Information processing device, information processing method, and information processing program

By collecting user information and using the generative model to generate interpreted content, the problem that users find it difficult to understand the meaning of news options is solved, and personalized option explanation display is achieved.

JP2025014892APending Publication Date: 2025-01-30LY CORP

Patent Information

Application Number
JP2023117829
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Filing Date
2023-07-19
Publication Date
2025-01-30

AI Technical Summary

Technical Problem

The prior art fails to consider the differences in user's meaning of the buttons for options in news articles, making it difficult for users to understand their meaning.

Method used

Information about the user's selection of options is collected through the information processing device, and interpreted content related to the options is generated and provided, and interpreted content is generated using a generative model such as a GPT model and displayed with the options.

Benefits of technology

Make it easier for users to understand the meaning of options and provide personalized interpretations to reflect user characteristics and interests.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2025014892000001_ABST
    Figure 2025014892000001_ABST
Patent Text Reader

Abstract

To provide an information processing device capable of making a user to easily understand the meaning of an option.SOLUTION: An information processing device comprises a collection unit, a generation unit, and a provision unit. The collection unit collects information on a user who has selected an option for each of the options presented for the user. The generation unit generates explanation content of each option on the basis of the information on the user collected by the collection unit. The provision unit provides the description content generated by the generation unit together with the option.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, news sites and the like have provided services that distribute summary content that summarizes news articles to be distributed (for example, see Patent Document 1). For example, such news sites present options such as "Like" to users and accept reactions from users to each news article. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2019-57266 A Summary of the Invention [Problem to be solved by the invention]

[0004] However, in the conventional technology, although the meanings of the options differ depending on the news article, no consideration was given to presenting the meanings of the options to the user.

[0005] The present invention has been made in consideration of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that enable a user to easily understand the meaning of options. [Means for solving the problem]

[0006] In order to solve the above-mentioned problems and achieve the object, an information processing device according to the present invention includes a collection unit, a generation unit, and a provision unit. The collection unit collects information about the user who selected each option presented to the user. The generation unit generates explanation content for each option based on the information about the user collected by the collection unit. The provision unit provides the explanation content generated by the generation unit together with the options. Effect of the Invention

[0007] According to the present invention, the meaning of each option can be easily understood. [Brief description of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Diagram 2] FIG. 2 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Diagram 3] FIG. 3 is a diagram illustrating an example of information stored in a content storage unit according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in a user information storage unit according to the embodiment. [Diagram 5] FIG. 5 is a flowchart illustrating an example of a processing procedure of the providing process according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, the information processing device, the information processing method, and the information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing according to the embodiment is realized by an information processing device 1 shown in Fig. 1.

[0011] 1 is an information processing device that distributes various contents. For example, the information processing device 1 provides news articles (corresponding to an example of contents) to each user through a news site.

[0012] The user terminal 100a and the user terminal 100b shown in FIG. 1 are terminal devices owned by the user Ua and the user Ub. For example, the user Ua and the user Ub can operate the user terminal 100a and the user terminal 100b to view news content distributed from the information processing device 1 through a news site. In the following, when the user terminal 100a and the user terminal 100b are not distinguished from each other, they are referred to as "user terminal 100", and when the user Ua and the user Ub are not distinguished from each other, they are referred to as "user U". In addition, while FIG. 1 illustrates an example in which the user terminal 100 is a smartphone, the user terminal 100 may be other devices such as a PC (Personal Computer).

[0013] Meanwhile, news sites accept reactions to articles from users U. For example, some news sites present options such as reaction buttons B1 to B3 to the user U as shown in Fig. 1, and accept selection operations from the user U on the reaction buttons B1 to B3. In the example shown in Fig. 1, the reaction button B1 is "educational," the reaction button B2 is "easy to understand," and the reaction button B3 is "a new perspective," and the user U will select the reaction button B1 to B3 that is closest to his or her own intuition regarding the news article.

[0014] However, since each user U has a different subjective opinion about an article, the meaning of each of the reaction buttons B1 to B3 will differ depending on the user U. Therefore, in the information processing according to the embodiment, explanation content for each of the reaction buttons B1 to B3 is also provided.

[0015] 1, the information processing device 1 first distributes content to the user terminal 100a (step S1). As described above, the information processing device 1 distributes the content together with a news article including reaction buttons B1 to B3.

[0016] Next, when the user Ua selects an option (reaction buttons B1 to B3) in the news article (step S2), the information processing device 1 collects information about the user Ua who selected the option (step S3).

[0017] For example, the information processing device 1 opens a comment section for a news article and accepts comments on the news article from each user U. The information processing device 1 collects, as information on the user Ua, information on comments written by the user Ua in the comment section for the news article, parts of the news article that the user Ua has highlighted, and the like.

[0018] At this time, the information processing device 1 may collect comments of users U whose attributes are similar to those of the user Ua, in addition to the comments of the user Ua. Having attributes similar to those of the user Ua means, for example, that the options selected by the user Ua are similar, but also includes having similar attributes such as age and gender, and viewing similar articles to those of the user Ua (i.e., having similar interests).

[0019] Next, the information processing device 1 generates explanation content for each option (reaction buttons B1 to B3) based on the collected information about the user Ua (step S4).

[0020] The information processing device 1 generates explanatory content from collected information about the user using a summary model that summarizes sentences. The summary model is, for example, a GPT model. For example, the information processing device 1 inputs a prompt for generating explanatory content for the options (reaction buttons B1 to B3), a news article, and information about the user to the summary model, and generates the explanatory content. The prompt for generating explanatory content for each option is, for example, "Please summarize the comments written in this URL (news article) from user U who selected 'I learned something (reaction button B1)'."

[0021] That is, in this case, the information processing device 1 will summarize the reactions on the news site to the news article by the user U who selected the reaction button B1, and generate commentary content. The summary model may generate commentary content that infers from the comments the reason why the user U selected the option. In this case, the information processing device 1 inputs a prompt such as "Infer from the comments the reason why the user U selected the option" to the summary model.

[0022] The information processing device 1 then provides the generated commentary content to the other user Ub together with the news article (step S5). As shown in Fig. 1, reaction buttons B1 to B3 are displayed on the user terminal 100b that has received the commentary content, and the commentary content Ce is displayed in a speech bubble. Note that the news article itself is omitted in Fig. 1.

[0023] This allows the user Ub to easily understand the meaning of the reaction buttons B1 to B3. At this time, the information processing device 1 may provide commentary content according to the user Ub to whom the content is to be provided. For example, the prompt in this case may be, in addition to the above prompt, "Please summarize what it means for this URL (news article) to be 'educational' according to the user attributes of the user Ub." In other words, in this case, the information processing device 1 can also individually optimize the commentary content for the user Ub.

[0024] In this way, the information processing device 1 according to the embodiment collects information about the user U who selected the option, and generates explanation content for the option based on the collected information about the user U. Therefore, the information processing device 1 according to the embodiment allows the user to easily understand the meaning of the option.

[0025] [2. Information Processing Device] Next, a configuration example of the information processing device 1 according to the embodiment will be described with reference to Fig. 2. Fig. 2 is a block diagram showing a configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 2, the information processing device 1 includes a communication unit 2, a storage unit 3, and a control unit 4. Note that the information processing device 1 may also include an input unit (e.g., a keyboard, a mouse, etc.) that receives various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display, etc.) that displays various information.

[0026] The communication unit 2 is realized by, for example, a network interface card (NIC) etc. The communication unit 2 is connected to a communication network such as 4G (4th Generation) or 5G (5th Generation) by wire or wirelessly, and transmits and receives information to and from each of the user terminals 100 etc. via the communication network.

[0027] The storage unit 3 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 has a content storage unit 31, a user information storage unit 32, and a model storage unit 33.

[0028] The content storage unit 31 stores various information related to the content. The content is a news article distributed on a news site. Fig. 3 is a diagram showing an example of information stored in the content storage unit 31 according to the embodiment.

[0029] 3, the content storage unit 31 stores information items such as "content ID," "content," and "reaction" in association with each other. The "content ID" is an identifier for identifying each content (news article).

[0030] "Content" is data about the content identified by the corresponding content ID. For example, the content includes a title, a thumbnail image, and a content body (news article).

[0031] "Reaction" is a user's reaction to the content identified by the corresponding content ID. For example, the reaction includes the number of views, the number of likes, comments, the number of times each option (reaction buttons B1 to B3) was selected, and information about the user IDs that selected each option.

[0032] Returning to the description of Fig. 2, the user information storage unit 32 will be described. The user information storage unit 32 stores various pieces of information related to users. Fig. 4 is a diagram showing an example of information stored in the user information storage unit 32 according to the embodiment.

[0033] 4, the user information storage unit 32 stores information items such as "user ID," "registration information," and "browsing history" in association with each other. The "user ID" is an identifier for identifying each user.

[0034] The "registration information" is information registered on a news site by a user identified by a corresponding user ID. For example, the registration information includes information on demographic attributes such as name, age, address, and occupation, and information on psychographic attributes such as hobbies.

[0035] The "browsing history" is the browsing history of a user identified by the corresponding user ID on a news site. The browsing history stores information on the news articles viewed and the viewing dates and times in chronological order.

[0036] Returning to the explanation of FIG. 3, the model storage unit 33 will be explained. The model storage unit 33 stores the summary model described above. The summary model generates explanatory content for each option. For example, the generative model is a language model that performs natural language processing, such as GPT (Generative Pre-trained Transformer) or BERT (Bidirectional Encoder Representations from Transformers).

[0037] Next, the control unit 4 will be described. The control unit 4 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in a storage device inside the information processing device 1 using a RAM as a working area. The control unit 4 is also, for example, a controller, and is realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0038] As shown in Fig. 2, the control unit 4 includes a delivery unit 41, a collection unit 42, a generation unit 43, and a provision unit 44, and realizes or executes the functions and actions of information processing described below. The internal configuration of the control unit 4 is not limited to the configuration shown in Fig. 2, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units in the control unit 4 is not limited to the connection relationship shown in Fig. 2, and may be other connection relationships.

[0039] The distribution unit 41 distributes news articles via a news site to each user terminal 100. For example, the distribution unit 41 distributes news articles including a comment section and reaction buttons B1 to B3 as described above.

[0040] The distribution unit 41 then accepts reactions from the user U to the distributed news article. Reactions include operating the reaction buttons B1 to B3, writing comments, attaching highlights to the news article, and the like.

[0041] When any of the reaction buttons B1 to B3 is selected by the user U, the distribution unit 41 notifies the collection unit 42 and instructs the collection of information about the user U.

[0042] The collection unit 42 collects information about the user who selected the option for each option presented to the user U. For example, the collection unit 42 collects information about the user U based on a collection instruction notified by the distribution unit 41.

[0043] For example, the collection unit 42 collects information on comments by the user U on a news article, parts of a news article that the user U has marked, comments made when sharing the news article on an SNS, etc. Then, the collection unit 42 stores the collected information in the content storage unit 31.

[0044] The generating unit 43 generates explanation content for each option based on the information about the user U collected by the collecting unit 42. In this embodiment, the generating unit 43 generates the explanation content using a summary model.

[0045] Specifically, the generation unit 43 generates the explanatory content by inputting a prompt for causing the summary model to generate explanatory content, the corresponding news article, information about the user U who selected each option, and the like, into the summary model.

[0046] At this time, the generation unit 43 may cause the summary model to summarize comments and the like made by users U with attributes similar to those of the user U who selected each option. The generation unit 43 may also generate different summary models depending on the users U to whom the commentary content is to be provided. The generation unit 43 may also input, for example, a prompt to the summary model for summarizing the contents of the options from the comments made by all users U.

[0047] Furthermore, the generation unit 43 may, for example, use the summary model to summarize comments by the user U on different news articles. For example, different news articles here are news articles about the same event, but include news articles about similar events.

[0048] In this way, the generation unit 43 generates commentary content by utilizing comments, etc. on different news articles, making it possible to generate commentary content even for news articles with few comments, etc. Then, the generation unit 43 passes the generated commentary content to the provision unit 44.

[0049] The providing unit 44 provides the commentary content generated by the generating unit 43 together with the options. For example, when the distributing unit 41 distributes a news article, the providing unit 44 provides the commentary content generated by the generating unit 43 together with each of the reaction buttons B1 to B3.

[0050] For example, as shown in Fig. 1, commentary content is displayed in a balloon for each of the reaction buttons B1 to B3, allowing the user U to intuitively understand the meaning of each of the reaction buttons B1 to B3.

[0051] [3. Processing flow] Next, a process procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 5. Fig. 5 is a flowchart showing an example of the process procedure of the providing process according to the embodiment.

[0052] 7, the information processing device 1 distributes content including options to a user through a news site (step S101). Next, the information processing device 1 collects information on a user U who has selected an option (step S102).

[0053] Next, the information processing device 1 generates explanation content for each option using the summary model (step S103), and provides content including the explanation content together with each option (step S104).

[0054] 4. Modifications In the above embodiment, the content is a news article, but the present invention is not limited to this. The content may be any other content, such as a questionnaire, that includes multiple options.

[0055] In the above embodiment, the reaction buttons B1 to B3 are used as an example of options, but the present invention is not limited thereto. For example, the options may be ones prepared in advance or ones posted by other users U, as long as they are presented to the user U and can be selected. Specifically, the options may be search tags (e.g., hashtags) posted by the user U. That is, the information processing device 1 may generate commentary content as options for hashtags selected by the user U and used in his / her own posts, or hashtags used by the user U when searching. For example, the information processing device 1 collects information about the user U who posted including the hashtag, or information about the user U who used the hashtag, and generates commentary content about the hashtag.

[0056] 5. Effects The information processing device 1 according to the embodiment includes a collection unit 42 that collects, for each option presented to a user, information about the user who selected the option, a generation unit 43 that generates explanatory content for each option based on the information about the user collected by the collection unit 42, and a provision unit 44 that provides the explanatory content generated by the generation unit 43 together with the option.

[0057] The generating unit 43 generates commentary content summarizing information about the user by using a summary model that summarizes sentences. The collecting unit 42 collects information about users who select reaction buttons for content as options, and the generating unit 43 generates commentary content for each reaction button.

[0058] Furthermore, the collection unit 42 collects comments on the content by users who have selected the reaction button as information about the users, and the generation unit 43 generates commentary content that summarizes the comments.

[0059] The generating unit 43 also generates commentary content by estimating from the comments the reason why the user who selected the option selected the reaction button. The generating unit 43 also generates different commentary content depending on the user to whom the commentary content is to be provided. The providing unit 44 also provides the commentary content for the option in a speech bubble format.

[0060] By using any one or a combination of the above-described processes, the information processing device according to the present application can allow the user to easily understand the meaning of each option.

[0061] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by a computer 1000 having a configuration as shown in Fig. 6. Fig. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. The computer 1000 has a CPU 1100, a RAM 1200, a ROM 1300, a HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0062] The CPU 1100 operates and controls each unit based on a program stored in the ROM 1300 or the HDD 1400. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer 1000 is started up, programs that depend on the hardware of the computer 1000, and the like.

[0063] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, etc. The communication interface 1500 receives data from other devices via a network (communication network) N and sends the data to the CPU 1100, and transmits data generated by the CPU 1100 to other devices via the network N.

[0064] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse (in FIG. 6, the output devices and the input devices are collectively referred to as "input / output devices") via an input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. The CPU 1100 also outputs generated data to the output devices via the input / output interface 1600.

[0065] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase change rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0066] For example, when the computer 1000 functions as an information processing device according to the embodiment, the CPU 1100 of the computer 1000 executes programs loaded onto the RAM 1200 to realize the functions of the control unit 4. The CPU 1100 of the computer 1000 reads and executes these programs from the recording medium 1800, but as another example, the CPU 1100 may obtain these programs from another device via the network N.

[0067] [7. Other] Although the embodiments of the present application have been described above, the present invention is not limited to the contents of these embodiments. The above-described components include those that can be easily imagined by a person skilled in the art, those that are substantially the same, and those that are within the so-called equivalent range. Furthermore, the above-described components can be appropriately combined. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0068] 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 a known method. In addition, the information including the processing procedures, specific names, various data and parameters shown in the above documents and drawings can be changed arbitrarily unless otherwise specified. For example, the various information shown in each drawing is not limited to the illustrated information.

[0069] In addition, each component of each device shown in the figure is a functional concept, and does not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads, usage conditions, etc.

[0070] For example, the above-mentioned information processing device may be realized using multiple server computers, and depending on the functions, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0071] Furthermore, the above-described embodiments and modifications can be appropriately combined as long as the processing contents are not contradictory.

[0072] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit", etc. For example, an acquisition section can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0073] 1. Information processing device 2. Communications Department 3 Storage section 4. Control Unit 31 Content storage unit 32 User information storage unit 33 Model Memory Section 41 Distribution Department 42 Collection Department 43 Generation part 44 Providing Department 100 user terminals Ce Commentary Content

Claims

1. a collection unit that collects information about the user who selected each option presented to the user; a generation unit that generates commentary content for each of the options based on the information about the user collected by the collection unit; a providing unit that provides the commentary content generated by the generating unit together with the options; An information processing device comprising:

2. The generation unit is generating the commentary content by summarizing information about the user using a summary model that summarizes text; 2. The information processing apparatus according to claim 1,

3. The collecting unit includes: Collecting information about the user who selected a reaction button for the content as the option; The generation unit is generating the commentary content for each of the reaction buttons; 2. The information processing apparatus according to claim 1,

4. The collecting unit includes: Collecting comments on the content by the user who selected the reaction button as information about the user; The generation unit is generating commentary content summarizing the comments; 4. The information processing apparatus according to claim 3,

5. The generation unit is generating the commentary content by estimating from the comment the reason why the user who selected the option selected the reaction button; 5. The information processing apparatus according to claim 4,

6. The generation unit is generating different commentary content depending on a user to whom the commentary content is to be provided; 2. The information processing apparatus according to claim 1,

7. The providing unit is providing the commentary content in a speech bubble format for the selection; 2. The information processing apparatus according to claim 1,

8. 1. A computer-implemented information processing method, comprising: a collection step of collecting information about the user who selected each option presented to the user; a generating step of generating commentary content for each of the options based on the information about the user collected by the collecting step; a providing step of providing the commentary content generated by the generating step together with the options; 13. An information processing method comprising:

9. a collection step for collecting information about the user who selected each option presented to the user; a generating step of generating commentary content for each of the options based on the information about the user collected by the collecting step; a providing step of providing the commentary content generated by the generating step together with the selection; An information processing program characterized by causing a computer to execute the above.

Citation Information

Patent Citations

  • Generation device, learning apparatus, generation method, learning method, generation program, learning program, and model

    JP2019057266A

Cited By

  • Information processing device, information processing method, and information processing program

    JP2026154784A