KR102705062B1 - Method and computer readable storage medium for automatic generating game quest using machinc readaing comprehension - Google Patents

Abstract

A computer readable storage medium according to one embodiment may store one or more programs, wherein the one or more programs may include instructions that, when executed by a processor of an electronic device, cause the electronic device to receive first information comprising a sequence of texts based on a natural language, in response to receiving the first information, obtain one or more scripts distinguished by one or more nodes mapped to at least one of the texts, and in response to obtaining the one or more scripts, combine resource data represented by the texts with the obtained one or more scripts to obtain second information representing a quest outputtable by a specified application. Various other embodiments are possible.

Description

METHOD AND COMPUTER READABLE STORAGE MEDIUM FOR AUTOMATIC GENERATING GAME QUEST USING MACHINC READAING COMPREHENSION

The following descriptions relate to a method for automatically generating a story quest using machine reading and a computer-readable storage medium thereof.

RPG (Role Playing Game) is a game in which a character's personality is formed and problems are solved while performing a specific role. Recently, with the development of the Internet, MMORPG (Massively Multi-player Online Role Playing Game) games that many users can enjoy online at the same time have appeared, and they are developing into a form in which many users can enjoy the game at the same time. Within the game, users can receive in-game content such as quests. Quests can allow users to grow their characters, obtain game items that increase the character's abilities, and obtain game money to purchase items, etc. Quests refer to missions that the user's character must perform. For example, when the user's character performs a quest, game items or game money can be provided to the user and/or the character as compensation for the performed quest. The forms of these quests are generally distinguished as eliminating villains or monsters, collecting specific items, and/or delivering specific items. Game developers are constantly trying to add quests in large quantities and continuously to stimulate users' interest, but the existing quest production method is mainly carried out manually by content designers, and it is inefficient as the work progress is slowed down due to dependencies between related tasks.

A method may be required to automate the process of creating and/or adding in-game content, such as quests.

The technical problems to be achieved in this document are not limited to the technical problems described above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which the present invention belongs from the description below.

A computer readable storage medium according to one embodiment may store one or more programs, the one or more programs including instructions that, when executed by a processor of an electronic device, cause the electronic device to receive first information comprising a sequence of texts based on a natural language, in response to receiving the first information, obtain one or more scripts distinguished by one or more nodes that map to at least one of the texts, and in response to obtaining the one or more scripts, combine resource data represented by the texts with the obtained one or more scripts to obtain second information representing a quest outputtable by a specified application.

An electronic device according to one embodiment comprises a memory storing a plurality of instructions, and at least one processor operably coupled to the memory, wherein the at least one processor, when executing the plurality of instructions, receives first information including a sequence of texts based on a natural language, in response to receiving the first information, obtains one or more scripts distinguished by one or more nodes mapped to at least one of the texts, and in response to obtaining the one or more scripts, combines resource data represented by the texts with the obtained one or more scripts to obtain second information representing a quest outputtable by a specified application.

A method of an electronic device according to one embodiment may include receiving first information including a sequence of texts based on a natural language, in response to receiving the first information, obtaining one or more scripts distinguished by one or more nodes mapped to at least one of the texts, and in response to obtaining the one or more scripts, obtaining second information representing a quest outputtable by a specified application by combining resource data represented by the texts with the obtained one or more scripts.

An electronic device according to one embodiment may automate the process of creating and/or adding in-game content, such as quests, by generating a script recognizable by a game application from natural language text written by a user based on natural language recognition.

The effects obtainable from the present disclosure are not limited to the effects described above, and other effects not mentioned will be clearly understood by those skilled in the art to which the present disclosure pertains from the description below.

FIG. 1 illustrates an example of an environment including electronic devices according to various embodiments.
FIG. 2 illustrates a simplified block diagram of a quest automatic generation system of a first electronic device according to various embodiments.
FIG. 3 is a flow chart illustrating a quest creation process (300) for automatically generating a quest based on a narrative entered by a developer according to various embodiments.
FIG. 4 is a flow chart illustrating a specific process of machine reading a narrative input by a developer according to various embodiments.
Figure 5 conceptually illustrates the process by which a narrative is translated into a script using machine reading, according to various embodiments.
Figure 6 conceptually illustrates the process by which a narrative is divided into multiple nodes and the divided nodes are visualized, according to various embodiments.
FIG. 7 is a flow chart illustrating a quest creation process (700) for automatically generating a quest based on a narrative entered by a developer according to various embodiments.
FIG. 8 illustrates a screen displayed on a developer's electronic device with a tool for inputting visual nodes provided according to various embodiments.
FIG. 9 is a simplified block diagram of electronic devices according to various embodiments.
FIG. 10 illustrates a workflow related to the creation of a quest based on a first electronic device according to various embodiments.

Below, various embodiments of this document are described with reference to the attached drawings.

The various embodiments of this document and the terminology used herein are not intended to limit the technology described in this document to the specific embodiments, but should be understood to encompass various modifications, equivalents, and/or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar components. The singular expressions may include plural expressions unless the context clearly indicates otherwise. In this document, expressions such as "A or B", "at least one of A and/or B", "A, B, or C" or "at least one of A, B and/or C" can include all possible combinations of the items listed together. Expressions such as "first", "second", "first" or "second" can modify the corresponding components, regardless of order or importance, and are only used to distinguish one component from another and do not limit the corresponding components. When it is said that a certain (e.g., a first) component is "(functionally or communicatively) connected" or "connected" to another (e.g., a second) component, said certain component may be directly connected to said other component, or may be connected through another component (e.g., a third component).

The term "module" as used in this document includes a unit composed of hardware, software or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integrally composed component or a minimum unit or part thereof that performs one or more functions. For example, a module may be composed of an application-specific integrated circuit (ASIC).

FIG. 1 illustrates an environment including electronic devices according to various embodiments.

Referring to FIG. 1, the environment (100) may include a first electronic device (110), a second electronic device (120), and a third electronic device (130).

In various embodiments, the first electronic device (110) may be at least one server providing a quest creation tool according to a method for automatically generating a story quest using machine reading. A user (or developer) having certain qualifications may access the quest creation tool provided by the first electronic device (110) using his or her own electronic device. In various embodiments, the first electronic device (110) may include a quest automatic creation system (111) providing the quest creation tool. The quest automatic creation system (111) may be a system formed by the first electronic device (110) and/or a plurality of electronic devices including the first electronic device (110). The first electronic device (110) may transmit a quest generated by developers in the quest automatic creation system (111) to a second electronic device (120) providing a game service. The second electronic device (120) may provide the quest received from the first electronic device (110) to users within the game service. In various embodiments, the first electronic device (110) may execute communication so that the developers' electronic device can connect and transmit the created quest to the second electronic device (120).

In various embodiments, the second electronic device (120) may be at least one server that performs the role of allowing a user to proceed with a game using a quest created by the first electronic device (110) and provides game play to a user using the third electronic device (130). The second electronic device (120) may store game data necessary for the game to proceed, such as game display, game screen processing, sound effect processing, and provision of various user interfaces for the game. In addition, the second electronic device (120) may store various game data related to the game progression, such as virtual space information that serves as the background of the game, game scenario information, and game quest information. The second electronic device (120) may adapt a story quest received from the first electronic device (110) to the game data and provide it to the users. The second electronic device (120) may transmit data on adaptive elements (e.g., difficulty of a quest, value of a quest reward, value of an item) that change according to the game play of the users to the first electronic device (110) so that it may be reflected in the story quest production process.

In various embodiments, the second electronic device (120) may include an account server. The account server manages user account information and may perform authentication for a user who accesses the device. At this time, the account information may include authentication information such as an ID and password, character type, level, HP (Hit Point), MP (Mana Point), character status information such as the character's item information, and the like.

In various embodiments, the second electronic device (120) may receive in-game information of a user playing a game from the third electronic device (130) and adaptively update game data based thereon. For example, the game data of the second electronic device (120) may be displayed on the third electronic device (130), and the user's in-game information for the displayed game screen may be updated or newly generated based on the in-game information transmitted by the third electronic device (130). For example, when the user of the third electronic device (130) acquires experience points or a new item while playing the game, the in-game information related to the acquisition of the item may be transmitted to an account server included in the second electronic device (120), and the user's account information may be updated based on the in-game information related to the acquisition of the item. The above-described transmission and reception of game data and in-game information between the second electronic device (120) and the third electronic device (130) may be performed in real time. In various embodiments, the second electronic device (120) may execute communication with the first electronic device (110) to receive a quest generated by the first electronic device (110), and may execute communication with the third electronic device (130) to provide a game service to the third electronic device (130).

In various embodiments, the third electronic device (130) may be a client device (e.g., a desktop computer, a laptop computer, a smartphone, a tablet computer, a game console, etc.) for a user to play a game provided by the second electronic device (120).

In various embodiments, the third electronic device (130) can access the game through an application that can access the game provided by the second electronic device (120). In various embodiments, if the game provided by the second electronic device (120) is a web game that can be enjoyed with a web browser without installing a separate client (or application), the third electronic device (130) can access the game through a web browser application. For example, a web browser is an application that enables the use of a web (WWW: world wide web) service. For example, a web browser refers to a program that receives and displays hypertext described in HTML (hypertext mark-up language), and may include, for example, Netscape, Explorer, Chrome, Safari, etc.

FIG. 2 illustrates a simplified block diagram of an automatic quest generation system (e.g., the automatic quest generation system (111) of FIG. 1) of a first electronic device (e.g., the first electronic device (110) of FIG. 1) according to various embodiments. Referring to FIG. 2, the automatic quest generation system (111) according to various embodiments may include a quest framework (210), a node visualization module (220), a simulation unit (230), and a game information collection unit (240). The quest framework (210), the node visualization module (220), the simulation unit (230), and the game information collection unit (240) may correspond to any one of the electronic devices (e.g., the first electronic device (110) of FIG. 1) constituting the automatic quest generation system (111), or may correspond to at least one of the programs included in the automatic quest generation system (111).

In one embodiment of FIG. 2, the quest framework (210) may include a narrative editor (211), a narrative translator (212), a quest resource database (213), and a script template database (214).

In various embodiments, the narrative editor (211) may provide a tool for writing a narrative of a quest story that a developer wants to create. The narrative editor (211) may provide a user interface (UI) for the developer to input a narrative. In other words, the narrative editor (211) may provide a UI for creating a quest, particularly for inputting a narrative, on the developer's electronic device. Here, the narrative, in its dictionary sense, means a story development inherent in an act of describing or describing a real or fictional event. In the present disclosure, a story quest may mean a series of events in which various events related to a PC (Player Character) in the game (e.g., events occurring between a PC and an NPC (Non Player Character)) are causally connected. In the present disclosure, a story quest may mean a combination of texts in the form of a scenario input by a developer. Developers can freely input a narrative in script form about a series of quests or events through the narrative editor (211).

In one embodiment, the narrative editor (211) may provide a text input tool as a UI based on a document writing tool (e.g., software such as a word processor) for a developer to input a sequence of scenes, episodes, or quests as sentences. In another embodiment, the narrative editor (211) may provide a visual input tool as a UI for a developer to write dialogue and text on visual nodes representing scenes, episodes, or quests, and to arrange multiple nodes and specify their order and relationships through wireframes.

In various embodiments, the narrative editor (211) may receive a narrative including information required for creating a story quest from a developer through the UI. For example, the information required for creating a quest may include text information including a character's personality, speaking habits, characteristics of a place, and context information of a previous quest or narrative. For another example, the information required for creating a quest may include a dialogue including a region where a quest is performed, a character, and a central event.

In various embodiments, the narrative translator (212) may translate information input by the narrative editor (211) into a script. Here, the script may mean a type of program that describes in text a processing procedure to be executed by a game client (e.g., a game application) in order to provide a game service. For example, the script may be composed of a combination of commands expressed using the rules and syntax of an application program or utility and simple control structures such as loops and IF/THEN, and may be used to automate a series of processes that combine procedures that can be controlled by an end user on an application program or an operating system (OS).

The narrative translator (212) can use a language model to translate information input by the narrative editor (211) into a script. For example, the narrative translator (212) can preprocess information received by the narrative editor (211) so that it can be used in a language model. In other words, the narrative translator (212) can preprocess review data using natural language processing (NLP) technology that analyzes and processes morphemes, syntax, etc., which are components of natural language, as a language that people usually use. The narrative translator (212) can convert a narrative into a form that can be translated into a script through natural language processing.

In various embodiments, the narrative translator (212) may include a machine reading engine that may utilize a word embedding method that densely vectorizes the meaning of words included in the narrative. Word embedding is a method of expressing words as dense vectors, and may mean converting words into dense representations. Dense representation is the opposite concept of sparse representation, and may mean unifying the dimension of vector representations of all words into a value set by the system. In addition, word embedding may be implemented in various ways, including LSA, Word2Vec, FastText, and Glove. The word embedding as above can utilize a method of loading pre-trained embedding vectors with a large corpus such as a web encyclopedia (e.g., Wikipedia) to vectorize words. In addition, a separate data set from the data set for representative words for quest generation can be prepared, and the upper layer of the existing model can be released and trained together with the new layer, Fine-Tuning, and/or Full-Learning can be used to vectorize by learning without using the existing model. Such machine learning can utilize the Pre-trained Embedding model and Fine-tuned model included in the narrative translator (212).

In various embodiments, the narrative translator (212) can summarize the narrative through natural language semantic analysis (NLU Semantic Analysis) of the entire narrative input through the narrative editor (211), distinguish the subject and keywords of the quest, regions, characters, central events, etc., grasp the overall context of the narrative, and tag (or label) each sentence and word included in the narrative with what information it contains.

In various embodiments, the narrative translator (212) can perform a probability analysis on the detailed information or sentences by referring to the context of the entire narrative. In various embodiments, the narrative translator (212) can verify the narrative probability through the probability analysis. If the narrative translator (212) determines that the input narrative lacks probability, it can provide a message informing the developer of the lack of probability through the UI provided by the narrative editor (211).

In various embodiments, the narrative translator (212) may separate phrases based on each scene and main episode represented by the narrative (or multiple dialogues included therein). Hereinafter, scenes and/or events represented by the narrative may be referred to as events. In another embodiment, the narrative translator (212) may separate phrases so that multiple phrases are included in one scene. A scene or phrase classified by the narrative translator (212) may be referred to as a node. The node may be visualized by the node visualization module (220). The visualized node is displayed on the developer's electronic device, allowing the developer to intuitively recognize the process of translating the narrative into a script.

In various embodiments, the narrative translator (212) can divide the dialogue sentences separated by phrase into sentences representing action information and situation information to be performed by the PC and NPC, or action information and situation information. The information or sentences divided in this way can have a short sentence form.

In various embodiments, the narrative translator (212) can replace actions for which meaning has been identified with previously learned verb types and identify objects as modifiers and parameters. The narrative translator (212) can retrieve and combine script templates corresponding to learned verb types to generate a draft of a script. The narrative translator (212) can retrieve and record quest resources (or resource names) as parameters stored in advance in the generated script draft, and can generate a script by modifying and adding lines to fit the quest execution of the appearing NPC.

In various embodiments, the narrative translator (212) can complete script generation by generating joint information that connects multiple scripts translated phrase by phrase according to the above method, script to script, and branching of script and dialogue, and inputting data corresponding to parameters.

In various embodiments, the quest resource database (213) can store resources related to quests as modules.

In various embodiments, the quest resource database (213) may store resource data used in the game. The resource data may include information and locations within the game where the PC performs a quest, information on monsters to hunt, NPCs that give quests or provide information, items to be obtained or used, and skills.

In various embodiments, the quest resource database (213) may store resource data having a unique ID value that is the same as a value in the game service. In various embodiments, the resource data may be modified in the quest automatic generation system (111) (or the quest resource database (213)) or may be modified in the game server (e.g., the second electronic device (120)) that provides the game service. The value of the resource data may be synchronized in real time in the quest automatic generation system (111) and the second electronic device (120), so that when the resource data is changed or added in one place, it may be reflected in real time in the quest production or the game service provision. In various embodiments, the resource data may not have a fixed value but may have a variable value. For example, the price of an arbitrary item may fluctuate depending on the supply and demand of the item, and a value having such a variable value may be reflected in real time in the quest resource database (213).

In the above embodiments, data synchronization between the second electronic device (120) as a game server and the quest resource database (213) can be performed by the game information collection unit (240) included in the quest automatic generation system (111).

In various embodiments, the quest resource database (213) may store not only resource data used in the game, but also additional information required for quest creation. For example, the additional information may include the appearance location and time of the monster that is the target of the quest's mission, clustering, aggression, personality and relationship information between NPCs, and special settings. In various embodiments, the additional information may be used to verify whether the machine reading of the narrative in automatic quest creation is not out of line with the probability.

In various embodiments, data (e.g., resource data, additional information) stored in the quest resource database (213) may be used by a developer when writing a quest scenario using the narrative editor (211). For example, the narrative editor (211) may provide a resource search function that searches for data stored in the quest resource database (213). Depending on the resource search function, the developer may set a resource name or characteristic information and a search condition, and then receive a list of the corresponding resources in a separate window. Specifically, when a developer using the narrative editor (211) searches for “Hero Grade & One-Handed Sword & Crafting,” a list of hero grade one-handed swords that can be obtained through crafting may be displayed. In addition, when a developer using the narrative editor (211) searches for “OO Region & Boss & Undead,” a window listing boss monsters of the undead type that appear in the corresponding region may be displayed. For another example, the narrative editor (211) may provide a resource name auto-completion function for data stored in the quest resource database (213). According to the resource name auto-completion function, a developer may input a special symbol (e.g., @, #, $) and a part of a resource name while writing a narrative, and the entire resource name may be auto-completed. For example, the special symbol @ represents a monster, and when the developer inputs "@언", the entire resource name "@운드" may be automatically completed.

In various embodiments, the script template database (214) may store predefined script templates according to the types of actions that the PC must perform. The actions that the PC must perform in a quest may be generalized into several verbs. For example, the PC performing the quest may include actions such as killing a monster (kill, hunt), collecting an item (gather, collect), delivering an item (deliver, give), receiving an item (take), using an item (use), or talking to another PC or NPC. In response to a quest that follows such generalized actions, a script template may be predefined, excluding parameters such as the target and quantity of the action.

In various embodiments, the quest framework (210) may obtain scripts representing the entire quest by combining predefined script templates for each action stored in the script template database (214), and/or by embedding parameters into the script templates. The quest may be a sequential set of actions, and the script of the quest may be a sequential combination of predefined script templates for each action. For example, the quest may be a sequential set of actions of killing a monster (kill), collecting items left by the monster (gather), and delivering the collected items to an NPC (give). In this case, the script corresponding to the quest may be configured by sequentially combining predefined script templates corresponding to kill, gather, and give stored in the script template database (214).

FIG. 3 is a flow chart illustrating a quest creation process (300) for automatically creating a quest based on a narrative input by a developer according to various embodiments. The process (300) of FIG. 3 may be executed by the first electronic device (110) illustrated in FIG. 1 or the automatic quest creation system (111) illustrated in FIG. 2.

Referring to FIG. 3, in operation 301, the first electronic device (110) may receive an input narrative for quest creation. The narrative may be input from a developer's electronic device through a UI (user interface) provided by the first electronic device (110). The first electronic device (110) (or narrative editor (211)) may provide a UI for quest creation, particularly for narrative input, to the developer's electronic device. Here, the narrative may mean a combination of texts in the form of a scenario input by the developer or a list of texts. For example, the developer may freely input a narrative in the form of a scenario regarding successive quests or events through the UI (user interface) provided by the first electronic device (110).

In operation 303, the first electronic device (110) (or narrative translator (212)) may analyze the narrative received in operation 301 using machine reading. For example, the first electronic device (110) may preprocess the narrative in which texts are listed using natural language processing (NLP) technology. In other words, the first electronic device (110) may convert the narrative into a form that can be translated into a script through natural language processing.

The first electronic device (110) can separate sentences based on events such as each scene and main episode in the narrative. The scene or sentence classified by the first electronic device (110) can be referred to as a single node. That is, in operation 303, the first electronic device (110) (or narrative translator (212)) can separate the narrative into multiple sentences or nodes through machine reading analysis of the narrative received in operation 301.

In operation 305, the first electronic device (110) (or the narrative translator (212)) may generate a script separated by node based on the analysis result of the machine reading. For example, the first electronic device (110) may replace the actions included in each node with verbs of a previously learned type and identify modifiers, parameters, and objects, and replace them with resource names or Unique IDs corresponding to quest resource data. The first electronic device (110) may retrieve and combine script templates corresponding to the learned verbs of a previously learned type to generate a draft of the script. The search for the script templates may be performed in the script template database (214). In various embodiments, each node may mean a quest, which is a continuous set of actions, and the script corresponding to the node may be a continuous combination of script templates predefined for each action. For example, a quest divided into nodes may be a sequential set of actions of killing a monster (kill), collecting items left by the monster (gather), and delivering the collected items to an NPC (give). In the above example, one or more scripts corresponding to such a quest may be generated by sequentially combining predefined script templates corresponding to kill, gather, and give stored in a script template database (214).

In operation 307, the first electronic device (110) (or narrative translator (212)) can automatically input quest resource data according to the script generated in operation 305 to generate a quest. The first electronic device (110) can retrieve and record a quest resource (or resource name) as a parameter pre-stored in the generated script. For example, the first electronic device (110) can record a text based on the machine reading analysis result of operation 303 in a line included in the script. The search for the quest resource data can be performed in the quest resource database (213).

In operation 309, the first electronic device (110) (or the simulation unit (230)) may perform a simulation on the generated quest in order to verify the generated quest. By testing the generated quest by simulating it, an environment may be provided in which the developer can quickly and easily provide feedback on whether the translation of the narrative into a script is well done, whether the probability between consecutive events of the generated story quest is sufficient, etc. In various embodiments, operation 309 may be performed selectively, and the quest generated in operation 307 may be directly transmitted to a server servicing the game (e.g., the second electronic device (120)).

As described above, the first electronic device (110) according to various embodiments performs the quest creation process (300), so that a developer can automatically create a quest by utilizing pre-modularized quest resources and script templates through parallel operations, simply by inputting a narrative. As the quest is automatically created, time resources, human resources, and duplicate costs are saved, so that the quest can be created efficiently.

FIG. 4 is a flow chart illustrating a specific process of machine reading a narrative input by a developer according to various embodiments. The process (400) of FIG. 4 may be a specific process of operation 303 described in FIG. 3, and these operations may be executed by the first electronic device (110) illustrated in FIG. 1 or the narrative translator (212) illustrated in FIG. 2.

Referring to FIG. 4, in operation 401, the first electronic device (110) (or narrative translator (212)) can perform natural language semantic analysis included in the narrative. First, the first electronic device (110) summarizes the entire narrative input by the developer, distinguishes topics and keywords, regions, characters, central events, etc., understands the entire context of the narrative, and tags each sentence and word included in the narrative with what information. The process of the first electronic device (110) tagging each sentence and word included in the narrative with what information will be described with reference to FIG. 5.

Figure 5 conceptually illustrates the process by which a narrative is translated into a script using machine reading, according to various embodiments.

Referring to FIG. 5, according to various embodiments, the first electronic device (110) (or narrative translator (212)) may summarize the narrative (510) input by a developer through natural language semantic analysis (NLU Semantic Analysis), distinguish the subject and keywords of the quest, regions, characters, central events, etc., understand the entire context of the narrative, and tag each included sentence and word with information. As described above, in various embodiments, the first electronic device (110) may perform machine reading to understand what information each sentence and word is, and may preprocess the narrative (510) to perform the machine reading.

For example, the first electronic device (110) (or narrative translator (212)) can determine the central action, central event, or theme of the quest in the narrative (510). For example, the narrative (510) can include the sentence "Starting village NPC OO earnestly asks for a favor from the PC" as fingerprint information. Also, the narrative (510) can include the sentence "Goblins keep destroying the farm, so I can't farm. Please hunt 30 goblins in the forest on the left! I'll give you 10,000 Aden and 3 sacks of crops." as input dialogue.

For a narrative (510) like this, the first electronic device (110) can determine the subject of the quest of the narrative (510) as 'request for monster hunting' and the main action as 'hunt' through a semantic analysis of the sentences "I earnestly ask you" and "Please hunt me!" in the fingerprint information included in the narrative (510).

In addition, the first electronic device (110) can tag "Start Village NPC OO (511)" as a quest giver in the fingerprint information, and can tag "earnestly (512)" as emotional information or context information. In addition, the first electronic device (110) can tag "Goblin (513)" as target information in the input dialogue, can tag "Left Forest (514)" as regional information, can tag "30 (515)" as a quantity parameter, can tag "10,000 Aden (516)" as a reward, and can tag "3 Sacks of Crops (517)" as a crop sack; reward item, 3 sacks as the reward item quantity, respectively.

Meanwhile, in various embodiments, the first electronic device (110) (or narrative translator (212)) may generate a script (520) based on the main action and tagged information determined as a result of semantic analysis of the narrative (510). For example, if the action information of the narrative (510) is semantically analyzed as 'hunt', the first electronic device (110) may load a script template for hunting from the script templates predefined for each action stored in the script template database (214), and determine the parameters to be input in the script. For example, the script (520) of FIG. 5 is loaded with a script template for 'hunt (523)', and within the script (520), the quest granter (521), the emotion information (522), the dialogue (523), and the parameter (525) may be adjusted based on the information tagged by the narrative (510). The action of generating such a script may be at least partially identical to the action in action 305 of FIG. 3.

In various embodiments, the first electronic device (110) can verify narrative plausibility through semantic analysis. If the first electronic device (110) determines that the input narrative lacks plausibility, the first electronic device (110) can transmit a message notifying the developer of the lack of plausibility to the electronic device through the UI provided by the first electronic device (110).

Referring back to FIG. 4, in operation 403, the first electronic device (110) (or narrative translator (212)) may separate the narrative into phrases based on the natural language semantic analysis result, based on the main event. For example, the narrative may include multiple scenes, multiple main episodes, or multiple dialogues, and the first electronic device (110) may separate the narrative into phrases based on the scenes, main episodes, or dialogues. The scenes, main episodes, or phrases classified by the first electronic device (110) may be referred to as a single node.

FIG. 6 conceptually illustrates a process in which a narrative is divided into a plurality of nodes and the divided nodes are visualized, according to various embodiments. Referring to FIG. 6, a narrative (610) input by a developer may include a plurality of phrases. In various embodiments, the first electronic device (110) may separate the plurality of phrases included in the narrative (610) according to the natural language semantic analysis performed in operation 401. For example, the narrative (610) may include a first phrase (611), a second phrase (612), and a third phrase (613). In various embodiments, the developer may include an identifier, sentence, or word for phrase separation when inputting the narrative (610). In one example of FIG. 6, the developer may display a speaker (business Jeff) for each dialogue that may be phrase separated in the narrative (610), so that the phrases may be separated based on the displayed speaker. That is, the UI that the first electronic device (or narrative editor (211)) provides to the developer as a tool for narrative input can provide identifier input that helps in syntactic separation.

Referring again to FIG. 4, in operation 405, the first electronic device (110) (or the narrative translator (212)) may generate a node according to the analysis result through analysis for each separated phrase. In operation 407, the first electronic device (110) (or the node visualization module (220)) may visualize the node generated in operation 405. In various embodiments, the first electronic device (110) may transmit the visualized data to the developer's electronic device so that the visualized node may be displayed on the developer's electronic device. Referring again to FIG. 6, after the phrase included in the narrative (610) is separated, the separated phrase is generated as a node and a visualized node (620) is illustrated. For example, the first phrase (611) may be mapped to the first node (621). The second phrase (612) may be mapped to the second node (622). The third sentence (613) can be mapped to the second node (623). Based on the generated nodes (621, 622, 623), the first electronic device (110) can generate a script corresponding to each node. For example, a first script (631) can be generated based on the first node (621), a second script (632) can be generated based on the second node (622), and a third script (633) can be generated based on the third node (623).

Referring again to FIG. 4, in various embodiments, the act of visualizing the node in operation 407 may be omitted. In the example of FIG. 6, after the narrative (610) is phrase-separated, the first electronic device (110) may immediately generate a script (630) corresponding to the separated phrase.

As described above, the method for automatically generating a quest based on a narrative including a combination of texts in the form of a scenario or a listed texts has been described, but the embodiment is not limited thereto. For example, if the developer inputs dialogue and text into visual nodes representing scenes, episodes, or phrases using the first electronic device (110), and defines the order and connection between a plurality of visual nodes through a wireframe, the first electronic device (110) can generate a quest based on the defined plurality of visual nodes and the wireframe.

FIG. 7 is a flow chart illustrating a quest creation process (700) for automatically creating a quest based on a narrative input by a developer according to various embodiments. The process (700) of FIG. 7 may be executed by the first electronic device (110) illustrated in FIG. 1 or the quest automatic creation system (111) illustrated in FIG. 2.

Referring to FIG. 7, in operation 701, the first electronic device (110) may receive input for a plurality of nodes and input for wireframes between nodes. For example, the first electronic device (110) (or narrative editor (211)) may provide a visual input tool as a UI that allows a developer to write dialogue and text in visual nodes representing scenes, episodes, or quests, and to arrange a plurality of nodes and designate their order and relationships through wireframes.

FIG. 8 illustrates a screen displayed on a developer's electronic device (e.g., a first electronic device (110) and/or an electronic device connected to the first electronic device (110)) using a tool for inputting visual nodes provided according to various embodiments. Referring to FIG. 8, a developer can arrange visual nodes (810) and connect wire frames (820) between visual nodes (810) through a screen (800) displayed on an electronic device. Arrangement of visual nodes (810) and connection of wire frames (820) can be performed through an operation such as drag and drop using an input means such as a mouse. The developer can register fingerprint information and dialogue for each visual node (810). For example, a developer may designate speakers as 'Deltras' and 'Jikel' in a visual node (810), and a tool for inputting a visual node provided by the first electronic device (110) may load resource data with 'Deltras' and 'Jikel' as resource names from a quest resource database (213). The loaded resource data may include profile images of 'Deltras' and 'Jikel', and the profile images may be displayed on each visual node (810).

In various embodiments, each of the visual nodes (810) may include an object (821) for generating a wireframe (820), and when a developer selects the object (821), the wireframe that can be generated may be displayed in the form of a dropbox (830). In various embodiments, in addition to the UI illustrated in the screen (800) illustrated in FIG. 8, a UI that supports various functions may be further provided.

Referring back to FIG. 7, in operation 703, the first electronic device (110) may generate narrative information based on machine reading analysis results for the input plurality of nodes and wireframes between nodes. For example, based on the fingerprint information and dialogue included in the visual nodes input in operation 701 and the wireframes representing the relationships between the nodes, narrative information for script generation may be generated, including fingerprint information including the personality of a character, speaking habits, characteristics of a place, context information of a previous quest or narrative, or information including dialogue including an area where a quest is performed, a character, and a central event. The narrative information generated in operation 703 may be used to generate a script for each node in operation 705. Operations 705, 707, and 709 may be substantially the same as operations 305 to 309 described in FIG. 3, and thus, any redundant description will be omitted.

FIG. 9 is a simplified block diagram of electronic devices according to various embodiments.

Referring to FIG. 9, an electronic device (900) may be an example of a first electronic device (110) and a second electronic device (120). The electronic device (900) may include a processor (902), a memory (904), a storage device (906), a high-speed controller (908) (e.g., a northbridge, a Main Controller Hub (MCH)), and a low-speed controller (912) (e.g., a southbridge, an I/O controller hub (ICH)). Within the electronic device (900), each of the processor (902), the memory (904), the storage device (906), the high-speed controller (908), and the low-speed controller (912) may be interconnected using various buses.

For example, the processor (902) may process instructions for execution within the electronic device (900) to display graphical information for a graphical user interface (GUI) on an external input/output device, such as a display (916) connected to the high-speed controller (908). The instructions may be contained in the memory (904) or the storage device (906). The instructions, when executed by the processor (902), may cause the electronic device (900) to perform one or more of the operations described above. According to embodiments, the processor (902) may be comprised of a plurality of processors, including a communication processor and a graphical processing unit (GPU).

For example, the memory (904) may store information within the electronic device (900). For example, the memory (904) may be a volatile memory unit or units. For another example, the memory (904) may be a non-volatile memory unit or units. For another example, the memory (904) may be another form of computer-readable media, such as a magnetic or optical disk.

For example, the storage device (906) can provide mass storage space to the electronic device (900). For example, the storage device (906) can be a computer-readable medium, such as a hard disk device, an optical disk device, flash memory, a solid-state memory device, or an array of devices within a storage area network (SAN).

For example, the high-speed controller (908) may manage bandwidth-intensive operations for the electronic device (900), while the low-speed controller (912) may manage low-bandwidth intensive operations for the electronic device (900). For example, the high-speed controller (908) may be coupled to memory (904) and to a display (916) via a GPU or accelerator, while the low-speed controller (912) may be coupled to storage (906) and various communication ports (e.g., universal serial bus (USB), Bluetooth, Ethernet, wireless Ethernet) for communicating with external electronic devices (e.g., a keyboard, a transducer, a scanner, or a network device (e.g., a switch or router).

The electronic device (950) may be an example of the third electronic device (130). The electronic device (950) may include a processor (952), a memory (964), an input/output device such as a display (954) (e.g., an organic light emitting diode (OLED) display or other suitable display), a communication interface (966), and a transceiver (968). Each of the processor (952), the memory (964), the input/output device, the communication interface (966), and the transceiver (968) may be interconnected using various buses.

For example, the processor (952) may process instructions contained in the memory (964) to display graphical information for a GUI on the input/output device. The instructions, when executed by the processor (952), may cause the electronic device (950) to perform one or more of the operations described above. For example, the processor (952) may interact with a user through a display interface (956) coupled with a display (954) and a control interface (958). For example, the display interface (956) may include circuitry for driving the display (954) to provide visual information to the user, and the control interface (958) may include circuitry for receiving commands received from the user and converting the commands for providing them to the processor (952). According to embodiments, the processor (952) may be implemented as a chipset of chips including analog and digital processors.

For example, the memory (964) may store information within the electronic device (950). For example, the memory (964) may include at least one of one or more volatile memory units, one or more non-volatile memory units, or a computer-readable medium.

For example, the communication interface (966) may perform wireless communication between the electronic device (950) and an external electronic device through various communication techniques, such as a cellular communication technique, a Wi-Fi communication technique, an NFC technique, or a Bluetooth communication technique, based on interworking with the processor (952). For example, the communication interface (966) may be coupled with a transceiver (968) to perform the wireless communication. For example, the communication interface (966) may be further coupled with a GNSS (global navigation satellite system) receiving module (970) to obtain location information of the electronic device (950).

FIG. 10 illustrates a workflow (1000) related to the creation of a quest based on a first electronic device (110) according to various embodiments.

The creation of a quest considers various elements such as NPCs (non-player characters), items, and various objects, and depending on the difficulty or scale of the quest, hundreds or thousands of elements can be used as resources. Resources created for the creation of quests are often discarded instead of being reused for the creation of other quests, and dynamic story quests that can interest users inevitably have very complex narratives. The composition of dialogue and text to express the episodic events included in story quests is also complex, and it is even more difficult to write the narrative of a series of quests with plausibility. In this way, creating story quests requires a lot of preprocessing work and also takes a lot of time, and main quests can require several months of work from concept design to actual reflection in the game.

Meanwhile, quest creation can be largely categorized into three tasks: resource creation, narrative writing, script writing, and data entry. Once resource creation and narrative writing are completed for quest creation, the work of applying the content to the game system is required. These tasks can be collectively called script writing and data entry. In particular, script writing and data entry are areas that developers have worked on manually one by one. Even for similar quests, new quests and existing quests are bound to have different internal structures, such as the order and number of times actions and targets are processed, so it is difficult to consider copying and reusing scripts from existing quests that are similar to the quest you created. Meanwhile, resource creation, narrative writing, and script writing are interdependent, so they may require repeated performance of other tasks.

Referring to the workflow (1000) of FIG. 10, dependencies between tasks such as quest script writing (task 1020), quest resource creation (task 1030), and quest narrative writing (task 1040) after quest concept design (task 1010) can be eliminated by using the first electronic device (110). For example, quest resource creation (task 1030) and quest narrative writing (task 1040) can be performed independently. As shown in FIG. 10, by the independently received tasks (1020, 1030, 1040), the time interval between quest concept design (task 1010) and quest testing and verification (task 1050) can be reduced. For example, the first electronic device (110) can make it easy to reuse quest resources and enable parallel activities, thereby reducing costs such as time consumed to create a quest.

A computer readable storage medium according to one embodiment of the present invention as described above may include instructions storing one or more programs, wherein the one or more programs, when executed by a processor of an electronic device, cause the electronic device to receive first information comprising a sequence of texts based on a natural language, in response to receiving the first information, obtain one or more scripts distinguished by one or more nodes that map to at least one of the texts, and in response to obtaining the one or more scripts, combine resource data represented by the texts with the obtained one or more scripts to obtain second information representing a quest outputtable by a specified application.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to recognize the first information based on a language model for supporting machine reading, thereby obtaining the one or more scripts.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to identify one or more events represented by the sequence of texts based on the language model, and in response to identifying the one or more events, obtain one or more nodes mapped to the one or more events.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to identify, based on the language model, the resource data that matches at least one word included in the texts and is included in a database stored in a memory of the electronic device.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to obtain the one or more scripts based on script templates contained in a database stored within a memory of the electronic device.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to recognize the first information based on a language model for supporting machine reading, and extract the one or more scripts from among the script templates.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device, in response to obtaining the second information, to perform a simulation for a quest indicated by the second information.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to obtain third information indicating a connection between the plurality of nodes based on a sequence of the texts, in a state where the plurality of scripts, distinguished by the plurality of nodes, are obtained from the first information.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to display the plurality of nodes on at least a portion of a display of the electronic device based on connections between the plurality of nodes.

For example, the one or more programs may further include instructions that, when executed by a processor of the electronic device, cause the electronic device to: receive a user input related to the plurality of nodes while displaying the plurality of nodes on at least a portion of the display; in response to receiving the user input, change the plurality of nodes displayed on at least a portion of the display based on the user input; and change the second information based on the changing of the plurality of nodes.

An electronic device according to one embodiment of the present invention, as described above, includes a memory storing a plurality of instructions, and at least one processor operably coupled to the memory, wherein the at least one processor, when executing the plurality of instructions, receives first information including a sequence of texts based on a natural language, in response to receiving the first information, obtains one or more scripts distinguished by one or more nodes mapped to at least one of the texts, and in response to obtaining the one or more scripts, combines resource data represented by the texts with the obtained one or more scripts to obtain second information representing a quest outputtable by a specified application.

For example, the at least one processor may, when executing the plurality of instructions, recognize the first information based on a language model stored in the memory and supporting machine reading, and obtain the one or more scripts.

For example, the at least one processor, when executing the plurality of instructions, may identify one or more events represented by the sequence of texts based on the language model, and in response to identifying the one or more events, obtain one or more nodes mapped to the one or more events.

For example, the at least one processor, when executing the plurality of instructions, may identify, based on the language model, the resource data that matches at least one word included in the texts and is included in a database stored in the memory of the electronic device.

For example, the at least one processor may, when executing the plurality of instructions, obtain the one or more scripts based on script templates contained in a database stored in a memory of the electronic device.

For example, the at least one processor may, when executing the plurality of instructions, recognize the first information based on a language model stored in the memory and supporting machine reading, and extract one or more scripts from among the script templates.

For example, the at least one processor may, in response to obtaining the second information, perform a simulation for a quest indicated by the second information when executing the plurality of instructions.

For example, the at least one processor, when executing the plurality of instructions, may obtain third information indicating a connection between the plurality of nodes based on a sequence of the texts, while obtaining a plurality of scripts distinguished by a plurality of nodes from the first information.

For example, the electronic device further includes a display, and the at least one processor, when executing the plurality of instructions, can display the plurality of nodes on at least a portion of the display based on connections between the plurality of nodes.

For example, the at least one processor, when executing the plurality of instructions, may display the plurality of nodes on at least a portion of the display, receive a user input related to the plurality of nodes, and in response to receiving the user input, change the plurality of nodes displayed on at least a portion of the display based on the user input, and change the second information based on the changing of the plurality of nodes.

A method of an electronic device according to one embodiment as described above may include receiving first information including a sequence of texts based on a natural language, in response to receiving the first information, obtaining one or more scripts distinguished by one or more nodes mapped to at least one of the texts, and in response to obtaining the one or more scripts, obtaining second information representing a quest outputtable by a specified application by combining resource data represented by the texts with the obtained one or more scripts.

The devices described above may be implemented as hardware components, software components, and/or a combination of hardware components and software components. For example, the devices and components described in the embodiments may be implemented using one or more general-purpose computers or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. In addition, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone, but those skilled in the art will appreciate that the processing device may include multiple processing elements and/or multiple types of processing elements. For example, the processing device may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

The software may include a computer program, code, instructions, or a combination of one or more of these, which may configure a processing device to perform a desired operation or may independently or collectively command the processing device. The software and/or data may be embodied in any type of machine, component, physical device, computer storage medium, or device for interpretation by the processing device or for providing instructions or data to the processing device. The software may be distributed over network-connected computer systems and stored or executed in a distributed manner. The software and data may be stored on one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. At this time, the medium may be one that continuously stores a program executable by a computer, or one that temporarily stores it for execution or downloading. In addition, the medium may be various recording means or storage means in the form of a single or multiple hardware combinations, and is not limited to a medium directly connected to a computer system, and may be distributed on a network. Examples of the medium may include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and ROMs, RAMs, flash memories, etc., configured to store program commands. In addition, examples of other media may include recording media or storage media managed by app stores that distribute applications, sites that supply or distribute various software, servers, etc.

Although the embodiments have been described above by way of limited examples and drawings, those skilled in the art may make various modifications and variations from the above description. For example, appropriate results may be achieved even if the described techniques are performed in a different order than the described method, and/or components of the described system, structure, device, circuit, etc. are combined or combined in a different form than the described method, or are replaced or substituted by other components or equivalents.

Therefore, other implementations, other embodiments, and equivalents to the claims are also included in the scope of the claims described below.

Claims (20)

In a computer readable storage medium storing one or more programs,
One or more of the above programs, when executed by a processor of an electronic device,
Receiving first information comprising a sequence of texts based on natural language;
In response to receiving said first information, obtaining scripts distinguished by a plurality of nodes mapped to different portions of said texts; and
In response to obtaining said scripts, instructions causing said electronic device to obtain second information representing a quest outputtable by a specified application by combining resource data represented by said texts with said obtained scripts;
The scripts corresponding to the above multiple nodes are:
Contains tags that cause another electronic device running said specified application to output said quest while loaded by said specified application;
The above tags are generated by embedding parameters based on the texts in one of the script templates classified according to the main actions determined by the semantic analysis results for the first information.
Computer readable storage medium. In the first paragraph,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions causing the electronic device to recognize the first information based on a language model for supporting machine reading comprehension and obtain the scripts. In the second paragraph,
The above one or more programs, when executed by the processor of the electronic device,
Identifying multiple events represented by a sequence of texts based on the language model; and
A computer-readable storage medium further comprising instructions that cause the electronic device to obtain the plurality of nodes mapped to the plurality of events, in response to identifying the plurality of events. In the second paragraph,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions causing the electronic device to identify the resource data contained in a database stored in a memory of the electronic device, the resource data matching at least one word contained in the texts based on the language model. In the first paragraph,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions causing the electronic device to obtain the scripts based on the script templates contained in a database stored within a memory of the electronic device. In paragraph 5,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions causing the electronic device to recognize the first information based on a language model for supporting machine reading, and to extract the scripts from the script templates. In the first paragraph,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions for causing the electronic device to perform a simulation for a quest indicated by the second information in response to obtaining the second information. In the first paragraph,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions that cause the electronic device to obtain third information indicating a connection between the plurality of nodes based on a sequence of the texts, wherein the plurality of scripts, which are distinguished by a plurality of nodes from the first information, are obtained. In Article 8,
The above one or more programs, when executed by the processor of the electronic device,
A computer-readable storage medium further comprising instructions causing the electronic device to display the plurality of nodes on at least a portion of a display of the electronic device, based on connections between the plurality of nodes. In Article 9,
The above one or more programs, when executed by the processor of the electronic device,
Receiving user input related to the plurality of nodes while displaying the plurality of nodes on at least a portion of the display;
In response to receiving said user input, changing said plurality of nodes displayed on at least a portion of said display based on said user input; and
A computer-readable storage medium further comprising instructions for causing the electronic device to change the second information based on changing the plurality of nodes. In electronic devices,
Memory for storing multiple instructions; and
comprising at least one processor operably coupled to said memory;
The at least one processor, when executing the plurality of instructions,
Receiving first information comprising a sequence of texts based on natural language;
In response to receiving said first information, obtaining scripts distinguished by a plurality of nodes mapped to different portions of said texts; and
In response to obtaining the above scripts, the second information representing a quest outputtable by the specified application is obtained by combining the resource data indicated by the texts with the obtained scripts,
The scripts corresponding to the above multiple nodes are:
Contains tags that cause another electronic device running said specified application to output said quest while loaded by said specified application;
The above tags are generated by embedding parameters based on the texts in one of the script templates classified according to the main actions determined by the semantic analysis results for the first information.
Electronic devices. In Article 11,
The at least one processor, when executing the plurality of instructions,
An electronic device that recognizes the first information based on a language model stored in the memory and supports machine reading, thereby obtaining the scripts. In Article 12,
The at least one processor, when executing the plurality of instructions,
Identifying multiple events represented by a sequence of texts based on the language model; and
An electronic device, in response to identifying said plurality of events, obtaining said plurality of nodes mapped to said plurality of events. In Article 12,
The at least one processor, when executing the plurality of instructions,
An electronic device that identifies the resource data contained in a database stored in a memory of the electronic device, the resource data matching at least one word contained in the texts based on the language model. In Article 11,
The at least one processor, when executing the plurality of instructions,
An electronic device that obtains the scripts based on the script templates contained in a database stored within a memory of the electronic device. In Article 15,
The at least one processor, when executing the plurality of instructions,
An electronic device that recognizes the first information based on a language model stored in the memory and supporting machine reading, and extracts the scripts from among the script templates. In Article 11,
The at least one processor, when executing the plurality of instructions,
An electronic device that, in response to obtaining the second information, performs a simulation for a quest indicated by the second information. In Article 11,
The at least one processor, when executing the plurality of instructions,
An electronic device that obtains third information indicating a connection between the plurality of nodes based on a sequence of the texts, while obtaining a plurality of scripts distinguished by a plurality of nodes from the first information. In Article 18,
The above electronic device,
Including more displays,
The at least one processor, when executing the plurality of instructions,
An electronic device that displays a plurality of nodes on at least a portion of the display based on connections between the plurality of nodes. In Article 19,
The at least one processor, when executing the plurality of instructions,
Receiving user input related to the plurality of nodes while displaying the plurality of nodes on at least a portion of the display;
In response to receiving said user input, changing said plurality of nodes displayed on at least a portion of said display based on said user input; and
An electronic device that changes the second information based on changing the plurality of nodes.

Images