)))) (Exclusive (((AGT AGT & -Curo)) (OBJ TH & Property)

 (TIK NIL) (LOC NIL))) Ministry))

 ($ Plan ($ reason (SI move (kill

 ((AGT AGT & -ro) (OBJ AGT & Kozushi)

 (TIM TIM & Time 1) (LOC #: G995)))

 ($ Discourse

 (Say ((AGT AGTXCHA ACTER)

 (OBJ AGT2CHA ACTE)))

 ($ Battlekeeper-Purpose

 (I want ((AGT AGT & —Chiro)) (TIM #: G979)

(LOC #: G994)))

 (Monopolize

 ((AGT AGT & -ro) (OBJ TH & Property)

 (T1H NIL) (LOC NIL))))))

 (Treat

 ((AGT AGT & -ro) (OBJ AGT & Kozuzu)

 (TIM «: G1008) (LOC *: G1009)))))

 Effect ($ reason ($ relation-purpose

 (Exposed ((AGT AGT & SAYA) (TIM #: G987)

 (LOC #: G996)))

(Kill ((AGT NIL) (OBJ AGT & Kozuzu)) (TIM #: G987) (LOC L0C & Location 1))) Omitted) ($ Reason (arrest

 ((AGT Police Officer) (OBJ AGT & -ro)

 (TIM «: G989) (LQC«: G997)) omitted) ($ Move

 (To be detained

 i (AGT TH% Sf) (OBJ AGTii-rou, (TIM »: G10I2)

 (LOC *: G1013))

 ($ Discourse (say

 (. (AGT AGTXCHA ACTE)

 (OBJ AGT¾CHA ACTE)))

 ($ Sequence

 ($ Cabinet-Purpose

 (Exposed ((AGT AGT & SAYA)

 (TIM «: G987) (LQC«: G996))) (Kill

 ((AGT NIL) (OBJ AGT & Kozhizu)

 (T1K «: G987) (LQC LOC & Location 1))))) (Arrested

 ((AGT TH¾ Police Officer) (OBJ AGT & -Chiro) (TIM «: G989) (LOC * t: G997)))

 (To be detained

 ((AGT TH Police Officer) (OBJ AGT & -ro) (TIM <t: GI012)

 (LOC *: G1013))))))))))))

 <Example 4 of plot creation>

"Agt ¥ ¾character gave birth to me, so Hayakawa gave me (as a child) _c (then) agtXcharacter told me that Hayakawa stole gold, so he owned a huge fortune (Afterwards) I wanted to monopolize the property, and the agt¾character told me that Hayakawa had a child, Kozuki, I killed Kozushi, and treated (corpse). (The ¾, a police officer arrested me. The agtYXcharacter stated that saya had killed me or a small W and had exposed Byby: the police officer had detained me. " }

> (techSplot-bv-view story

 Select: ((1 (AGT & Hayakawa)) (2 (AGT & Kozushi))) (3 (AGT & SAYA)) (4 (AGT & —ro))) "

(Main reason (S reason

 (Steal

 ((AGT AGT & mill) (OBJ 0BJX Fri) (TIH l: G992) (LOC #: G993)) Omitted) (Own ((AGT AGT & Hayakawa) (T1K «: G961> (LOC»: G967)

 (OBJ TH & Property) (DEG HODX Huge Man)) Ministry ½))

(AGT AGT & Kusagawa, TIM »: G976 <(LOC«: G977) omitted) ⁽ $ Parallel ($ reason ((AGT AGT% CHARACTE) (TIM #: G980)

 (LOC #: G981) (QBJ AGT & —ro)))

 ($ Move (Make ((AGT AGT & Hayakawa)) (T1H i: G959)

 (LOC #: G968 «(OBJ AGT &-ro)))

 ($ Discourse (say ((AGT AGT¾CHA ACTE)

 (OBJ AGT & -ro)))

 ($ Sequence

 (Stealing ((AGT AGT & Hayakawa.) (OBJ OBJ Fri)

 (TIM #: G992) (LOC »: G993)))

 (Own ((AGT AGT & Hayakawa)

 fTIM #: G961) (LOC #: G967)

 (QBJ TH & Property) (DEG M0D ¾ million)))

(Relieve ((AGT AGT & Hayakawa) (TIM «: G976)

 (LOC #: G977))))

 (Make ((AGT AGT & Hayakawa)) (TIM *: G957) (LOC #: G969

 (OBJ AGT & Kozei) Omitted)))

($ Estimated Building-Panel ($ Goal ($ Move ($ 閱 Section-Purpose

 (I want ((AGT AGT & -ro) (TIM #: G955) (LOC #: G970)) (Exclusive ((AGT AGT & ro)

 (OBJ TH & Property) (TIM NIL) (LOC NIL))))) ($ discourse (say ((AGT AGHCHARACTER)

 (OBJ AGT & -ro)))

 f accept

 ((AGT AGT & Hayakawa) (TIM l: G957)

 (LOC «: G969) (QBJ AGT & Kozei))))) (ί Plan ($ Reason (Kill ((AGT AGT & -Jiro) (OBJ AGT & Kozuzu))

 (TIM TIK & Time 1) (LOC »: G971)))

 (Treat ((AGT AGT & —Chiro)) (OBJ AGT & Kozuzu)

 (TIM «: G984) (LOC #: G985)))))

 Effect

 (Violent R ((AGT AGT & SAYA) (TIM *: G963)

 (LOC *: G972)))

 (Kill ((AGT NIL) COBJ AGT & Kozushi)

 (TIH #: G963) (LOC L0C & Location 1))) Omitted) Reason (ίMove

 (arrest

 ((AGT THXS Inspector) (OBJ AGT & -Chiro) CTIH «: G965) (LOC #: G973)))

(R U ((AGT AGTXCHA ACTER ' (OBJ AGT &-ro)))

 ($ Relation-Purpose

 (Exposed ((AGT AGT & SAYA)

 (TIM <I: G963) (LOC #: G972)) (Kill ((AGT NIL) (OBJ AGT & Kozushi))

 (TIM i: G963)

 (LOC L0C & Location 1))))))

 (To be detained ((AGT TH¾ police officer)

 (OBJ AGT & -II5)

 (TIM «: G988)

 (LOC i: G989)))))))

In this way, it was shown through this experiment that different narrative structures were automatically created based on differences in the setting of narrative parameters. Enough to increase if individual number of the story parameters and story strategy rule based on it Maze, Vallier one cane down of the story that is created is增加_c

8 Conclusion on system branching

 In the above, the configuration of the actual darning system of the story structure creation automation support system and the experimental examples of story structure creation have been described. In the present invention, a basic method of creating various stories from fragmentary information, a framework that can organically integrate and expand various knowledge expressions in AI and other knowledge for stories, applicability to various systems A technical task was to realize a general-purpose framework with a framework.However, by constructing and experimenting with a system, the story branching method that expands and transforms the story tree and the story strategy that controls its use were separated. With the possibility of expanding or customizing story techniques and story moth abbreviations, and the possibility of creating various structures based on the distinction between story contents and story expressions, we show examples of solutions to section S above, and demonstrate the effectiveness of this methodology. Proven.

 1. System creation and story creation process: The system consists of a story creation management module, a story strategy module, a story technique module, a knowledge base module consisting of a conceptual knowledge base and a story knowledge base. The story creation process is divided into core story creation, story creation, and document creation tasks. Basically, each task is based on the user's input of story parameters and material information. Performed every time. Both tasks are performed through a cycle in which story techniques based on a knowledge base under the control of the story strategy extend or transform the story as a story tree.

 2. Knowledge arrowhead base: The knowledge base consists of a concept knowledge base that stores conceptual knowledge, and a narrative Ift base that is used when using story-type knowledge arrowheads such as scripts. The former is divided into the knowledge bases of event concept, object concept, event concept, decoration concept, person concept, time concept, and space concept, and the latter is script, causality, goal-planning relationship, theme pattern. The attribute of each concept that is a «component of an event in the narrative tree that is divided into each slime base, etc. corresponds to the component in the concept knowledge base. The characteristic values of each item in the conceptual knowledge base are often linked to other concepts.

3. Narrative branch method and narrative The main narrative techniques are as follows: from the seeds of the arguments and the twelve or so of the sakusaku, the associative type, a-containing type, element substitution type, pull substitution type. It can be divided into six types. The narrative creation cycle based on the narrative castle is determined by the points that apply to the narrative branch method. ^ Decision of the word technique, execution of the narrative technique, and the return value of the narrative technique are performed in unified order with the narrative tree as a whole. These make it possible to flexibly and automatically create various story structures. 9 Effects brought by the automated story structure creation support system

 The effects obtained by this automated system for creating story structures are organized as follows, mainly from a technical point of view.

 1. Realizing the diversity of story structure creation

 According to the experiments shown in the examples, seven core stories were created from one piece of material information, three stories were created from one of them, and four professionals were created from one of them. , '/ 卜 was created. But this is only a small part of the possible story. In general, it is possible to create a story with a different number of combinations of story parameters, and in fact. From a single human power used in the actual example. Has been confirmed to be possible.

This W section is shown in the schematic diagram of Fig. 4.

 This diversity in output is due to the fact that many extensions or transformations are possible based on the specific nodes that make up the story tree. For example, the event concept "Kill J has six other relevant event concepts that can be directly linked, and has six more links to the narrative knowledge base. New phenomena and trees can be created in a variety of forms using the types of concepts and rules that are directly related to each other. In this way, a particular object can be expanded or transformed in various ways without using a uniform method, so that the diversity of the story tree as a whole can be realized.

 In addition, the expansion and transformation of the story tree in each task is not necessarily performed from the upper node to the lower node, and it is possible to focus on nodes at any level. It can be realized in a mixed form of '' / For example, if it is possible to extend a certain event as a speed of a lower event, it is also possible to extend the story by using a joint that includes this event as a component. There is such a degree of freedom in applying the narrative technique to the narrative tree, and there is no need to preliminarily limit expansion and deformation.

 In addition, the realization of diversity in the creation of such narrative stories becomes even more remarkable by first increasing the amount of IE descriptions in the conceptual and narrative knowledge bases and improving the quality. For example, the more precise the concept of the relationship between the individual concepts and the link to the narrative knowledge base, the greater the possibility of the narrative. Also, because more interesting stories are created. Domain knowledge of the actual story ゃ Leading literary narrative techniques is possible in the same way.

 2. Flexible automatic control system

Also by experimental results. Story parameters to reflect the partial change even if _P was also confirmed that the change rather than size or create binding粜of, * theme * Yes focus Ya * theme of * of large and small story of Zenkyu structure of exert at the level of sound to create, * characters -. intentionality * because * degree of detail * of large and small Ma ">'in the way of the story of the events developed, such as the use of use and goals act of but-further _e on the sound The narrative technique applied to the upper-level f¾ points of the narrative tree is a structural change of the whole thing, regardless of the type of narrative branch method. If applied to the lower-level nodes, it is local. For example, in <Three creation examples 3 and 4>, the existence of * oma * Thus, it can be seen that the former is a story in which the story structure is built in advance, and the latter is a more fragmentary story. In this way, the difference in story structure creation can be flexibly realized according to the difference in the value setting for the story parameter.

3. Achieve versatility and ease of change

 This experiment Kiyoshi was limited to the story of a fictional novel. For example, to extend the system so that it is possible to specify the creation of another Chanl story. Basically, the overall structure of the relevant Chanl story is specified. We need to add the knowledge of the pattern to the narrative knowledge pace, and add other knowledge if needed: However, the story of the story can be selected. This pattern can be chosen and other common knowledge can be used as it is. For this reason, we refer to the story parameters to add fragmentary knowledge to the narrative knowledge base without newly describing Marco's "sum" to create a story of a specific format of the genre. The story strategy makes it possible to create a different story structure for Shan Shan.

 Is the story structure automation support system an amusement · art? ίί · Automating the process of creating stories in human creative activities and creative work in various fields such as management. Improving the efficiency of their imagination and creative abilities, expanding their possibilities, It is a computer system that plays a role in increasing flexibility in making various decisions. Until now, the level of processing from the word to the sentence is the limit of the S word processing technology in computers, and its practical applications are — those that improve efficiency in basic human tasks such as machine processing and machine translation. Was limited to On the other hand, the automated story structure support system is a system that supports the relationship between sentences and sentences, the relationship between sentence and sentence, that is, the creation of a story, which is the most advanced repertoire in discourse. It is not just about improving work efficiency. The invention realized through creative use, creative use, support, etc. is, as we have seen above, the structural aspects of the story, This system is used as the basic data in the internal wrapper, and can be used in the story expression hierarchy, including natural language, video, sound, etc. This system can be used for the following purposes.

 First, it is possible to use the narrative machine automation support system as advanced human interface in various information processing systems, and secondly, it can be used for various human creative and creative activities. It can be used as a basic technology for a cucumber tool to support :: and. The applications of story creation from these directions include not only various social applications, but also those that are more direct to story creation and expression. For the writer, the first approach can be thought of as a medium for narrative expression, and the second approach can be thought of as a media or a tool for creative writing. This can be thought of as providing a fundamentally new added value or a new production method ife to the multimedia system. The following is a description of its use in these aspects.

 1. High-level human interface

-66- The present invention is a human interface of a conventional computer that has the ability to structure a specific semantic content into a story in multiple expression forms. It responds to a certain user event in a fixed manner He had only the ability. On the other hand, it is possible to realize a more flexible user interface by using tree shouting, which has the ability to automatically create responses for the number of hakama from a certain event. Has a characteristic that it expresses the abstract meaning even more aesthetically than it is. Therefore, from this point of view, more intimate communication between humans and computers can be achieved. One solution for achieving this is .. In educational systems, ^ -min 'simulation systems, etc. This factor is the motivation for the user to use the system. Work efficiency and work efficiency and creativity.

 2. Support for creative and creative activities

 In the meantime, it is not possible to come up with alternative candidates all at once because of the limitations of each person's knowledge and experience. On the other hand, the present invention can easily output a story candidate having a different number of hakama from a specific input by utilizing a flexible combination capability of a computer. Through the active use of the narrative creation function of such a trainer, the present invention can be used to support a variety of creative and creative activities and decision-making activities among humans. In tasks, computers do not necessarily create a single complete answer as a substitute for humans, but tell a variety of possible answers to the same question or the idea of betting from different perspectives and contexts. Through the presentation of 提示 認識 す る, it is recognized that it plays a role in stimulating the ideas and thinking activities between:: is important :. The two «I abilities of the present invention. It is important to utilize both the diversification function of flexibly creating multiple narratives from the input of a document and the convergence function of intentionally and organically integrating fragmentary event groups according to a certain theme. Through the creation described above As possible the virtual support method Te realized.

 For tasks such as decision support based on simulations of political and business activities, for example, by presenting a variety of alternatives and creating possibilities. It is important to provide users with a multifaceted perspective. Become. It is also possible to introduce a narrative creation mechanism more directly in applications to support higher-level creative activities such as creating advertisements and supporting drama and movie production. . The technology to realize such an application does not exist in the current industrial domain, or it will be a very effective solution for the advancement of multimedia in coastal information processing equipment in the future.

 3. Narrative expression and creative tools

A number of shanguls and metias have been pioneered and used to express the story. Here, the genre of the narrative means a soft container for narrative expression such as novels, drama, and comics, whereas the media of the narrative means narratives such as books, video equipment, and CDs. Means a hard container for expression. For example, one story called “The Tale of Genji J” is converted into various story genres including novels, dramas (Noh 'Kabuki-contemporary drama), movies, TV dramas, comics, ), TV. It has been expressed on various media such as video equipment. Present. As a new genre for the story. A winter branch-type store using the convenience store as described above has appeared, and at the same time, the computer will load them. It is now being used as a media for new ^ word expressions. Nire: In the W word table of サ サ ユ ー ユ ー 書 き i i i if i ifi f aro i It is possible to make a winter, but there is a distinctive characteristic of the image 'Old Voice' in the tenth edition, but the divergence and the generality of the story that are currently realized. The flow is designed in advance. There is no flexibility. Also, first of all, it is necessary to incorporate a very IS-like bifurcation diagram. It is a fact that it takes a lot of time to do the work. In such a field, the automatic creation function of r- By incorporating it, it becomes possible to streamline the production process of the Hyper Senki Story, and to automatically control the winter development (or convergence) of the story development. Many advertisements and scenarios are realized as literary works or multimedia systems. This trend is likely to be weakened only if it is strengthened. It is also conceivable to develop it into an entertainment device that includes a narrative (such as the composition of a story tailored to each user, etc.) The present invention can be used as a fundamental technology in these systems that focus on media and entertainment.

■ 7 (·- 【¾

Product ^ Techniques

 Be

Pair (^ elephant concept) argument ¾ of - ⁷ Zo屮of ⁷ Do not to be in the pair - Gaiima the ί ·, ϊ:!.! One: the 1 ΐι .ί

 (U す る J).

³ ^ ¾ person paired Eta I specifically ¾ of屮忡I one another ¾ Citations ¾; · the person 1 ^ free ^ UIF ¹ to 4 forms, joined by opposed I¾] engagement of both.

Control (object) 3 11 S2 width object J f, tlfl · J 1 Φ 1 丄 Ψ ^ cultivate 5111 ϊ¾ J ^ J: & ^ Φ ΐ¾ 1 ϊ | ^W Jί¾3- ί c.- control Join.

Parallel (concept) Now and in the column ($ 今) na in the elephant of the argument を 持 つ Have a general rule- ⁷ ΐί · ίρ

 And combine them by a parallel relationship.

Parallel (弪 ¾person) Generates an event that includes another character with parallel (similar) tropism to the climbing person in the event of the argument, and combines them by a parallel relationship.

Parallel (object) Creates an object that includes another object with parallel (neck-like) tropism with the object under argument, and joins them by a parallel relationship.

Description Search for extensibility in the knowledge base for the specified element in the event of the argument, and

Searches for tropism in the knowledge base for the specified element in the event of the argument and

 Generate a description speed of the target attribute and combine them by a description mechanism.

Reason (Cause) Another event concept that constitutes the reason (cause) for the event concept in the event of the argument is retrieved from the knowledge space, and the Φ elephant including the concept is placed before the argument argument. Is determined by the cause and effect.

Result Retrieve another event concept from the knowledge base that produces a result for the event concept in the event of the argument, place the event including the subject concept after the event of the argument, and combine the two by the factor ra.

The specified -prime in the event of the argument is more concretely specified by lowering the link! In the knowledge base. Hide events. [Table 2]

■ 7 ： [Table: Re

-7: (- 【table "

Type Name Description, object ϋίί 氺 Type * Indicates the type of object. For example, novels, Hiro, etc.

 * Theme * Designate the theme that controls the entire object. It is linked to the theme pattern.

 Genre * Specify a pattern specific to the genre of the story.

 * β length * Specify the length of the object.

 * Redundancy * Specifies whether the story exhibition 1¾ is redundant or tight.

 * Physical properties * Specify the degree of narrative strength. It is Mil with Mizagawa, who is mainly in charge of the story.

 * Concreteness * (* Abstract Designate whether the composition or expression is concrete or abstract.

 Gender *)

 * In a storyline, for example, is it possible for a dead person to easily come back to life? Reality * Specify the degree of reality or unrealism of the story in this sense.

* Drama * Shows the degree of dramatic excitement and structure. If this is strong, for example, insertion techniques such as “injection”, fcgaj, and “power” are frequently used.

 * Exorcism * Specifies the degree of exclusivity of the story exhibition 153. If this is exotic, techniques such as “nesting stories” are used.

 * Theme-specificity If a theme exists, specify the degree of dominance it has over the story. If the dominance is strong, the theme pattern appears on the upper floor of the story tree.

 * Responsivity * Specify whether there are many repetitions of people, people, etc. mainly

 It is related to the reaction.

* Specify the granularity of * Details *. Mainly scripts and IMji. [Table, ^Γ )]

-7- [Expression ']

-7Γ,- [Table 7]

[Table 8]

-7H- [Table ί

Overview of the robot

 ΙΐΐΒ.

 25-1-1 The child is a river);

 25-1-2

 25-1-3 One year n; i, -Rri j of river died in self accident

 25-1-4 The heir has disappeared.

 28-1 (Sugino tailored Niseko Nobuko to seize Hayakawa's property: Oh,)

I searched for `` clues ''.

 25-1- ι Sugino made some `` clues j powers '' and fake chicks into real ϊ.

 1 Last fall, Sawaki and Kozaki met in Sano.

 2 After a week, the two met 药 in the room where Kojima was.

 3 On the next holiday 11, Kogiku visited the atelier i Shakugi.

 4-5 After that, Sawaki visited the teahouse of Kogiku about twice, and their relationship began.

 25-1 ί 1) This year's positive fi, rich -kawa came to Zashi with his daughter Nobuko and secretary cedar.

 25-1 f2) At that table, the child who had gone missing was told.

 25-1 (3) At that time, ¾ 'thought that the appearance of cedar? Ί and Ry 了 was strange.

 25-1 (4) There is a maiko who has a ίιί

25-1 (5) to be consistent with ^Γ clue "that small bell also search for Nobuko became ¾ss. (At that time small ½ wore a kimono of the same color and pattern and killed a geisha.)

 35-5-1 Sugino did not know the face of the true daughter maiko of Hayakawa,

 35-5-2 I didn't know if my name was Kosuzu or Kosuzu.

 36-2 (1) Sugino is a small bell whose face is unknown.

 36-2 (2) I put a piece of my name SW on the mark in the ¾ of the band because it was too short.

25-3 (1) On the night of Setsubun, the landlady of Kogiku's shop publishes at Hayakawa's house (in Tokyo).

 35-4 (1) Button ¾ Due to the talk of the story,

 25-3 (2) At that time, Sugino appeared at; ε¾.

 J 5-4 {2} Sugino appears on the landlady «¾.

c (i) On the night of S5, Sawaki was playing at Club Hanagi ISI with 犮 jin ii.

 G (2) At that time, there was a request from Kozushi, who was there, to go to Ishigami in Club Kyo to get rice.

14-5 The story to small »was a male voice.

 14-2 (Actually) Ishigami had not visited Kyoto.

 14-3 (Actually) no one was calling calm.

 (14-6 small) ΐ¾ to II was ¾s for fake invitation.

 C (3) Kozushi went out.

 6 (4) Sawaki also left the store immediately.

 35-2 Sugino wants the false identity of Nobuko Niseko to be exposed.

 35-3 One after another, they killed Maiko and went (S killed small »).

 3C-1 (1) Sugino is at Hanamikoji.

 36-1 (2) We examined the trace of the burn on the clue p.

36-2 (3) (Sugino wears a face and cannot see his face. (36 · 2 (1)) '-on 38, tl mark. (30 "2 (2)) When I did that, I cut off and meshed. [Table [o]

1ϋ- 1 Small ίί was strangled by a rope.

 7 (1) Immediately after that, the shakugi was in Hana-no-moji, where he was cold

7 (2) A small ^ corpse was ¾ 兑.

 8 (1) The traffic shouts,

8 (2) Someone is scrutinizing,

«« ... Arrow ^ Apple I J Other Tf ^ Τί did.

 1ϋ (1) Kariya saw that the killed maiko was wearing a kimono and his sleeves were torn.

1U (2) coroner inferred,

 10-1 Kozuki was strangled by Loeb.

 10 (3) »SU deduced,

 Ιϋ-2 Kozushi is a tangle of love,

 1 ()-3 Killed by grudge.

 11 The corpse was taken to the responsible office.

 12 (1) Is Takaya in Sawaki?

12 (2) Sawaki replied, ¾i,

12-1 What happened at Hanagien (6 (1)-C (4)).

12 (3) Sawaki was taken to the station by Inspector If.

13 Kariya and Piro go to the club flower ittSl,

 14 (1) Taken to the manager.

 14 (2) The manager was loyal and spoke.

 14-1 Hanagi Kozushi at ISI (6 (2) 6 (3)).

 14 (3) Kariya talked to Club Kyo and lost his photo.

 14 (4) Kyo's mom said.

 14-2 Ishigami has not visited,

 14-3 No one is calling Kozushi.

 14 (5) Kariya again took control of the flower manager.

 14 (6) The manager recalled, did,

 -5S £ to 14-5 Small »was a male voice (6 (2)).

 14 (7) Kariya and the school entrance were determined,

 14-ϋ ϋ to Small »was an invitation for fake.

 14 (8) «5 mouths inferred,

 14-7 total Bfl

 14-8 Murder by grudge.

 14 (9) IS mouth inferred,

 14-9 Sawaki are both ill,

 14-10 Both ill people put on two sets.

 15 Are you in charge? I returned to Ϊ.

 16 The police then went to the suspect.

 17 At the same time, the police investigated the evil S.

 18 At the same time, IT Insight included W1.

 35-2 Sugisaki wants the false identity of Nobuko Niseko to be revealed.

 35- 3 Maiko was smashed one after another (this time Ochitsu was killed).

22-1 ill input is small »

22-2 Do you know that it is available?

22-3 Next, 千 Osen.

 36- 1 (1) Cut off the sleeve of Sugi

■ 8 (1- 【Table I 1 C- 1 (2) -T- was examined for traces of burns on J¾, which is one of the ^ 3.

C-2 (3) (The cedar ϊί 'is a small i & (3G-2 (1)) who has a face and cannot see his face; (36- 2 (2)) I cut it off and checked it.

9 (1) The night after 30 minutes, Sawaki was playing with Kogiku in his teahouse.

9 (2) At that time, a police car stopped in front of tea 茶.

0 When I stepped out of the window, the person who had put on a kimono on the street had fallen.

1 (1) Small ¾ and Sawaki go outside ίΐ ',

1 (2) The two men have seen a maiko-style corpse, whose back has been stabbed with a knife, falling.

2 (1) The following morning, Kogiku visited Sawaki's atelier.

2 (2) Kogiku argued that the evening death was a tourist maiko called Osen ^.

2 (3) Kogiku reasoned.

2-1 Although i-iri killed Xiao.

2-2 You know that you are wrong,

2-3 Next I killed Osen.

2 (4) Sawaki inferred,

2-4 The criminal was killed by someone.

2 (5) Kogiku followed another dance element that waited for something in common with the killed Niiri.

2 (6) Sawaki inferred,

2--5 ίΐι 人 people were killed because they were scooped with a knife.

3 The same police were narrowing down the investigation into the case.

3 (1) Police inferred,

3- 1 The same perpetrator kills a woman in n¾.

4 Hashiguchi suspected that Sawaki was suspicious.

5 (1) Kogiku visited B, Sawaki's atelier, where Ochao was off.

5 (2) Kogiku said,

5-1 (1) This year's New Year. Hayakawa, who waits for money, came to ft with her daughter Nobuko and her honorary Sugino.

5-1 (2) At that table, a missing Nobuko ** found β * «was found. According to that, 5-1-1 Nobuko was born by Hayakawa to a geisha in Kyoto With a child.

5-1-2 I left it for a long time,

5-1-3 —The year thorn, Hayakawa's chief, died in a car accident.

5-1-4 Trace «Because it was gone,

5-1-5 ^One of the ¹ "was released based on the clue j.

5-1 (3) At that time, Kozuki thought that Sugino and Nobuko seemed strange.

5-1 (4) Koiko, a geisha wearing a mask, came into the club,

5-1 (5) Kosuzu also looks for Nobuko, and it is 「κ to match the“ clue ”.

5 (3) Kogiku and Sawaki reasoned.

5-2 Next, small f is targeted.

5-3 (1) Night of 235 minutes. The landlady of Kogiku's i visited Hayakawa 束 in (Bunkyo).

5-3 (2) At that time, Sugi ff came to ΪΚ.

5 (Kozaki and Sawaki reasoned.

5-3 (3) The alibi has some tricks.

C Two days have passed.

7 In the evening, from Kogiku, Hayakawa came to G K1 tonight.

• «I- [Table 12]

28 That night, Kojima, Kojima, and Sawaki were on the fi fi of Gi 1--1.

 28 (1) The child guessed,

28-1 Fake ίΓ,-Τ · か か '), + ίϊίίϊί was 17!

 2 Li (1) At 9 o'clock, woman: From t'i to Kosuzu

 29 (2) I was ordered to go to the river ¾ 敉.

30 A small child came out and came out.

 35-1-1 Kogiku was Kozuru's name.

 31 <The tree asks the 扦 arrow for a response,

 Ill after 32 small 小.

 : "(1)

33 (2) Because I put a small »»

 3 (: "Sawaki jumps to},

: "(4) Yes.

 34 (I) — hour After about IK1. When Sawaki picks up,

34 (2) From Shiya

34- '. Report of the arrest of ϋΐΐ

 34- 2

 34 (3) and lost S: ¾.

 35 (1) The following day, Sawaki took consciousness at the bed of the disease K and took K.

35 (2) Kariya was standing sideways.

35 (3) Kariya said,

 35-1 After the arrest, Sugino became sullen,

35-1-1 Kogiku's ridiculing of Kosuzu.

35 (4) Kariya inferred,

35-2 Sugino tried to tell the true identity of Nobuko Nise,

35-3 One after another killed the bookkeeper.

35 (5) Kariya said,

35-4 (1) On the night of the IJ5— incident, a button ¾

35-4 (2) The landlady's ¾: Puni cedar?

 35 (6) Kariya is S,

35-5 After his arrest, Sugino said,

35-5-1 Hayakawa's true daughter maiko's face was not clear,

 35- 5-2 Naito did not know whether it was Kosuzu or Kosuzu.

36 (1) Kogiku and Kosuzu enter the room.

3C (2) Kariya inferred,

3C-1 (1) Sugino «cuts off the sleeves of things,

 36- 1 (2) I examined the trace of W's fire, one of the clues.

 36 (3) Small »showed off a business card cut from Kuzuta cedar ff from Kosuzu.

 30 (4) Kozaki reasoned.

36-2 (1) Sugino is wearing a jfii and cannot understand the face.

3G-2 (2) Behind the mark. To the 0 mark. It was so quick that I lost fJ's worth of stimulus. W.

36 (5) Small 約 and small.

--

Claims

 The scope of the claims

1. Inputting fragmentary events or subtrees and story parameters, and using the story creation management module's story structure creation cycle to create descriptions that describe concepts or relationships between concepts stored in the knowledge base. Utilize the rules of the story strategy (story strategy module) to automatically operate the procedures of the story technique (story technique module), convert the input information into a story structure, and output the story structure. Automation support system.

 2. In claim 入 力, the input information, the event in the middle of the process or the part of the story tree, or the entire story tree is processed. The event or the story tree in which the processing object is expanded or deformed is processed. By repeating the cycle of creating a new story tree in combination with this, a story structure creation and automated torture system equipped with a story generation management mechanism to execute the creation of the story structure.

 3. The narrative according to claim 1, comprising a narrative technique module that is applied to the events or subtrees during the generation of the force coasting information or the entire narrative tree and is composed of a group of narrative techniques that extend or transform them. «I structure creation automation support system.

 4. Refers to the input story parameters in claim 1. Consists of a story strategy group that infers and determines the story technique application point in the story tree to be processed and the story technique to be applied to it. A story structure creation automation support system equipped with a story strategy module.

5. In claim 4, referencing the narrative parameters that have been manually input, in each cycle of creating the story structure. Infer and determine the application point of the story branch method in the story narrative to be processed. From the story strategy group A story structure creation automation support system with a structured story strategy module.

6. In claim 4, referencing the input story parameters, in each cycle of the story structure creation, the story technique to be applied to the applicable story branch method application point is determined. An automated narrative structure creation system with a narrative strategy module composed of word strategies.

7. An article with a knowledge base that stores the information used for the concepts used in the narrative technique and the definitions used to conclude the concepts in §S claim 1 in terms of the expansion of the story structure and the transformation process in the narrative technique Structure creation automation support system.

 8. Includes a network-based conceptual knowledge base that refers to events, things, things, things, decorations, characters, space, and time that are used and referred to in the execution of the narrative technique in Training Item 7. , Story structure automation support system.

 9. The automated narrative structure creation support system according to claim 7, further comprising a narrative knowledge base for storing 'specifications of a connection relationship between concepts used in executing the narrative branch method.

 10. In claim 1, based on the fragmentary elephants or subtrees and the narrative Halla metric which are the initial human powers, this is called the core story, the story, and the pro ". An automated narrative structure creation search system with a function to automatically unfold the narrative structure.

 1 1. In the ifl song term 10, the fragmentary event or subtree, which is the initial input, is based on the story 、, ラ メ メ ft .. Equipped with a function that automatically expands to story structuring. Automated support system for story structure creation.

1 2. In §10, the core story is used as input, and based on the value of the story parameter, this is automatically converted into a story structure of a story, which is an event sequence according to time order. With the function to deploy. Automated payment system for ISfll construction.

13. In claim 10, based on the value of the story parameter, the story is automatically expanded into the story structure of the plot, which is an event sequence according to the I-spout in the text, based on the story. A story structure creation automation support system with the following functions:

 14 4. In claim 3, applied to a single event or a subtree of the story structure, referring to the concept knowledge base and searching for various properties for specific elements therein. An automated narrative machine creation support system equipped with a "description" narrative technique that creates a rapid chain of events consisting of depictions of features and the like.

 1 5. In claim 3, applied to the events of Junichi or the subtree of the story structure. Concept Searching the knowledge base for various elements for specific elements in it, Generates a chain of events that express general sexuality, such as や and 住, and creates a narrative structure that combines them.

 16. In claim 3, applied to a single event or a subtree of a narrative structure, a concept knowledge base is searched for an event concept that further embodies a specific event concept. An automated narrative structure creation support system equipped with a “concrete” narrative technique that replaces it with the above event concept.

 17. In claim 3, applied to a single event or a subtree of a story structure, referring to the concept knowledge base to search for an event concept that further abstracts a specific event concept therein, An automated system for creating story structures, equipped with "abstraction" narrative techniques that replace them with the above event concepts.

 1 8. In claim 3, a single event or a subtree of a story structure is used as a complaint, and a concept knowledge base is searched for an event concept corresponding to an instance of a specific event concept therein. Then, an automated narrative structure creation support system equipped with a “case-in-place” narrative technique that replaces this instance with the above-mentioned event concept.

 1 9. Applied to a single event or a subtree in a narrative structure in training item 3. Concept Searches the event knowledge that corresponds to the frame of a specific event concept in the knowledge base. An automatic narrative structure creation support system with “framed” narrative branch method that replaces this frame with the above event concept.

 20. In claim 3, an automated narrative structure creation support system that is applied to the subtrees of the narrative structure and creates a new narrative structure that summarizes the narrative structure.

21. In the blue blue claim 3, the mental state of the characters in this event caused by the occurrence of this event is created by referring to the narrative knowledge base, Yes "Mental state creation" Equipped with narrative technique. Automated support system for narrative structure creation.

 2 2.Applied to Junichi's event in i-Kikui 3 and generates a new event driven by the mental state of a specific character in this event with reference to the narrative knowledge base. Yes “Event creation based on emotional state j Automatic narrative structure creation support system equipped with narrative techniques.

2 3. In i-cultivation claim 3, a plan sequence in which a single event or subtree is used as a complaint, and with reference to the narrative knowledge arrowhead base, the input event or subtree as the goal and result (effect) The goal building and planning are combined by the M section. "Eye-building-planning (development) J An automated narrative structure creation system with storytelling techniques.

2 4. This applies to the first event or the end of the part in Supplement 3. Narrative Knowledge ¾ Base With reference to, create a goal-plan event sequence that includes human-powered phenomena or sub-ends in the plan sequence. Equipped with an automated torture system to create a narrative structure,

 25. In claim 3, apply to a single event or subtree, create a sequence of events to satisfy the input event or partial thick as desired, by referring to the narrative knowledge base, These systems are linked by a desire-satisfaction relationship. An automated support system for narrative structure creation, equipped with the "Hagibo-satisfaction (development)" narrative branch method.

 26. In claim 3, a single elephant or a subtree of a narrative structure is used as a subtree, and referring to the narrative knowledge base, an input event or a subtree in an event sequence for satisfying a desire. A system for automating the creation of narrative structures with the "II hope-satisfaction (including)" narrative technique that creates a sequence of hope-satisfaction events that are included in and includes these in a desire-satisfaction relationship.

 27. In Claim 3, which is applied to a single event or partial thickness, creates a sequence of events of a subject structure including a human-powered event or a partial tree with reference to the narrative knowledge base, An automated narrative structure creation support system with "subject (containment") narrative techniques: 28. In claim 3, applied to a single event or subtree, A specific event or part end is inserted as a recollection content at the position, and this is connected to the previous event by the person in charge of reminiscence. "Automation support system for story structure creation with reminiscence J story technology.

 2 9. In claim 3, it applies to a single event or a sub-item, and inserts a specific event or a subtree as a reasoning content at a specific position in it. "Reasoning", which is linked by reasoning relations An automated narrative structure creation support system with narrative techniques.

 30. In Claim 3, the method is applied to an event of a cliff or a partial tree, and refers to a concept knowledge heave and responds to the event or the partial thickness. An automated support system for creating story structures, equipped with "reaction" story techniques.

3 1. In claim 3, applied to a single event or portion thick, and參照concept knowledge base. Bonded good events or subtree occur as succession W engaged in succession relationship to their ^Γ succession An automated narrative structure creation support system equipped with narrative techniques.

3 2. In the cultivation request 3, apply to the subtree of the story structure and create a subtree that is reorganized (deformed) based on the viewpoint of a specific character. A story structure creation automation support system equipped with story techniques.

 3 3. In training 3, this applies to a single nested or narrative subtree, referring to the conceptual knowledge arrowhead base and to the frame of a particular character in it. Creating an instance “Creating characters” A system for automatically supporting the creation of narrative structures equipped with narrative techniques.

3 4. In claim 3, which applies to the first event or the end of the story structure, and changes the name of the particular character and the other three characters who have changed their character A story-creating automated system for narrative “I-story creation: 3 5. Ikuichi's event or story« I-story It applies to the end of the part of ffll. $ Illuminates the base of the intellectual team and creates an instance corresponding to the frame of a specific space in it. The story machine is created.

3 6. In 誧 ι. 3. ^ — Event or thing ^ «I-built part ^: is passed through. W "Lame to JS room: Ma. People: fHL Creation of things ”A story support method that automates the creation of story structures.

 37. The narrative structure according to claim 3, wherein the narrative structure is applied to a single event or the end of the narrative structure and generates a sequence of events by repeating the specified number of times. Creation automation support system

 38. In Claim 3, applied to a single event or a subtree of a story structure, which is regarded as a figure, and the ground structure that forms the framework is connected before or after the ground-map relationship. "Ground-Figure" A story structure creation automation support system equipped with a story technique.

 3 9. In claim 3, it applies to a single event or a subtree of a story structure, regards it as a necessary case, and precedes the structure of the setting that guides it-case 閱. "Settings-Incidents" that are linked by a staff A story structure creation automation support system equipped with a story technique.

 4 0. In Education 3, the story is used for subtrees of the narrative structure, and a "movement" narrative technique is used to transform the narrative «structure by moving a specific event or subtree in it. Also, a story structure automation system.

 4 1. In claim 3, applied to the subtree of the story structure, in order to compare the story knowledge base with the realization of the later event in the middle of the two events in the input. An event or subtree is intentionally inserted, and they are connected by a case-related relationship.

 42. An automated narrative structure creation support system according to claim 8, comprising an event concept knowledge base describing a verb (event) concept, its nature, and other related concepts.

 43. The automated narrative structure creation support system according to claim 8, further comprising a physical concept knowledge base that describes physically existing physical objects, that is, physical objects, their attributes, and other related concepts.

4 4. The system for automating story structure creation according to claim 8, comprising a concept knowledge base that describes the concept of an abstract thing (thing) that does not physically exist, its attributes, and other related concepts. Tem.

 45. The automatic narrative structure creation support system according to claim 8, further comprising a conditional concept arrowhead base describing an adjective concept for modifying another concept, its attributes, and other related concepts. 46. The system for automatically supporting creation of an object-like structure according to claim 8, further comprising a person concept knowledge arrowhead base describing an instance of a character, its character, and other related concepts.

47. An automated narrative structure creation support system according to claim 8, comprising a time concept knowledge base describing time instances, their characteristics, and other concepts related to M.

 48. An automated narrative structure creation support system that includes a space concept knowledge base that describes the instances of space, its attributes, and other related concepts in Blue Claim 8.

 4 9. In the item 9, a plan for achieving a specific vehicle image and achieving it W | and a building containing rules for inferring the final result-equipped with a planning knowledge base, A story structure creation automation support system.

 50. In W claim 9, an automated narrative structure creation support system equipped with a theme pattern knowledge base that stores the definition of theme patterns that represent the subject M in the story.

5 1. 求 求 求 、 、 、 に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て に お い て 、 、 、 自動 に お い て 自動 に お い て に お い て_c Claims for amendment harm

[1 September 9, 996 Accepted by the International Bureau: Claims 23, 27, 49 and 50 originally filed were withdrawn: Claims 1, 2, and 2 originally filed 4, 5, 6, 10, 10, 11, 12, and

13 amended; new claims 52-55 added; other claims unchanged. (Page 5)]

 1. (After correction) Wi One-sided event or partial tree ¾ ',' Using the group of humans as a human power, the story creation management module's object SS structure creation service 、 ss base The concept stored in the は is «記述 念 念 念 記述 記述 記述 記述 記述 技法 技法 技法 技法 技法 技法 技法 技法Fragmentally defined objects in the module: s Techniques are automatically selected and executed, so that the input information is gradually and responsive to the difference. u is converted to ts format and output is set to u.

 2. Just after) ^ In request 1, the human power information, the ¾ or subtree in the process of construction, or the entire object is treated as an inch *, and it is expanded or deformed. With the story tree and the foldable thing, it is a foldable thing to create a S-tree. It is possible to create a ftr¾t «structure by making a tree. ? 15.Structure ^ structure S structure support system

3. In the request 1, the information of human power and the elephant in the process of growing is not suitable; the branch tree or the scoop is suitable for the ffl ^{1 and the} sway is not extended ¹ ^ ^ ^;か «Successful scoop ^ Technical module with f 'た Π Π * ¾ it Jii ίδ stem

 4. (After Sodemashou),; S request 1, processing 1 \

Fti in the story tree that is ί ί: 点 m point & ひ 滷 滷 滷 推 推 推 推 推 推 推 推 推 ti 推 推 ti ti ti---ti ti ti ti ti ti ti 1 ^ ffiSi-A system with a ladder made up of a group and its control mechanism

5. (After the supplementary IF.) In claim 4, in each cycle of the construction of the scoop, referring to the group of human-assisted ί¾όίίharrah ゥ, the scoop in the tree is j¾ffiili'J¾. ? technique infer the proper - is interest ffl to constant, cross-sectional specific is the stand of 'Les over' ϋ¾ ^ ¹ i¾ ^ 'Les over' Les ^ and its; was liij your machine «the« & e, ^ ¾ «5 ^ Growth support system ^

 6. In the request 4, illuminate the ^ S harness that was created, and in the rt¾W5 construction it's ^ Sai ^, use the appropriate ffl Guess ^-

Fl f fl 片 fl fl fl fl fl fl fl fl fl i i; BfP '—' L ST and its ift an machine ii? «s, i ^ 'ffi structure 造: power iiiJi s system.

7. In request ¾U, expansion of scoop 5 ^ by :: 5 · 0: W is done in the form of a pass,; /; 怙 怙 怙 怙 怙 怙 ¾. SStructure while maintaining the ォ structure.

8. In the request: π 'ίίΛ ^'' ^L ' i · W W W, † f¾, r ?, J ί'ί decoration, person ft, empty question, time rJ] PU ^Π -c ^ eff of the formula ffi [the scaffolding has been teffed, the activation of the scoop A has been done.-9. In claim 7, on the 杓 of the scoop-· lffl 溉 台 台The person in charge of storing the fi definition, 5 知 25 一 I へ 、 ¾ 、 、, ^ ¾ «5; ≥ ^ 1"]

10. (Correction ¾> ί, In the request 1, iyi people 'I-like thing-5ι or -Z ·} 物 ¾ ¾ 、''''群''z z z z 1 ', ^ Skillmonu'-, ί * 7 ^ Abbreviated module L & H '¾ja ft] and ^ ^ _S g ffi 3 for each of the following words: つ, α, fi, fi, ½, ½, ½ 'A ί¾

-87-Supplemented ii _:; :: / 'i Article 19 Manufacturing automation support system

 1 1. (after correction) ^ In the query 10, the fragmentary elephant or subtree that is the initial input is used. The story creation management module, the story technique based on the values of the Igo parameters Module, narrative strategy module) Using the knowledge base, the structure of the core story, which is the first development of the narrative, is automatically (provided with a function to create a structure). , A story structure creation automation support system.

 1 2. (After amendment) In claim 10, the core story is used as input, and the narrative parameters are set based on the fiS of each narrative parameter. With the function to automatically create the physical structure of the story, which is a series of phenomena according to the time sequence, using the story, story strategy module and knowledge space. Word structure creation automation support system.

 1 3. (After Correction) ^ In query 10, input the story and input the story word module based on the value of the ^ word parameter. Using a story war ^ module and knowledge base, a function to create a story structure of a broth, which is an event sequence that follows the II order, in a text expression An automated system for creating story structures c

1. ^ In claim 3, applied to the sub-tree of the medium or story-structure, and with reference to the concept knowledge base, add ₀ attribute to the particular: prime of the sub. ^ 'Osh, ¾ · Look? ? Of generating a drawing copy or made书象of the chain, these binding ^ was the story撗造( 'capital: Ri issue with I depiction "product ¾ technique, story structure created S whether support sheet Suchimu _t -

1 5. In ^ claim 3, applied to a single question 1 or ^ '^ of a story M5, referencing the concept knowledge base to determine the gender of a particular element in it. Retrieve and generate the fast chain of phenomena that express the general character, including the age and tt of the person, etc. Structure with ^ System _r

 1 6. In query 3, in the sub-tree of medium-one elephant or object ffi-fi, it is ffled, and with reference to the concept ¾1 knowledge base, * Mutualization of the concept *) 8 [Search for a reminder and convert it to 1: Article * Convert K to the concept Γ Pv embodied I Create scoop structure with narrative technique β®) Support system

 1 7. In the case of ^ 3, find the middle of the 书 * or object ^ structure; the ffl is applied to the branch tree, and the β concept ¾ I abstract the concept extracted from *; and convert it to the ad ^ elephant concept. I Abstraction ” :

 1 8. In request 3, in yi—'s ** or narrative structure ') "Make a measurement to the tree; iSffl, refer to the memorial knowledge base, ^ を 概念 概念 概念 杓 杓 す る 'す る' す る 杓 杓 杓 杓 杓 杓 杓¾: Naru? 1 Automated: Throw Stim

1 9. In claim 3, apply to the subtree of the elephant or object ^ ffi S in the middle of claim 3. Applying the concept ¾1¾ to the base tree, and ¾ the sense that corresponds to the laser beam, the frame is provided with a heat ¾ thing * to concepts and ^ conversion "頹化1 story technique, ¾« s; rp½ ΰ © of support sheet Suchimu _r

 2 0. In claim 3, the flap was properly ffled to the tree of the ladle and required it. Ϋίδ system-

2 1.In the case of ^ Eq.3, j jffl and ^ base for ^ の---

-88-Revised ffl paper (Treaty No. 19 Creating the mental state of the ladle in this phenomena brought about by the occurrence of the event I Creating the mental state "

 22. ^ In claim 3, applied to an event, referring to the knowledge base, a new state driven by the mental state of a particular character in this study Automatically create story structures with mental language I-language techniques

23. (Deleted)

 24. In request 3, it is applied as a tree or a tree of Φ-, and referring to the knowledge base, the elephant or the tree of human power is put in the picture line. A system for creating an image of a drawing and combining the stiffnesses with a target drawing relationship.

 25., In application 3, applied to a single * or ^ ^ tree, referring to the knowledge base and inputting it or asking for a Satisfaction * Create columns and tie these to the s s—satisfaction clerk. “Wish ^ one satisfaction (open)! Scaffolding with narrative techniques.

26. In claim 3, in--¾ は は_{6 6 6}適 適 適 適

¾ 遴 Base-See the human power · 1ί ¾ or 21: ^ Wish a tree! Wish in the elephant row for tl 願 願 ¾ ¾ 願 願 ί ί ί 願 ί ^ ί ί ί ^ ^ ^ ί ί ί ^ Made rp.

 27. (Reduced Pit)

 28. In claim 3, ^ f is applied to the tree or tree, and it is applied to the tree at a particular position S in the tree. I こ こ)) ϋ ϋ ϋ Ι Ι Ι Ι Ι ΛΓΐ Ι ΛΓΐ Ι ΛΓΐ Ι Ι)))))))))))

 29. In the request —3, the fol- lowing * or; ffl is applied as a branch tree, in which: (The specified ti ^ contains the vertice ffi as the fixed ffi content or the 'tree is ίΦ This is done by ift 1!; 1 and the reasoning clerk. "Throw! Technique <;

 30. In claim 3, Ψ--') or ¾ tree is suitable for ίι 、, based on conceptual knowledge, and generated as an i-relationship SW SW を SW ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾

 31. In claim 3, applied to the first thing or ί'ίΠ>, and applied to the concept base, and the * Raise the sap tree with the succession ra staff. “The story creation structure EJ3¾iDanij 支 system with the succession I technique

 32. »In ^ 项 3, it is suitable for a rapper;

部分, 再 ¾ 再 部分 再 部分 再 部分 部分 部分 再 再 再 部分 再 部分 部分 部分 部分 部分 部分 を

33.,; 5 In claim 3,-or ft 5 ¾i≤; '3:' to WL; fiffl, based on the concept ¾1 ¾ In the game of the ladle! ^^ ί ί ろ す ろ is is is is is is is is is is is

 34. In ^^ item 3, Ψ.— or ^^ W¾ Π !: Suitable as a branch tree, specially for human-powered babies! FT: The 人 ί ® 性 人 人 人 ί ί ί 性Create a lens; “^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ to to this leads

-89-Articles caught ^ * 19)

35. In claim 3, applied to a single event or a subtree of a physical structure, referring to the conceptual knowledge base, to a frame in a specific space within it Create an instance

Creation of empty questions ”An automated support system for creating story structures with story techniques.

 36.5 In claim 3, applied to the M-event or the subtree of the story structure, and based on the concept ¾1 knowledge base, ¾g the frame of a specific object in it. Create an instance

"Making a story structure with a story-growing narrative technique"

 37. In claim 3, it is a quasi-first thing * or applied to the tree of the story structure, and it repeats it a specified number of times to generate a sequence of objects. In addition, the structure of the structure

 38. ^ In claim 3, applied to a subtree of one or more objects or objects, and converting it to 0, the structure of the earth that forms the framework is described before or after. Later, it will be linked with the Chiichi RI relationship.

 39.In claim 3, -one thing or thing is applied as a ^ tree of structure, and it is treated as an upper case to make that person ,; I ^ SiSi 'structure D i¾ iL i & system equipped with the technique を ^

40. In request 3, 杓 .ί is applied to the sub-tree of the IS, and a particular 中 or 中 therein is moved by moving the π-tree. painting ffi the r ^ dynamic I ladle technique to变形things concrete, story ½ concrete create ϋ whether支投shea scan Senmu _c

 41. In Request 3, the story tree is ffled to the tree of the story structure, and the object: 15 knowledge S¾ page, in the middle of human power: I lost a ^ or a subtree to make the ¾ ¾. き 揷 揷 揷 揷 揷 揷 カ カ カ カ カ カ カ カ カ カ カ カ カ カ カ カ; Pull system,-

42. ^ In 求 8,: BJ ^ (^ ⁽ ) The concept that describes the concept and other concepts related to 係 fk and ra ¾Concept ai is is based, ί¾, 5 Throw system.,

 43. ・ In claim 8, we have learned the concept of the concept of a ladle concept, which is based on the concept of a mono-class that exists as a ladle IS, that is, the concept of the ladle S and its related aspects. Structure ί '成 A * H

44. ^ In claim 8, we described the W-notation of the oily mono (pattern) and its Λ characteristics and other related ia-notations to the object ffil'J. ^ ^ ^ 千 千 千 千 千 千 稱 千

 45. In claim 8, a modified concept base describing other concepts related to the concept and the related concept for decorating other concepts with t¾ and f ^ was created. Shi Stim.

46. · In Request 8, in ft fi:> ≤ ('卜 di 人物 人物 人物 人物 人物 人物 人物 人物 人物 人物 Α Α : Naridan i £ i8

47. In request 8, when rii! Hl is performed on other instances of the fstance related to the instance of time and its characteristics, IH] «念 ΪΠ ΪΠ ベ ー^{3 3} 35 Υ (t El ¾ Ka支½ sheet Suchimu _r

48. In the request Jfl8, I を 1; ≥: ¾13¾ based on I1 and ≥13 while IHj's タ status and other concepts related to it ¾.化 化 ¾¾ シ シ ム_r

 49.

 51. In the fi 9 of the water, ^ 定 定 定 定 定 定 定 定

-90-Amended ffl¾ (Article 19 of the Convention) —Automation support system with narrative structure, equipped with a mental reaction knowledge base for storing files.

5 2. (Addition) In claim 4, "Chima", "Theme", "Length", "Logic". (Specificity), "Character-Intentionality", "Character-Psychology" The type of narrative technique used depending on the difference in human power to the narrative parameters such as “point of view”, “repetitiveness”, and “detailedness”. By changing the timing and appropriate ffl timing, etc., it is easy to diversify the story composition. ■ A collection of fragmentary rule definitions that can be flexibly realized. Object structure creation automation support system composed of a certain object strategy rule group and its control mechanism 5 3. (Addition) ^ In claim 4, based on the input object _π parameter group, All the corresponding general rules are selected, and one rule is selected from among them according to the priority set as a parameter. The utilized to control the use of the narrative strategy rule group in the process of S-option, with a controller in the object ¾ against Bft, narrative structure create automated support system.

54. (Addition) In claim 5, the ffl points suitable for the narrative technique are determined by formally moving the nodes in the narrative tree in a certain order based on the narrative parameter group that has been manually input. How to set the focus to be expanded intensively in the tree, how to create the parameters by referring to the parameter values and the state of the current story? By the method and the like to determine the ffi optimal ladle technique suitable ffl point for each V during .Ί go-between, with a story ^{1 i¾} BS rules group for determining the ladle language technique point of application, story ffi concrete create automation Support system.

 5 5. (Addition) Claim 6: The current creation tasks, parameters, types of trees to which narrative techniques can be applied, locations of trees to which narrative techniques can be applied, etc. The narrative technique applicable to the narrative technique application point that has the ffl of the ffl F fl fl fl fl fl fl fl fl fl fl fl

 -91

Amended.About ¾19) Damage to account under Article 19 of the Convention

^ The first section of the SS encloses the overall structure and main processing functions of the present invention, which consists of a fuzzy management module, a knowledge base, a scouting technique module, and ft; The _c citation ί shown is a document that describes a system that realizes one of the abilities of story creation, or its ability to create is based on the goal A fixed algorithm based on a small, uniform method, such as a simulation? In spite of the fact that this depends on the m, the description is fragmented; the knowledge base, the material technique module, the ladle and the strategy moduleせ を 定 的 な 的 な 的 な 定 定 的 な 的 な w ¾ 的 な ¾ 定 定 ¾ ¾ ¾ ¾ ¾ 定 ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾ ¾: It is about a system that s ¾ を を を 物語 ¾ 物語 物語 物語 物語 物語 物語 物語Ability to respond to human-power f sensitive information and to enable the creation of t-words

By ^ forms ability to Γ formed in A勐it'j ·钦a ladle of by Π ίΗ heat treatment ffl, _r. This from that of the machine ffi in argument ffl example forms s .1 to w become ability It is described by ^ Technical Modules & Strategic Modules, and is described below. The second field of ffl is, among the components of the present invention:: | Of the module;!

The 求 δ enclosing three terms are the description of the ^ ^ technique module among the ^ components of the description.

The S5 W ¾ 4 term in the request is a description of the strategy module, a component of the present invention.

The request, 西 5 west 7 if ?, is a knowledge-based notation in the key elements of this scream, W.

上 2nd, 3rd, 4th, and 7th are on the top of the description in the description. '述 述 述 述 ^ ^ 述 述 述 述' 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述 述And the newly added IJU from ¾ 5 2 ¾ to Ϊ 55 、, the sub-description of the header of :: 5 ¾ 1 ¾ 7; is given from 4 2 ¾ to 51 ¾ To

Sections {5}, 14th to 41, of the request are the sections on each of the techniques described in section ii'j in the scooping technique module: H in ^ asked of ffi ffl S 2 3 ^ fine ¾ 2 7 term, 2i associated with in predicates in the argument W example:!. for r is 1¾ cross-sectional that there is, i'i ^1] Vf was Sawa ', Te , These two become ^, Tr,-

,! S request 《ΰ ffl '75 5 Hi, “5 6 び; i 5 2 ¾? 5 5 5 W is a scoop, ΐ5 ¾ ¾ ¾ ジ ジ ¾ ¾ ¾ ¾; -The j'l great advantage in the description: · The sign is in this ^^^ By making use of the same set of narrative techniques in A, by using the same number of rule groups 7 and their control mechanisms, it is possible to create scribbles in an extremely simple way. _c ie at the point as possible Te row, hand in the ladle word generation machine ellipse, which is ^ mentioned in the cited example, which is the (4 rather than using the procedures for the small number of generation, Me f [¾ constant A bleaching algorithm is defined, in which platform the formation is performed with ~ f hand, so that the one with the structure of ί "] _c contrast to only be generated, in the present invention, those which respond to fixed growth Arugori rhythm of coming is, ¾ soft · Y standing for ί.ϊ Tanai narrative strategy rule group a with the II The result is that it is driven by it to turn the scoop into a ^ R ^^ In the conventional method, an algorithm is devised for each fixed application case (ie, the structure of the required scoop). According to the present invention, it is necessary to move the system one by one, but only by handing one of the rules applied to the structure of — It is possible to adapt to the application software of the industry, and the profit ffl of the industry is greatly expanded. There are «85 rules' groups in the 'legorism' sub-block, and the module is' r 'in' r ': ί ί ί ί ろ. _r pressure is 'is ¾ management, such as removal · ϋ ^ the effect on the gutter ^ Tsu oice丄§ ι ¾ possible to the ¾ Umate ¾' Kowama in - possible a young of ¾_々 such as octopus Allowed And to the point, the present invention is ¾ to w in 栊 that is Ψί to pull example, a 圻 |. ¾ of ½ BiSusumu * n the to fi ^

„ ^: The as 两 求 5 of the request is the description of the ^ 定 technique-suitable w-point machine t» in the scoop BS. The ϊδ 两 6th 项 of the request is じ; It is the _iL statement of the decision 栲 栲.............................. で は. で は で は .. In the meantime, the fundamental advantages of this book n) j, which allows for the use of a scoop “15 works hi”, were clearly described. 55 11H 5 3: is the description of the control of the rule selection in the 4 module ¾ μ μ μ [[[[[[[4 4 4 4! The 两 55 of £ 1 ^ which is related to some zo / is; S ffl ladder ,; ft Is a ji! That is a ji! <<1 'on the top of the statement, and makes a strategic module.

, is request ¾a ii 4 2 ¾ through 51 is a subordinate request to a 識 knowledge base; a. Mi5a 49 9 and 51 m of the request in ι¾ When Mi are the same as the ^ statement in the ffl example: '; r -Then, the two are '/ i of η, Ί; S 1 and fl are πίΐ'n'j in screaming (') ·: htcho: Hid : 1! '' R '''''': 1 ': 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1: 1力 、, this hand L'I ^ or this book «There is no Bys-like * point in the R, because -r, w ^;!; ^,, Η of "Ή r'- the« i ''Oru's in is rather than, of T: «ft Ηϋ a have is this Toka ^llF l ^π is ^ H fi'j in ¾ yelling. '·.'. '. T T T T T T T T T T T T T T T T T 片 片 T 片 片 T T 片 片 片 片j T W w Γ τ Te of ^ i skills, ί: of (1 · ¾ t¾ a ili This is a point that can be realized by embedding and that various effects that were previously impossible on utilization and development are obtained as described above. In this respect, the present invention is 'substantially different from the description of the cited example', and the definition of the S-form of each f task is clear and appropriate. It differs from the description in the cited example. For these reasons, the present invention claims novelty and inventive step.

, 求 w 四 四 四 四 四 四 四 四 四 四 四 四 四 四 四 四 四

^ Generation module 1, 、 杓 技法 技法 技法 戦 略 ft 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略 戦 略The definition is unique in this description <