JP7832802B2 - Content generation device, content generation method, and content generation program - Google Patents

Description

This invention relates to a content generation device, a content generation method, and a content generation program.

Traditionally, there have been dating/marriage matching services and services that offer experiences to individuals (for example, online services teaching cooking or English conversation).

AI movie posters, [online], [searched December 16, 2021], Internet <URL: https://noahveltman.com/aimovies/> VQGAN+CLIP - How does it work?, [online], [searched December 16, 2021], Internet <URL: https://alexasteinbruck.medium.com/vqgan-clip-how-does-it-work-210a5dca5e52>

In the aforementioned services, when users choose a partner, they only have access to basic information about that person; they cannot see their inner self. This has led to the problem that it is difficult for users to choose a partner. This invention was made in view of the above, and aims to make it easier for users to understand the inner self of their partner in matching services and the like.

To solve the aforementioned problems, the present invention is characterized by comprising: a user information acquisition unit that acquires user information of a target user and user information of a viewer; a content generation unit that identifies information common to the user information of the target user and the user information of the viewer, and generates an image representing the image of the common information using a learning model that generates an image representing the image of the text from the text contained in the identified information; and a provision unit that provides the image to the viewer's terminal device.

According to one embodiment of the system, users can more easily understand the inner thoughts and feelings of others in matching services, etc.

Figure 1 illustrates an example of the processing performed by a content generation device (server). Figure 2 shows an example of a system configuration including a server. Figure 3 shows an example of user information. Figure 4 is a flowchart showing an example of the steps a server will take. Figure 5 is a hardware configuration diagram showing an example of a computer that implements the functions of a content generation device.

The following describes in detail, with reference to the drawings, the embodiments for implementing the content generation device according to this application (hereinafter referred to as "embodiments"). However, the content generation device according to this application is not limited to the embodiments described below.

[Example of processing]
An example of the processing performed by the content generation device (server) 100 will be explained using Figure 1. The server 100 is, for example, a server that provides various information to users of a matching service. The server 100 stores user information for each user used in matching. The server 100 also generates content (for example, an image) that represents the impression associated with the user information, using a learning model that generates an image representing the image of the text from the text itself.

For example, as shown in Figure 1, when server 100 receives a request to view another user's information from the terminal device 10 of a browsing user (a user making a matching request), it obtains user information for both the browsing user and the other user. Then, server 100 generates content (e.g., an image) that reflects information common to both the browsing user and the other user.

For example, when server 100 obtains user information for the browsing user and other users (target users), it identifies common information from the obtained user information (e.g., common hobbies, common places visited, etc.). Next, server 100 inputs the text of the common information from the obtained user information (e.g., text indicating common hobbies, text indicating common places visited) into a learning model and generates an image that reflects the image of that text. Then, server 100 sends the generated image to the browsing user's terminal device.

For example, if the browsing user and other users share the hobbies of outdoor activities and reading, server 100 generates an image of someone reading while sitting around a campfire outdoors and sends it to the browsing user's terminal device. Similarly, if the browsing user and other users both visit the sea, server 100 generates an image of the sea and sends it to the browsing user's terminal device.

By doing this, server 100 can provide content that makes it easier for browsing users to understand commonalities with their potential matches (other users). As a result, browsing users can more easily select potential matches.

[Example Configuration]
Next, an example of a system configuration including a server 100 will be described using Figure 2. As shown in Figure 2, system 1 comprises terminal devices 10 and a server 100. In system 1, there may be multiple terminal devices 10 and multiple servers 100.

The terminal device 10 is, for example, an information processing device used by users of the matching service. For example, the terminal device 10 may be a desktop PC (Personal Computer), a notebook PC, a tablet device, a mobile phone, or a PDA (Personal Digital Assistant).

In the following text, terminal device 10 may be referred to as "user." That is, in the following text, "user" can be read as "terminal device 10." Furthermore, in the following text, when it is not necessary to distinguish between terminal devices 10 used by each user, it may be simply referred to as "terminal device 10."

The terminal device 10 and the server 100 are connected via a communication network (not shown) by wired or wireless means, enabling communication between them.

Server 100 is, for example, a server that provides various information to users of a matching service. For example, when Server 100 receives a request from a browsing user to view information of other users, it provides the browsing user with content that reflects user information common to both the browsing user and the other user. Server 100 comprises a communication unit 110, a storage unit 120, and a control unit 130.

(Regarding the Communications Department)
The communication unit 110 is implemented, for example, by a NIC (Network Interface Card). The communication unit 110 is connected to the communication network by wire or wireless connection and transmits and receives various types of information with the terminal device 10.

(Regarding the memory unit)
The memory unit 120 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or storage devices such as hard disks and optical discs. The memory unit 120 stores, for example, user information for each user. The memory unit 120 also stores the learning model (specifically, the parameters used by the learning model).

(Regarding user information)
User information refers to information about users of the matching service. As shown in Figure 3, for example, user information includes user attributes such as the username (or user identification information), gender, occupation, hobbies, place of origin, how they spend their holidays, and personality.

This user information may include, for example, user activity logs, as shown in Figure 3. Activity logs show, for example, when and what actions the user took (e.g., when and where they visited), when and what posts they made on social media, and when and what searches they performed using search engines. User activity logs may be managed together with the user's user information, or they may be managed separately.

(Regarding the learning model)
Returning to the explanation of Figure 2, the learning model is a model that generates content (for example, an image) that represents the image of the text from the text itself. This learning model is generated and updated by the model generation unit 131 (described later) of the control unit 130.

(Regarding the control unit)
The control unit 130 is a controller, and is realized by executing various programs (corresponding to an example of a content generation program) stored in the storage device inside the server 100 using RAM as a working area, for example, by a CPU (Central Processing Unit) or MPU (Micro Processing Unit). The control unit 130 is a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or FPGA (Field Programmable Gate Array).

The control unit 130 comprises a model generation unit 131, a request reception unit 132, a user information acquisition unit 133, a content generation unit 134, and a provision unit 135, and implements or executes the information processing functions and operations described below.

The internal configuration of the control unit 130 is not limited to the configuration shown in Figure 2; other configurations are also acceptable as long as they perform the information processing described later. For example, the model generation unit 131, the request reception unit 132, the user information acquisition unit 133, the content generation unit 134, and the provision unit 135 may each be mounted on a device separate from the server 100.

More specifically, the functions performed by the control unit 130 may be realized through the collaborative processing of servers performing the functions of the model generation unit 131, the request reception unit 132, the user information acquisition unit 133, the content generation unit 134, and the provision unit 135.

(Regarding the model generation section)
The model generation unit 131 generates a learning model that generates content (e.g., an image) representing the image of the text from the text itself. Known techniques may be used to generate this learning model.

Furthermore, when the model generation unit 131 generates a learning model, if there is a large amount of text with a particular impression, the learning model may be trained to produce images with colors corresponding to that impression. Alternatively, the model generation unit 131 may train the learning model to generate images that represent the shape of the object indicated by the text, or images that represent the impression of that object.

Furthermore, the model generation unit 131 may, for example, determine whether images (or colors) containing the shape of the object indicated by the text, or the shape representing the impression of the object, have been collected for each text using crowdsourcing, and then modify the learning model using the results of that determination.

(Regarding the Request Reception Department)
The request receiving unit 132 receives requests from the browsing user's terminal device 10 to view other users' information.

(Regarding the user information acquisition department)
The user information acquisition unit 133 acquires user information from the storage unit 120. For example, when the request reception unit 132 receives a request from the browsing user's terminal device 10 to view information of another user, the user information acquisition unit 133 acquires the browsing user's user information and the user information of the other user (the user whose information is to be viewed) from the storage unit 120.

Here, the user information of other users (users being viewed) acquired by the user information acquisition unit 133 is, for example, the user information of users who are estimated to be compatible with the viewing user based on the viewing user's user information (for example, users with a match rate of a predetermined value or higher).

Furthermore, if the viewing request from the viewing user's terminal device 10 includes information specifying the user to be viewed, the user information acquisition unit 133 may acquire the user information of the specified user to be viewed.

(Regarding the content generation section)
The content generation unit 134 generates content that represents the impression (image) of the user from the text included in the user's user information.

For example, the content generation unit 134 first identifies corresponding information between the user information of the viewing user and the user information of the target user, which are obtained by the user information acquisition unit 133. For instance, the content generation unit 134 identifies information such as common hobbies, preferences, places visited, posted content, and places of origin between the viewing user's information and the target user's information. The content generation unit 134 may also identify other information that is presumed to be compatible based on the user information of the viewing user and the target user.

Next, the content generation unit 134 inputs the text representing the identified information into the learning model and generates content (for example, an image).

In this case, the content generation unit 134 may generate content that reflects the match rate between the user information of the viewing user and the user information of the target user. For example, the content generation unit 134 may generate images with altered colors depending on the level of the match rate between the user information of the viewing user and the user information of the target user.

Furthermore, for example, the content generation unit 134 may generate images with colors that correspond to the user information trends of the target user.

Furthermore, when the content generation unit 134 generates the above content, it may combine the user information of the viewing user and the user information of the target user to generate content (for example, an image) that shows the relationship between the two users. For example, if the viewing user's user information includes a search history related to cooking, and the target user's user information includes information indicating that their hobby is camping, the content generation unit 134 may generate an image of someone cooking at a campsite.

Furthermore, the content generated by the content generation unit 134 may include not only images, but also music, or a combination of music and images. Additionally, the content generated by the content generation unit 134 may include information related to scent and taste (for example, keywords describing scent and taste).

(Regarding the provision department)
The provisioning unit 135 provides the content generated by the content generation unit 134 to the terminal device 10 that sent the viewing request. For example, the provisioning unit 135 transmits the image generated by the content generation unit 134 to the terminal device 10 that sent the viewing request via the communication network.

[Example of processing procedure]
Next, using Figure 4, an example of the procedure for processing performed by server 100 will be explained. It is assumed that server 100 has already generated a learning model.

First, when the request receiving unit 132 of the server 100 receives a request to view another user's information from the viewing user's terminal device 10 (S1), the user information acquisition unit 133 acquires the viewing user's user information and the user information of the other user (the user to be viewed) from the storage unit 120 (S2). Then, the content generation unit 134 identifies the corresponding information using the user information acquired in S2 (S3). For example, the content generation unit 134 identifies common user information between the viewing user's user information and the user information of the other user acquired in S2.

After S3, the content generation unit 134 inputs the text representing the information identified in S3 into the learning model and generates content that shows an image of the identified information (S4). For example, the content generation unit 134 inputs the text representing hobbies common to both the browsing user's user information and the user information of other users, identified in S3, into the learning model and generates an image representing hobbies common to both users.

After S4, the provisioning unit 135 provides the content generated in S4 to the viewing user's terminal device 10 (S5). For example, the provisioning unit 135 transmits an image generated in S4 that shows a common hobby of both users to the viewing user's terminal device 10.

By doing this, server 100 can provide content that makes it easier for browsing users to understand commonalities with their potential matches (browsing target users). As a result, browsing users can more easily select a matching partner.

[Other Embodiments]
Furthermore, the server 100 may generate and provide content that represents the impression of the target user (content that serves as a portrait of the target user) from the text contained in the user information of the target user. In this way, users can intuitively understand the inner self of the other party without having to look at the other party's user information in detail. As a result, users will find it easier to choose a matching partner.

Furthermore, the aforementioned System 1 may be applied to dating/marriage matching services and services that provide experiences between individuals (for example, online services teaching cooking or English conversation) when matching users with potential partners.

In this case, for example, when server 100 receives a request from a user of the above service to view information of other users, it retrieves user information of other users whose user information matches the above user's user information at a predetermined rate or higher.

The server 100 then identifies common user information for each pair of user information between the browsing user and other users with a match rate above a predetermined value, and generates content (e.g., images) using this identified user information. Afterward, the server 100 provides a list of the generated content to the browsing user's terminal device 10. The browsing user then selects a recipient from the content provided by the server 100 on the terminal device 10.

This approach allows users of matching services to intuitively understand commonalities with other users without having to examine their user information in detail. As a result, it becomes easier for users to choose a partner on matching services.

[Hardware Configuration]
Furthermore, the content generation device 100 according to the above-described embodiment can be realized by a computer 1000 having the configuration shown in Figure 5. The following explanation will use the content generation device 100 as an example. Figure 5 is a hardware configuration diagram showing an example of a computer 1000 that realizes the functions of the content generation device 100. The computer 1000 has a CPU 1100, RAM 1200, ROM (Read Only Memory) 1300, HDD (Hard Disk Drive) 1400, communication interface (I/F) 1500, input/output interface (I/F) 1600, and media interface (I/F) 1700.

The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs dependent on the computer 1000's hardware.

The HDD 1400 stores programs executed by the CPU 1100, as well as data used by such programs. The communication interface 1500 receives data from other devices via the network N and sends it to the CPU 1100, and transmits data generated by the CPU 1100 via the network N to other devices.

The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice, via the input/output interface 1600. The CPU 1100 acquires data from input devices via the input/output interface 1600. Furthermore, the CPU 1100 outputs the generated data to output devices via the input/output interface 1600.

The media interface 1700 reads programs or data stored in the recording medium 1800 and provides them to the CPU 1100 via the RAM 1200. The CPU 1100 loads such programs from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded programs. The recording medium 1800 can be, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical Disk), tape media, magnetic recording media, or semiconductor memory.

For example, when the computer 1000 functions as a content generation device 100 according to the embodiment, the CPU 1100 of the computer 1000 realizes the functions of the control unit 130 by executing a program loaded onto the RAM 1200. The HDD 1400 stores the data in the storage unit 120. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be obtained from other devices via a network N.

[others]
Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those illustrated; all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content remains consistent.

Furthermore, the terms "section," "module," and "unit" mentioned above can be reinterpreted as "means" or "circuits." For example, a decision unit can be reinterpreted as a decision means or a decision circuit.

[effect]
As described above, the content generation device 100 comprises a user information acquisition unit 133, a content generation unit 134, and a provision unit 135. The user information acquisition unit 133 acquires information about the target user. The content generation unit 134 generates content that reflects the impression of the target user from the text included in the user information of the target user. The provision unit 135 provides the generated content to the viewer's terminal device.

This allows the content generation device 100 to provide content that makes it easy for users to understand the other person's inner self, even without having to view detailed user information in matching services, etc.

Furthermore, as described above, the user information acquisition unit 133 may also acquire the viewer's user information, and the content generation unit 134 may identify corresponding user information from the target user's user information and the viewer's user information, and generate content that shows an image of the identified user information.

This allows the content generation device 100 to provide content that makes it easy for users to intuitively understand their relationship with another user, even without having to view detailed user information in matching services, etc.

Furthermore, as mentioned above, the corresponding user information described above may be user information that is common to both the target user's user information and the viewer's user information.

This allows the content generation device 100 to provide content that makes it easy for users to intuitively understand commonalities with other users, even without having to view detailed user information in matching services, etc.

Furthermore, as described above, the content generation unit 134 may generate content that reflects the viewer's impression using a learning model that generates images representing the text from the text itself.

This allows the content generation device 100 to provide images that represent the textual image of user information. As a result, in matching services and the like, content can be provided that makes it easier for users to visually understand the other person's inner qualities, etc., without having to view the other person's user information in detail.

Furthermore, as described above, the content generated by the content generation unit 134 may be an image depicting the object indicated by the user information. Alternatively, the content generated by the content generation unit 134 may be an image with colors corresponding to the user information's tendencies.

This allows the content generation device 100 to provide images that represent the subject indicated by the user information. As a result, in matching services and the like, content can be provided that makes it easier for users to visually understand the other person's inner qualities, etc., without having to view the other person's user information in detail.

Although several embodiments of this application have been described in detail based on the drawings, these are illustrative examples, and the present invention can be implemented in various modified and improved forms based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

10 Terminal device 100 Server (content generation device)
110 Communication Unit 120 Storage Unit 130 Control Unit 131 Model Generation Unit 132 Request Reception Unit 133 User Information Acquisition Unit 134 Content Generation Unit 135 Provision Unit

Claims (3)

A user information acquisition unit that acquires user information of target users and user information of viewers,
A content generation unit that identifies common information between the user information of the target user and the user information of the viewer, and generates an image representing the image of the text from the text contained in the identified information, using a learning model,
A content generation device characterized by comprising a providing unit that provides the aforementioned image to the viewer's terminal device. A content generation method performed by a content generation device,
The process involves obtaining user information of the target user and user information of the viewer,
The process involves identifying common information between the user information of the target user and the user information of the viewer, and generating an image representing the image of the common information using a learning model that generates an image representing the image of the text from the text contained in the identified information.
A content generation method characterized by comprising the step of providing the aforementioned image to the viewer's terminal device. The process involves obtaining user information of the target user and user information of the viewer,
The process involves identifying common information between the user information of the target user and the user information of the viewer, and generating an image representing the image of the common information using a learning model that generates an image representing the image of the text from the text contained in the identified information.
A content generation program that causes a computer to perform the steps of providing the aforementioned image to the viewer's terminal device.