WO2022092246A1 - Program, information processing device, and method - Google Patents

Abstract

This program causes an information processing device (10) including a processor to execute: a first step of outputting to a user a literary work for learning the preferences of the user; a second step of accepting input of a response from the user, where the response is an emotion other than a preference held by the user with respect to the output literary work; a step of repeating the first step and the second step a predetermined number of times; a step of using a plurality of groups comprising the output literary work and the response to the output literary work to learn the preferences of the user; a step of selecting a literary work matching the preferences of the user from a set of literary works, on the basis of the learned preferences of the user; and a step of outputting the selected literary work to the user.

Description

[Name of invention determined by ISA based on Rule 37.2.] Program, information processing device and method

This disclosure relates to programs, information processing devices, methods, and information processing systems.

In recent years, applications have been developed that learn user preferences regarding copyrighted works and automatically present images of user preferences.

US Pat. The desired image, including each step of extracting the user's relative preference for the image; formulating the user's subjective determination of the desired image using the relative preference for either the image component or the depiction feature. "Learn the user's preference for".

Japanese Unexamined Patent Publication No. 2000-305974

However, in the field of art, for example, the user's favorite art is often produced by the artist who created the art. The gallery contracts with a painter and opens a solo exhibition of the painter to sell it to users who like the painter's paintings. For this reason, an artist who is known to some extent can obtain the art from the gallery, but if the art of an unknown artist is the user's preference, it is difficult for the user to find the art that he / she wants to purchase. There was a problem.

Therefore, the purpose of this disclosure is to provide a program that can be presented to the user even if the copyrighted work of the user is the copyrighted work of an unknown author.

In the program according to the present disclosure, a first step of learning a user's preference in advance in an information processing device including a processor, and a copyrighted work of the user's preference based on the user's preference learned in advance, the copyrighted work of the user. The second step of selecting from a set of works including the works of authors who are not well known in the field to which they belong and the third step of outputting the selected works to the user are executed.

According to the program according to the present disclosure, even if the copyrighted work of the user is the copyrighted work of an unknown author, it can be presented to the user.

It is a block diagram which shows the whole structure of an information processing system 1. It is a block diagram which shows the structure of an information processing apparatus 10. It is a block diagram which shows the functional structure of an information processing apparatus 10. It is a figure which shows an example of the data structure of the user DB 121. It is a figure which shows an example of the data structure of a painting DB 122. An example of the screen displayed on the user terminal 20 is shown. An example of the screen displayed on the user terminal 20 is shown. An example of the screen displayed on the user terminal 20 is shown. An example of the screen displayed on the user terminal 20 is shown. It is a figure which shows the structure of the user terminal 20. It is a block diagram which shows the functional structure of a user terminal 20. It is a flowchart which shows an example of the flow which performs the registration process by an information processing apparatus 10. It is a flowchart which shows an example of the flow of performing a learning process by an information processing apparatus 10. It is a flowchart which shows an example of the flow which performs the display process by an information processing apparatus 10.

Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The information processing system 1 according to the present embodiment is a system for presenting a user's favorite copyrighted work to the user terminal 20. In the following explanation, the case where the work is a painting belonging to the field of art will be described as an example. The work is not limited to paintings, and is not limited to the field of art. In the following description, the same parts are designated by the same reference numerals. Their names and functions are the same. Therefore, the detailed description of them will not be repeated.

<1. Overall configuration of information processing system 1>
FIG. 1 is a block diagram showing an overall configuration of the information processing system 1. As shown in FIG. 1, the information processing system 1 includes an information processing device 10, a user terminal 20, a radio base station 30, and a network 40. The information processing apparatus 10 and the user terminal 20 are connected to each other so as to be able to communicate with each other via the network 40. The network 40 is composed of a wired or wireless network. The information processing device 10 and the user terminal 20 are connected to the network 40 by using an arbitrary wired or wireless communication standard. In the present disclosure, the case where the information processing apparatus 10 is connected to the network 40 by wire and the user terminal 20 is wirelessly connected to the network 40 via the wireless base station 30 will be described as an example. The configuration is not limited to this.

<2. Configuration of information processing device 10>
Next, the configuration of the information processing apparatus 10 will be described with reference to FIGS. 2 and 3. The information processing device 10 is a device that executes a learning process for learning a user's favorite image, a display process for presenting a user's favorite painting, and the like. The information processing device 10 is, for example, a laptop computer, a rack-mounted computer, a tower-type computer, or the like. The information processing device 10 may be composed of a plurality of information processing devices 10 and the like.

FIG. 2 is a diagram showing the configuration of the information processing apparatus 10. As shown in FIG. 2, the information processing apparatus 10 includes a processor 11, a memory 12, a storage 13, a communication IF 14, and an input / output IF 15.

The processor 11 is hardware for executing an instruction set described in a program, and is composed of an arithmetic unit, registers, peripheral circuits, and the like.

The memory 12 is for temporarily storing a program, data processed by the program, or the like, and is, for example, a volatile memory such as a DRAM (Dynamic Random Access Memory).

The storage 13 is a storage device for storing data, and is, for example, a flash memory, an HDD (Hard Disc Drive), or an SSD (Solid State Drive).

The communication IF 14 is an interface for inputting / outputting signals because the information processing device 10 communicates with an external device.

The input / output IF15 functions as an interface with an input device (for example, a pointing device such as a mouse, a keyboard) for receiving an input operation and an output device (display, speaker, etc.) for presenting information.

FIG. 3 is a block diagram showing a functional configuration of the information processing apparatus 10. As shown in FIG. 3, the information processing apparatus 10 includes a communication unit 110, a storage unit 120, and a control unit 130.

The communication unit 110 performs processing for the information processing device 10 to communicate with an external device.

The storage unit 120 stores data and programs used by the information processing device 10. The storage unit 120 stores the user DB 121, the painting DB 122, the model DB 123, and the like.

The user DB 121 is a database that holds information about each user. FIG. 4 is a diagram showing an example of the data structure of the user DB 121. As shown in FIG. 4, the record of the user DB 121 includes an item "user ID", an item "preference", an item "browsing history", an item "favorite", and the like.

The item "user ID" is information that identifies the user.

The item "preference" is information indicating the user's preference. For example, the user class described later.

The item "browsing history" is a history of paintings browsed by the user.

The item "favorite" is information indicating a painting or author registered as a favorite by the user.

The painting DB 122 is a database that holds information about paintings. FIG. 5 is a diagram showing an example of the data structure of the painting DB 122. The painting DB 122 also includes paintings by authors who are not well known in the field of art. This is to present the painting of an unfamiliar author or the unfamiliar author himself to the user in the information processing system 1 of the present disclosure. A well-known author is an author who is widely known among consumers in the field to which the work belongs. For example, if the author is a painter, a painter who has a contract with a gallery, a painter who has been featured in the media, a painter who has been known to consumers by exhibiting at solo exhibitions, group exhibitions, etc., has received awards. It corresponds to a well-known author such as a painter. The same applies to well-known works. However, the author of a well-known work is not always well-known. This makes it possible to support unfamiliar authors and reach unknown works that users cannot know by ordinary methods (gallery, gallery, exhibition, etc.). As shown in FIG. 5, the record of the painting DB 122 includes the item "author ID", the item "painting ID", the item "painting data", and the like.

The item "author ID" is information that identifies the author.

The item "painting ID" is information for identifying a painting.

The item "painting data" is data related to painting. The painting data is, for example, image data when the painting is imaged.

In the control unit 130, the processor 11 of the information processing device 10 performs processing according to a program, so that the reception control unit 131, the transmission control unit 132, the first output unit 133, the learning unit 134, the selection unit 135, and the second output unit 136 , The function shown in the registration unit 137, the input unit 138, and the notification unit 139 is exhibited.

The reception control unit 131 controls the process in which the information processing device 10 receives a signal from an external device according to a communication protocol. Specifically, the reception control unit 131 receives various information from the user terminal 20. For example, the reception control unit 131 receives the answer described later from the user terminal 20.

The transmission control unit 132 controls a process in which the information processing device 10 transmits a signal to an external device according to a communication protocol. Specifically, the transmission control unit 132 transmits predetermined information to the user terminal 20. For example, the transmission control unit 132 transmits the image data of the painting, the image data of the painting selected by the selection unit 135, and the like to the user terminal 20.

The first output unit 133 outputs a painting for learning the user's preference to the user. Specifically, the first output unit 133 outputs a screen for displaying a painting for learning the user's preference. At this time, the first output unit 133 outputs the painting designated by the learning unit 134. The first output unit 133 outputs a painting designated by the learning unit 134 each time or in advance. The order of the paintings designated by the learning unit 134 and output by the first output unit 133 is such that the accuracy of learning the user's preference is improved. The first output unit 133 causes the transmission control unit 132 to transmit the image data to the user terminal 20. As a result, the painting is displayed on the user terminal 20.

The first output unit 133 receives input of a subjective answer about the output painting to the user terminal 20. The subjective impression is, for example, the user's subjective impression such as the emotion that the user has toward the image, the atmosphere that the user feels, the intuition, and the good or bad. In this disclosure, the case of using the emotion of the user will be described as an example. In this case, the first output unit 133 causes the user terminal 20 to display the user's emotions as a subjective answer so that they can be input. To display the user's emotions so that they can be input, for example, the following methods (1) to (3) can be adopted.
(1) Prepare multiple options related to the user's emotions and display them in a selectable manner.
(2) A meter showing the degree of emotion of the user is displayed, and the degree of emotion can be specified by operating the meter.
(3) Display a button that allows you to enter the degree of emotion according to the time you press it.

For the user's emotion, for example, a four-stage index of Happy / Relaxed / Inspired / Not Internet can be adopted. Further, it may be configured to include Other (others). In this case, the painting that the user feels Happy can be regarded as the image that the user prefers most. By using such a user's subjective answer, the user's preference can be recognized more accurately. With such a configuration, it is possible to continuously input the evaluation without burdening the user and without getting bored. In particular, by using such a GUI, the user's intuitive and cognitive load can be minimized.

6 to 9 show an example of a screen displayed on the user terminal 20. FIG. 6 is an example of the case of (1). As shown in FIG. 6, the screen 140 includes a painting display unit 141, and buttons 142 to 146. The painting display unit 141 is an area for displaying a painting. Buttons 142 to 146 are user emotional choices. In the example of FIG. 6, buttons 142 to 144 are buttons corresponding to Happy, Relaxed, and Inspired. Button 145 indicates Not internet, and button 146 indicates Other. The first output unit 133 configures the screen 140 so that a user's answer is received when any one of the buttons 142 to 146 is pressed. In particular, for buttons that are strongly influenced by the user's emotions, usability can be improved by making the buttons larger in size than other buttons.

7 and 8 show an example of the case of (2). As shown in FIG. 7, the screen 150 includes a painting display unit 141 and a slide input unit 151. The hand portion 152 indicates the user's hand and is not included in the screen 150. The slide input unit 151 can input the strength of the user's emotions from Not interested to Very interested by sliding the hand unit 152. Further, as shown in FIG. 8, the screen 160 includes a painting display unit 141 and a slide input unit 161. The hand portion 152 is the same as in FIG. 7. By operating the adjustment unit 162 by the hand unit 152, the slide input unit 161 can input the emotional strength of the user from Not intersted to Very intersted. A linear meter such as the slide input unit 151 or the slide input unit 161 accepts the input of the user's emotional strength at a position arbitrarily stopped by the user. With such a configuration, it is possible to obtain an answer so that the user can input easily without imposing a burden on the user.

FIG. 9 shows an example of the case of (3). As shown in FIG. 9, the screen 170 includes a painting display unit 141 and an input display unit 171. The input display unit 171 includes a button unit 172 and a gauge unit 173. The hand portion 152 is the same as in FIG. 7. The input display unit 171 is configured so that the gauge of the gauge unit 173 accumulates while the button unit 172 is pressed. By using a GUI such as the input display unit 171, it is possible to obtain an answer so that the user can input easily without imposing a burden on the user.

The learning unit 134 learns the user's preference. Specifically, the learning unit 134 first accepts input of a subjective answer about the output work from the user. Specifically, the learning unit 134 receives the answer received from the user terminal 20 by the reception control unit 131. The learning unit 134 then determines the painting to be output by the first output unit 133 based on the received answer.

The learning unit 134 repeats outputting the copyrighted work by the first output unit 133 and accepting the input of the answer a predetermined number of times. The predetermined number of times is, for example, 10 times. In this case, the painting is displayed to the user and the input of the answer is accepted 10 times.

Next, the learning unit 134 learns the user's preference. Specifically, the learning unit 134 inputs in advance the order of the output paintings, the output paintings, the answers to the paintings, and the answers, so as to output the first vector showing the tendency of the user's preference in advance. The user's preference is learned using the learned first model. The first vector is information indicating a tendency of user's preference. The first vector is, for example, information such as a vector, a matrix, a function, etc., which are composed of a plurality of elements indicating a user's preference. The learning unit 134 stores the second vector of the user in the user DB 121.

The learning unit 134 may relearn the user's preference at a predetermined timing. This is to cope with the possibility that the user's preference may change. In this case, the learning unit 134 can set the predetermined number of times of repeating the output of the copyrighted work by the first output unit 133 and the acceptance of the input of the answer to be less than the first time. Since the user's preference does not change significantly, it is possible to learn with a small number of sheets and reduce the burden on the user at the time of re-learning.

The learning unit 134 can be configured to have a different screen output by the first output unit 133 depending on the learning scene. For example, the learning unit 134 causes the first output unit 133 to output the example of FIG. 6 when learning the user's preference. The learning unit 134 causes the first output unit 133 to output any example of FIGS. 7 to 9 when re-learning the user's preference. With such a configuration, first, the user's preference is accurately learned by the five-step learning, and then the re-learning is performed by the continuous value of the two indexes that does not impose a load on the user. As a result, it is possible to accurately learn the user's preference without imposing a burden on the user.

Further, the learning unit 134 outputs the second vector, which is a user class indicating the tendency of preference to which the user belongs, by inputting the order of the output paintings, the output paintings, the answers to the paintings, and the answers. It may be configured to learn the user's preference by using the second model learned in advance. The second vector is information indicating a tendency of user's preference classified in advance. The second vector is, for example, information such as a vector, a matrix, a function, etc., which are composed of a plurality of elements for classifying the user's preference. The learning unit 134 stores the second vector of the user in the user DB 121.

Further, the learning unit 134 may be configured to learn the first vector and the second vector as the user's preference.

The learning unit 134 learns the first model in advance so as to output the first vector showing the tendency of the user's preference by using the painting and the answer as teacher data. At this time, the first vector user class output by the first model may differ depending on the order in which the paintings are output. Therefore, the learning unit 134 determines the order of the paintings to be output so that the first vector output by the first model is closest to the tendency of the user's preference. As a method for determining the order, for example, a method can be adopted in which a score indicating that the first vector output by the first model is close to the tendency of the user's preference is obtained for each image and determined. The learning unit 134 uses a set of a plurality of paintings, a plurality of answers, and the order in which the paintings are output for the teacher data, and the first model, the paintings output by the first output unit 133, and the order thereof. To learn. Using a plurality of sets, it is possible to verify whether or not the first vector output by the first model is close to the tendency of the user's preference according to the order of the output paintings. As the order learning method, it is possible to adopt the above-mentioned score for each image, the above-mentioned score for each combination of images to be output, and the like. The order may be different depending on the answer.

As the first model, any model such as a neural network can be used. As a learning method, for example, an inverse error propagation method or the like can be used. The first model, the painting to be output, and the order may be learned at the same time. In this case, the parameters of the first model, the painting output by the first output unit 133, and the order thereof are learned so that the objective function for the first vector and the objective function for the order are maximized at the same time. At this time, the learning unit 134 may be configured to learn in such an order that the user does not lose interest. In this case, it is sufficient to collect data from a plurality of users in advance as to what order of paintings loses interest in the answer.

As the painting used for learning by the learning unit 134 and the painting output by the first output unit 133, those stored in the painting DB 122 in advance are used. The painting used for learning may be configured to use one stored in an external database server. The learning unit 134 stores the learned parameters of the first model, the paintings output by the first output unit 133, and their order in the model DB 123.

Further, the learning unit 134 learns in advance the second model so as to output the second vector, which is a user class indicating the tendency of preference to which the user belongs, using the painting and the answer as teacher data. At this time, the second vector output by the second model may differ depending on the order in which the paintings are output. Therefore, the learning unit 134 determines the order of the paintings to be output so that the second vector output by the second model is closest to the tendency of the user's preference. Therefore, the learning unit 134 uses a set of a plurality of paintings, a plurality of answers, and the order in which the paintings are output for the teacher data, the second model, the paintings output by the first output unit 133, and the paintings thereof. Learn the order and. As the second model, any model such as a neural network can be used. As a learning method, for example, an inverse error propagation method or the like can be used. The second model, the painting to be output, and the order may be learned at the same time. In this case, the parameters of the second model, the painting output by the first output unit 133, and the order thereof are learned so that the objective function for the second vector and the objective function for the order are maximized at the same time. As the painting used for learning by the learning unit 134 and the painting output by the first output unit 133, those stored in the painting DB 122 in advance are used. The painting used for learning may be configured to use one stored in an external database server. The learning unit 134 stores the parameters of the learned second model, the paintings output by the first output unit 133, and their order in the model DB 123.

Further, the learning unit 134 relearns the paintings output by the first output unit 133 and their order by using the answer received from the user terminal 20 after the output by the second output unit 136.

The selection unit 135 selects a painting of the user's preference from a set of paintings including a painting of an author who is not well known in the art field to which the painting belongs, based on the user's preference learned in advance. Specifically, the selection unit 135 uses a third model that outputs a painting of the user's preference when at least one of the first vector and the second vector, which is the user's preference learned, is input, and the user's preference is used. Select a painting from the painting DB 122. The third model is a model in which a plurality of paintings close to the user's preference are selected from the paintings included in the painting DB 122 based on at least one of the first vector and the second vector.

For example, the selection unit 135 selects a painting having a score representing a user's preference of a predetermined value or more from a plurality of paintings selected by the third model. As a general rule, the number of paintings selected by the selection unit 135 is one. As an exception, if the user permits it in advance, or if there is a painting with the same score, etc., it is defined. Further, the selection unit 135 may be configured to weight the paintings of unknown authors so as to preferentially select the paintings of unknown authors.

Further, the selection unit 135 selects the user's favorite painting from the painting DB 122 by further using the fourth model that outputs the features of the painting that the user does not like when inputting at least one of the first vector and the second vector. It can be configured. The painting selected by the fourth model should not be presented to the user. Therefore, the selection unit 135 can use a method such as selecting a painting using the third model after excluding the plurality of paintings selected by the fourth model from the candidates in advance.

The second output unit 136 outputs the selected painting to the user. Specifically, the second output unit 136 outputs a screen for displaying the painting selected by the selection unit 135. First, the second output unit 136 acquires the image data of the painting and the information about the author of the painting for each of the selected paintings from the painting DB 122. Next, the second output unit 136 generates a screen including image data of the painting and information about the author of the painting. The second output unit 136 causes the transmission control unit 132 to transmit the screen to the user terminal 20. As a result, the painting is displayed on the user terminal 20. The second output unit 136 may be configured to cause the transmission control unit 132 to transmit image data for each of the selected paintings and information about the author to the user terminal 20 without generating the screen. In this case, the user terminal 20 may be configured to generate the screen and display it to the user.

Here, the selection unit 135 and the second output unit 136 can be configured to be executed at a predetermined timing. For example, by selecting a painting on a regular basis such as daily, weekly, or monthly, and presenting the selected painting to the user, the user can appreciate the favorite painting. In particular, works of art such as paintings and sculptures are not frequently considered by users. Therefore, the painting is presented to the user at a predetermined timing that the user does not feel uncomfortable. This also leads to the user considering purchasing a painting. Users can also purchase and invest in paintings by authors who are not well known. The painting may be presented to such a user frequently. The predetermined timing may be configured to be set by the user.

Further, the number of paintings selected by the selection unit 135 can always be less than or equal to a predetermined number. For example, the number may be 5 to 10 or less. In this case, the number of art that the user can view per day is limited. Therefore, the user can be motivated to check the image every day without consuming the content at once. In addition, by keeping the speed of content consumption constant, it is possible to prevent the time for visually recognizing each work of art from diminishing. Due to such restrictions, it takes a certain amount of time for the results selected by the user to be accumulated. For this reason, it is still important to optimize the order in which images are presented to the user. In addition, since a small number does not burden the user and the degree of concentration on art increases, it is possible to increase the possibility that an unknown artist can view his / her own art.

Registration unit 137 accepts registrations of unfamiliar authors. Specifically, the registration unit 137 accepts registrations of authors other than authors, such as authors who already belong to the gallery and authors who are well-known or well-known in the field of art. For example, in a specific area (for example, a specific country, region, other administrative division, etc.), the well-knownness is determined mainly by consumers, business associates, etc. in that field. Then, the registration unit 137 stores the author and information related to the author in the storage unit 120.

Information related to the author includes information indicating that it is not well known, and other information is the author's name, contact information, the author's work, etc. Even an unfamiliar author can solve the problem that it is difficult to match with a user who likes his painting. In this way, by registering an unfamiliar author, an unknown author is supported. The registration unit 137 does not exclude the registration of authors other than unknown authors. That is, for such authors, the degree of familiarity, information about the gallery to which they belong, etc. are included in the information about the authors.

Further, the registration unit 137 accepts the favorite registration of the author or the painting output by the second output unit 136 from the user. The registration unit 137 registers the received author or painting as a favorite by storing it in the user DB 121.

The input unit 138 accepts the input of the painting from the registered author. Specifically, the input unit 138 stores the received image data of the painting in the painting DB 122 in association with the author.

When the input unit 138 receives the input of the painting from the author registered by the registration unit 137, the notification unit 139 notifies the user of the accepted work. Specifically, when a painting is newly input from the author registered as a favorite, the notification unit 139 notifies the user who has registered the author as a favorite that the new painting has been registered. Upon receiving the display request from the user terminal 20, the notification unit 139 causes the second output unit 136 to output the new painting to the user. When the user terminal 20 receives the notification, the user terminal 20 displays a screen for accepting the display request from the user. It should be noted that the user may be configured to be configurable whether or not to receive the notification by the notification unit 139. Further, the notification unit 139 may be configured to include image data of a new painting in the notification. In this case, the user terminal 20 may be configured to notify the notification as a push notification including image data.

<3. Configuration of user terminal 20>
FIG. 10 is a diagram showing the configuration of the user terminal 20. The user terminal 20 is a device that presents a painting output from the information processing device 10 to the user. The user terminal 20 is, for example, a computer such as a laptop personal computer or a smartphone.

The user terminal 20 includes a processor 21, a memory 22, a storage 23, a communication IF 24, and an input / output IF 25. The processor 21, the memory 22, the storage 23, the communication IF 24, and the input / output IF 25 have the same configurations as the processor 11, the memory 12, the storage 13, the communication IF 14, and the input / output IF 15, respectively.

FIG. 11 is a block diagram showing a functional configuration of the user terminal 20. As shown in FIG. 11, the user terminal 20 includes a communication unit 210, a storage unit 220, and a control unit 230.

The communication unit 210 performs processing for the user terminal 20 to communicate with an external device.

The storage unit 220 stores data and programs used by the user terminal 20.

The control unit 230 exerts the functions shown in the reception control unit 231, the transmission control unit 232, the display unit 233, and the input unit 234 when the processor 31 of the user terminal 20 performs processing according to the program.

The reception control unit 231 controls a process in which the user terminal 20 receives a signal from an external device according to a communication protocol. Specifically, the reception control unit 231 receives various information from the information processing device 10. More specifically, the reception control unit 231 receives image data, a screen, and the like from the information processing device 10.

The transmission control unit 232 controls a process in which the user terminal 20 transmits a signal to an external device according to a communication protocol. Specifically, the transmission control unit 232 transmits predetermined information to the information processing apparatus 10. More specifically, the transmission control unit 232 transmits the user's subjective response to the information processing apparatus 10.

The display unit 233 displays the image output by the first output unit 133. Specifically, when the reception control unit 231 receives the image data output by the first output unit 133 from the information processing device 10, the display unit 233 displays the image data. At this time, the display unit 233 displays the image data so that the user's subjective answer can be input as the subjective answer.

Further, the display unit 233 displays the image output by the second output unit 136. Specifically, when the reception control unit 231 receives the screen output by the second output unit 136 from the information processing device 10, the display unit 233 displays the screen. At this time, the display unit 233 displays the screen so that the user's subjective answer can be input as the subjective answer.

Further, when the reception control unit 231 receives the notification from the information processing apparatus 10, the display unit 233 displays the content of the notification. When the function of the user terminal 20 of the present disclosure is implemented in an application installed on the user terminal 20, the notification may be displayed to the user by push notification. In this case, the display unit 233 may be configured to include the image data in the push notification and display it.

The input unit 234 accepts the input of the user's subjective answer from the user. When the input unit 234 accepts the input of the subjective answer, the transmission control unit 232 causes the transmission control unit 232 to transmit the answer to the information processing apparatus 10.

<4. Operation>
Hereinafter, each process in the information processing system 1 will be described with reference to the drawings. FIG. 12 is a flowchart showing an example of a flow of performing registration processing by the information processing apparatus 10. The registration process is executed when a painting is input by the author.

In step S101, the input of the painting is accepted from the registered author.

In step S102, the input unit 138 stores the received image data of the painting in the painting DB 122 in association with the author.

In step S103, the notification unit 139 determines whether or not a painting is newly input from the author registered as a favorite.

If no painting has been input from the author registered as a favorite (NO in step S103 above), the process ends.

On the other hand, when a painting is input from the author registered as a favorite (YES in step S103 above), in step S104, the notification unit 139 indicates that a new painting has been registered for the user who has registered the author as a favorite. Is notified and the process ends.

FIG. 13 is a flowchart showing an example of a flow of learning processing by the information processing apparatus 10.

In step S201, the first output unit 133 outputs to the user a painting for learning the user's preference. Specifically, the first output unit 133 causes the transmission control unit 132 to transmit the image data to the user terminal 20.

In step S202, the reception control unit 131 receives an answer from the user terminal 20.

In step S203, the learning unit 134 determines whether the step S201 and the step S202 are repeated a predetermined number of times.

If the process has not been repeated a predetermined number of times (NO in step S203), the learning unit 134 next specifies the painting to be output in step S201, and returns to step S201.

On the other hand, when the process is repeated a predetermined number of times (YES in step S203 above), in step S204, the learning unit 134 learns the user's preference.

In step S205, the learning unit 134 stores the user's preference in the user DB 121.

FIG. 14 is a flowchart showing an example of a flow of performing display processing by the information processing apparatus 10. The display process is started at a predetermined timing.

In step S301, the selection unit 135 selects a painting of the user's preference from a set of paintings including a painting of an author who is not well known in the art field to which the painting belongs, based on the user's preference learned in advance. do.

In step S302, the second output unit 136 outputs the selected painting to the user. Specifically, the second output unit 136 causes the transmission control unit 132 to transmit the screen for displaying the painting selected in step S301 to the user terminal 20.

In step S303, the learning unit 134 relearns the user's preference. Specifically, the answer is received from the user terminal 20, and the user's preference is learned based on the selected painting and the answer.

As described above, according to the program according to the present disclosure, the first step of learning the user's preference in advance in the information processing apparatus including the processor, and the user's preference based on the user's preference learned in advance. Perform a second step of selecting a work from a set of works including works of authors who are not well known in the field to which the work belongs, and a third step of outputting the selected work to the user. Thereby, even if the work preferred by the user is the work of an unknown author, it can be presented to the user.

Further, with the conventional technique, even if a work of an unknown author can be found, there is a problem that it is difficult to continuously purchase the work of the author of the work. In addition, there is a case where a user wants to support an author who creates a favorite work in order to obtain a favorite work, but there is a problem that it is difficult to confirm a method for supporting the work. Since this disclosure also presents information about an unfamiliar author, it is possible to match the user with the work of an unfamiliar author. Then, it can be matched with the author who created the work. Therefore, it is possible to support the activities of the author and create a virtuous cycle between the user and the author.

In addition, there was a problem that the user did not know the type of copyrighted work that relaxed or enlightened himself. In this disclosure, preference is learned based on the subjective response of the user. In particular, the user's preference can be learned by the options of Relaxed and Inspired. Therefore, by presenting a favorite work based on these viewpoints, the user can present the work according to the sensibility. Specifically, the target to be learned above can learn not only the user's preference for likes and dislikes of the copyrighted work, but also the user's preference according to the emotion of the input answer. For example, if the answer is Relaxed, the user feels relaxed with this work, so they can learn the characteristics of the work they prefer when they want to relax. In this way, by learning the user's preference according to the emotion of the answer, by presenting the favorite work based on the above viewpoint, the user can present the copyrighted work according to the sensibility.

In addition, there is a service in which the author posts the copyrighted work and the user searches for the copyrighted work. In this service, copyrighted works with high evaluation are displayed as the top search. However, it is not always highly evaluated by all users, and it is not easy to search for a user's favorite copyrighted work. For this reason, there is a problem that it is troublesome because it is necessary to check various search methods and a large number of copyrighted works until the user arrives at a favorite copyrighted work. In the present disclosure, a user learns a user's favorite copyrighted work simply by inputting a subjective answer, and automatically presents the user's favorite copyrighted work. Therefore, the user can reach the favorite copyrighted work without imposing a burden on the user.

Also, in order to get a high evaluation, the author needs to appeal the goodness of the work by himself, but it is difficult to appeal depending on his name, so it is possible to find a person who likes his work. There was the problem that it was difficult. In this disclosure, even an unfamiliar author presents a user's favorite work to the user. Therefore, even an unfamiliar author can appeal to a user who likes his / her own work.

Although the embodiments related to the disclosure have been described above, these can be implemented in various other embodiments, and can be implemented by making various omissions, substitutions, and changes. These embodiments and modifications, as well as those omitted, replaced or modified, are included in the technical scope of the claims and the equivalent scope thereof.

For example, in the above disclosure, the case where the copyrighted work is a painting has been described as an example, but the present invention is not limited to this. The work may belong to another field of art, such as engraving, prints, illustrations, and graphic design. Further, the work may be a work belonging to the field of music, scholarship, or literary arts. In addition, the author is not limited to the creator of the work, but includes the creator, the person who has the right to the work, and the like.

In the case of paintings, it is normal for well-known authors to register in the gallery and sell the paintings there. Other paintings are basically not available. There is a site for registering paintings, but there are problems such as not showing what the user really likes, and not learning the taste in the first place. In addition, there is only one work of art such as paintings and sculptures. Therefore, the investment value is also included. This disclosure learns user preferences and selects anonymous works. For this reason, the techniques of the present disclosure are useful in supporting unfamiliar authors, especially in the arts field.

In the case of engraving, 3D data can be used instead of image data.

Further, in the present disclosure, the case where each database (for example, painting DB 122) is configured in the information processing apparatus 10 has been described as an example, but the present invention is not limited to this. Each database may be configured as a database existing outside the information processing apparatus 10.

Further, in the present disclosure, the first output unit 133 or the second output unit 136 of the information processing apparatus 10 is configured to generate a screen to be displayed to the user, but the present invention is not limited to this. The user terminal 20 may be configured to generate a screen to be displayed to the user.

<Additional notes>
The matters described in each of the above embodiments will be added below.

(Appendix 1) In the information processing apparatus (10) including the processor, the first step (S204) of learning the user's preference in advance and the user's favorite copyrighted work based on the user's preference learned in advance are described. The second step (S301) of selecting from a set of works including the works of authors who are not well known in the field to which the works belong, and the third step (S302) of outputting the selected works to the user are executed. Program to let you.

(Appendix 2) The first step is a fourth step (S201) of outputting a work for learning the user's preference to the user, and inputting a subjective answer about the work from the user. By executing the fifth step (S202) of acceptance, the fourth step, and the sixth step (S203) of repeating the fifth step a predetermined number of times, the user's preference is learned in advance (Appendix 1). The program described.

(Appendix 3) The second step is the program described in (Appendix 1) or (Appendix 2) in which the copyrighted work of the unknown author is selected from the set of the copyrighted works.

(Appendix 4) The third step is the program according to any one of (Appendix 1) to (Appendix 3) that outputs information about the author of the selected work.

(Appendix 5) The seventh step of accepting the registration of the unknown author and the eighth step (S102) of accepting the input of the work from the registered author are executed (Appendix 1) to (Appendix 4). The program described in any of.

(Appendix 6) The 9th step of accepting the favorite registration of the author output by the 3rd step from the user and the input of the copyrighted work from the author registered by the 9th step are accepted. The program according to the tenth step (S104) for notifying the user of the work and the execution (Appendix 5).

(Appendix 7) A work output in the fourth step repeated in the sixth step based on the work output in the fourth step and the favorite work of the user selected in the second step. The program according to any one of (Appendix 2) to (Appendix 6) for executing the eleventh step of learning the order of.

(Appendix 8) In the fourth step, each time the sixth step is repeated, the output works are changed so as to output the works in an order that enhances the accuracy of learning the user's preference ((Appendix 8). Appendix 7) The program described.

(Appendix 9) In the second step, the user is selected from the set of copyrighted works by using the answer and a first model that outputs a first vector showing a tendency of preference by inputting the answer. The program according to any one of (Appendix 2) to (Appendix 8) for selecting a favorite work.

(Appendix 10) The second step uses the answer and a second model that outputs a second vector, which is a user class indicating a tendency of preference to which the user belongs, by inputting the answer. The program according to any one of (Appendix 2) to (Appendix 8) for selecting a favorite work of the user from a set of objects.

(Appendix 11) In the second step, the user class is obtained based on the answer and the second model, and when the obtained first vector is input, the user's favorite painting is output in advance. The program according to (Appendix 9), which selects a work of an unknown author from a set of the works by using the third model.

(Appendix 12) In the second step, when the third model and the first vector are input, a fourth model trained in advance so as to output a fourth vector showing the characteristics of the copyrighted work that the user does not like is output. The program according to (Appendix 11), which selects a favorite work of the user from a set of the works using and.

(Appendix 13) The program according to any one of (Appendix 2) to (Appendix 12), which accepts input from the user in the fifth step with a subjective evaluation as an answer to the copyrighted work output by the fourth step.

(Appendix 14) The program according to (Appendix 13), wherein the subjective evaluation is the emotion held by the user with respect to the work output by the fourth step.

(Appendix 15) The program according to (Appendix 14) that displays the emotions of the user in a selectable manner in the fourth step.

(Appendix 16) The program according to (Appendix 14), in which, in the fourth step, a meter indicating the degree of emotion of the user is displayed, and the degree of emotion can be specified by operating the meter (Appendix 14).

(Appendix 17) Based on the first step (S204) of learning the user's preference in advance and the user's preference learned in advance, the author's favorite work is not well known in the field to which the work belongs. An information processing device that executes a second step (S301) of selecting from a set of copyrighted works including a copyrighted work and a third step (S302) of outputting the selected copyrighted work to the user.

(Appendix 18) Based on the first step (S204) of learning the user's preference in advance and the user's preference learned in advance, the author's favorite work is not well known in the field to which the work belongs. A method of executing a second step (S301) of selecting from a set of works including a work, and a third step (S302) of outputting the selected work to the user.

(Appendix 19) A step (S204) of preliminarily learning a user's preference in an information processing apparatus including a processor, and a step (S301) of selecting a pre-learned user's favorite work from a set of works. In the learning step, a step (S201) of outputting a literary work for learning the user's preference to the user and a step of receiving a subjective answer about the literary work from the user. (S202), a program for executing the step (S203) of repeating the output step and the accepting step a predetermined number of times.

1 information processing system, 10 information processing equipment, 11 processor, 12 memory, 13 storage, 14 communication IF, 15 input / output IF, 20 user terminal, 21 processor, 22 memory, 23 storage, 24 communication IF, 25 input / output IF, 30 wireless base station, 31 processor, 40 network, 110 communication unit, 120 storage unit, 121 user DB, 122 painting DB, 123 model DB, 130 control unit, 131 reception control unit, 132 transmission control unit, 133 first output unit. , 134 learning unit, 135 selection unit, 136 second output unit, 137 registration unit, 138 input unit, 139 notification unit, 140 screen, 141 painting display unit, 142 button, 144 button, 145 button, 146 button, 150 screen, 151 slide input unit, 152 hand unit, 160 screen, 161 slide input unit, 162 adjustment unit, 170 screen, 171 input display unit, 172 button unit, 173 gauge unit, 210 communication unit, 220 storage unit, 230 control unit, 231 Reception control unit, 232 transmission control unit, 233 display unit, 234 input unit.

Claims (14)

For information processing equipment including processors
The first step of outputting a copyrighted work to the user for learning the user's preference,
The second step of accepting the input of the answer from the user with the emotions other than the preference that the user has for the output work as an answer.
A step of repeating the first step and the second step a predetermined number of times,
A step of learning the user's preference according to the emotion of the answer by using a plurality of pairs of the output work and the answer to the output work, and
A step of selecting a copyrighted work of the user's preference from a set of copyrighted works based on the learned preference of the user.
Steps to output the selected copyrighted work to the user,
A program to execute. In the second step, the answer is to accept happiness, relaxation, or stimulating input.
In the first step, the answer is selectively displayed together with the work.
The program according to claim 1. The third step to relearn the user's preferences,
A step of selecting a copyrighted work of the user's preference from a set of the copyrighted works based on the relearned user's preference.
To execute further,
The third step is
A meter that indicates to the user a work for re-learning the user's preference and a predetermined degree of emotion that the user has for the output work, and is a meter that can be operated by the user. Steps to display and
A step of receiving the input of the answer from the user with the predetermined degree of emotion as the answer by the user operating the meter.
A step of re-learning the user's preference using the output work and the answer to the output work, and
The program according to claim 2. The program according to any one of claims 1 to 3, which outputs information about the author of the selected work together with the selected work in the step of outputting the selected work to the user. Steps to accept the registration of authors and
Steps to accept input of copyrighted works from registered authors,
The program according to any one of claims 1 to 4. A step of accepting a favorite registration for the author output by the step of outputting the selected work to the user from the user, and a step of accepting the favorite registration.
When the input of the copyrighted work is received from the author registered by the step of accepting the favorite registration, the step of notifying the user of the accepted copyrighted work and the step of notifying the user.
The program according to claim 5. Based on the copyrighted work output in the first step and the favorite copyrighted work of the user selected in the selected step, the order of the copyrighted works output in the first step repeated by the repeating step is learned. The program according to any one of claims 1 to 6, wherein the step is executed. The seventh step is described in claim 7, wherein the output works are changed so that the works are output in an order that enhances the accuracy of learning the user's preference each time the repeated steps are repeated. program. The selection step is a work of the user's preference from the set of works using the answer and a first model that outputs a first vector indicating a tendency of preference by inputting the answer. The program according to any one of claims 1 to 8, which selects a product. The selection step is from the set of works using the answer and a second model that outputs a second vector, which is a user class indicating the tendency of the user's preference by inputting the answer. The program according to any one of claims 1 to 8, wherein the user's favorite copyrighted work is selected. The selection step is a third pre-learned step to obtain the user class based on the answer and the second model, input the obtained first vector, and output the user's favorite painting. The program according to claim 10, wherein a work of the author is selected from a set of the works using a model. The selection step uses the third model and, upon input of the first vector, a fourth model pre-learned to output a fourth vector showing features of the work that the user does not like. The program according to claim 11, wherein the user's favorite copyrighted work is selected from the set of copyrighted works. The first step of outputting a copyrighted work to the user for learning the user's preference,
The second step of accepting the input of the answer from the user with the emotions other than the preference that the user has for the output work as an answer.
A step of repeating the first step and the second step a predetermined number of times,
A step of learning the user's preference according to the emotion of the answer by using a plurality of pairs of the output work and the answer to the output work, and
A step of selecting a copyrighted work of the user's preference from a set of copyrighted works based on the learned preference of the user.
Steps to output the selected copyrighted work to the user,
Information processing device that executes. The computer
The first step of outputting a copyrighted work to the user for learning the user's preference,
The second step of accepting the input of the answer from the user with the emotions other than the preference that the user has for the output work as an answer.
A step of repeating the first step and the second step a predetermined number of times,
A step of learning the user's preference according to the emotion of the answer by using a plurality of pairs of the output work and the answer to the output work, and
A step of selecting a copyrighted work of the user's preference from a set of copyrighted works based on the learned preference of the user.
Steps to output the selected copyrighted work to the user,
How to run.

Images