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

Abstract

To efficiently guide a user to a content.SOLUTION: An information processor includes an extraction part, a generation part, and a provision part. The extraction part extracts post information favorably evaluated by a user out of post information having been posted to each content, The generation part generates a summarized content according to the preferable tendency of the user, on the basis of the post information extracted by the extraction part. The provision part provides the summarized content generated by the generation part.SELECTED DRAWING: Figure 1

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, there are known techniques for distributing distribution content such as news articles. For example, Patent Document 1 discloses a technique for providing provided content including distribution content and each piece of posted content for the distribution content. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-197422 Summary of the Invention [Problem to be solved by the invention]

[0004] However, conventional techniques leave room for improvement in guiding users to content.

[0005] The present invention has been made in view of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can efficiently guide a user to content. [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 an extraction unit, a generation unit, and a provision unit. The extraction unit extracts posted information that has been favorably rated by a user from among posted information posted for each piece of content. The generation unit generates summary content that matches the user's preferences based on the posted information extracted by the extraction unit. The provision unit provides the summary content generated by the generation unit. [Effects of the Invention]

[0007] According to the present invention, it is possible to efficiently guide users to content. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of a prompt according to the embodiment. [Figure 3] FIG. 3 is a block diagram illustrating an example of the configuration of the information processing device 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. [Figure 5] FIG. 5 is a diagram illustrating an example of information stored in the content information storage unit according to the embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of the collection process according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of the generation process according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an 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] The information processing device 1 according to the embodiment is, for example, an information processing device that operates a news site, etc. For example, the information processing device 1 distributes distribution content including news articles to each user.

[0012] 1, the user terminals 100, including the user terminal 100a and the user terminal 100b, are information processing devices used by users. The user terminals 100 are realized, for example, by smartphones, tablet terminals, notebook PCs (Personal Computers), desktop PCs, mobile phones, PDAs (Personal Digital Assistants), etc. The user terminals 100 display information distributed by the information processing devices 1 using a web browser or an application.

[0013] Meanwhile, news sites accept comments from users on news articles and distribute these comments together with the news articles, and in such cases, other users can also react to the user's comments.

[0014] When a news site displays a comment that a user sympathizes with, that user tends to view other comments and other news articles. Therefore, by displaying comments that users sympathize with, it is expected that the page views of the entire news site will increase.

[0015] Therefore, in this embodiment, summary content is generated by summarizing comments and the like that users have given favorable ratings, and the summary content is provided to the corresponding users.

[0016] 1, the information processing device 1 distributes distribution content to the user terminal 100a (step S1). The distribution content includes news articles and comments from each user on the news articles.

[0017] Users can view the distributed content through the user terminal 100a and post comments on news articles. The comments correspond to posted information.

[0018] For example, when a user of the user terminal 100a posts a comment on a news article, the comment is notified to the information processing device 1 as posted information (step S2). Note that the posted information may include a comment posted by the user when the news article is shared on an SNS.

[0019] Next, the information processing device 1 distributes the distribution content including the posted information received from the user terminal 100a to another user terminal 100b (step S3), and receives a reaction to the comment from the user of the user terminal 100b (step S4).

[0020] Reactions include "liking" a comment, highlighting a comment, etc. In this way, users can give favorable evaluations of comments through reactions.

[0021] Then, the information processing device 1 collects information about these reactions for each user, and thereby can estimate the user's empathy policy, such as which comments the user will give a favorable evaluation to.

[0022] Therefore, the information processing device 1 extracts posted information that has been favorably rated by the user from among the posted information posted for each content (step S5). Specifically, the information processing device 1 extracts posted information that has been "liked" by the target user, sentences that the user has highlighted in the posted information, etc.

[0023] In step S5, the information processing device 1 extracts posted information using a generative model (hereinafter simply referred to as a generative model) such as a GPT (Generative Pre-Trained Transformer). Subsequently, the information processing device 1 generates summary content tailored to the user's preferences from the extracted posted information, etc., by inputting a prompt (described later) to the generative model (step S6).

[0024] Then, the information processing device 1 provides the summarized content to the user terminal 100b of the target user (step S7). Here, the summarized content is content that summarizes posted information that the user has given a favorable evaluation to, in other words, content that summarizes comments that the user can easily relate to.

[0025] For example, the information processing device 1 periodically provides summary content to the user terminal 100 by push notification via an application related to a news site. Note that the information processing device 1 may provide the summary content to the user by posting it on the top screen of the news site.

[0026] In this way, the information processing device 1 generates summary content based on posted information that the user has given a favorable rating, and provides the generated summary content to the user. In other words, the information processing device 1 can appropriately guide the user to content (for example, a news site) by providing summary content that the user is likely to identify with.

[0027] Next, a prompt to be input to the generative model will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of a prompt according to an embodiment. As shown in Fig. 2, the prompt includes an instruction sentence regarding the extraction conditions (filter conditions) for comments (here, "Please read the data below for each user and extract the comments that users most 'relate to' within the comment section of the target article"), the conditions for the comments to be extracted (here, "comments to be extracted" and "filter conditions"), and an instruction sentence for creating a summary comment ("Please summarize the extracted comments in 50 characters or less").

[0028] In addition, the filter conditions entered as prompts are divided into the content of the article you are currently reading (hereinafter also referred to as condition 1) and content that refers to the content below in the same category as the article you are currently reading (hereinafter also referred to as condition 2).

[0029] Of these, condition 2 further includes the content of comments that have been "liked" within the last 30 days, the content of articles that have been "liked" within the last 30 days, and paragraphs that have been highlighted within the last 30 days.

[0030] That is, under condition 2, posted information that the user has given a favorable rating, the contents of the news articles, and sentences contained in posted information that the user has focused on are extracted.

[0031] The information processing device 1 can generate summary content by inputting news articles, posted information linked with user reactions, and the like into the generation model along with these prompts.

[0032] In this way, the information processing device 1 generates summary content using the generation model, thereby making it possible to automatically generate content that matches the empathy axis of each user.

[0033] [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. 3. Fig. 3 is a block diagram showing the configuration example of the information processing device 1 according to the embodiment. As shown in Fig. 3, 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 or a mouse) that accepts various operations from an administrator who uses the information processing device 1, and a display unit (e.g., a liquid crystal display) that displays various information.

[0034] 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.

[0035] The storage unit 3 is realized by, for example, a semiconductor memory element such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 has a user information storage unit 31 and a content information storage unit 32.

[0036] The user information storage unit 31 stores user information. Fig. 4 is a diagram showing an example of information stored in the user information storage unit 31 according to the embodiment. As shown in Fig. 4, the user information storage unit 31 stores information items such as "user ID," "registration information," and "reaction history" in association with each other.

[0037] The "User ID" field stores an identifier for identifying each user. The "Registration Information" field stores information registered on the website of the information processing device 1 by a user identified by the corresponding user ID. The registration information includes information on demographic attributes such as name, age, and address, and information on psychographic attributes such as hobbies and preferences.

[0038] The "reaction history" item stores information about the reaction history of a user identified by the corresponding user ID. For example, a reaction is a user action such as "liking" a comment or "highlighting" a comment, and the reaction history includes information about the corresponding action and the comment, news article, etc. that caused the action.

[0039] Returning to the description of Fig. 3, the content information storage unit 32 will be described. The content information storage unit 32 stores content information. Fig. 5 is a diagram showing an example of information stored in the content information storage unit 32 according to the embodiment.

[0040] 5, the content information storage unit 32 stores information items such as "content ID," "content details," and "posted information" in association with each other. The "content ID" item stores an identifier for identifying content (news article).

[0041] The "content details" field stores information about the content identified by the corresponding content ID, i.e., the news article itself. The "posted information" field stores posted information, i.e., comments, posted to the content identified by the corresponding content ID. Such posted information includes information about reactions made by each user.

[0042] Returning to the explanation of Fig. 4, the control unit 4 will now 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) using RAM as a work area to execute various programs (corresponding to examples of information processing programs) stored in a storage device inside the information processing device 1. 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).

[0043] As shown in Fig. 4, the control unit 4 includes a distribution unit 41, a reception unit 42, an extraction unit 43, a generation unit 44, and a provision unit 45, and realizes or executes the functions and actions of the information processing described below. Note that the internal configuration of the control unit 4 is not limited to the configuration shown in Fig. 4, and may be other configurations as long as they perform the information processing described below. Furthermore, the connection relationship between the processing units included in the control unit 4 is not limited to the connection relationship shown in Fig. 4, and may be other connection relationships.

[0044] The distribution unit 41 distributes distribution content to each user's user terminal 100. For example, when a news site is accessed from the user terminal 100, the distribution unit 41 selects a news article to be distributed from the content information storage unit 32 and distributes it as distribution content through the news site.

[0045] In this case, the distribution unit 41 may distribute news articles in which comments similar to the summary content described below have been posted so that they are preferentially displayed on the user terminal 100, or may distribute comments within the news article that are similar to the summary content so that they are preferentially displayed on the user terminal 100.

[0046] The accepting unit 42 accepts comments on news articles from users via the user terminal 100. The accepting unit 42 stores the comments accepted from the users in the content information storage unit 32 in association with information such as the user ID of the user and the time.

[0047] The receiving unit 42 also receives reactions to the comments from users via the user terminal 100. For example, the receiving unit 42 receives reactions such as "like" or "highlight" to the comment.

[0048] When the receiving unit 42 receives a reaction to a comment from a user, the receiving unit 42 stores the reaction in the “reaction history” of the user information storage unit 31 and adds it to the “posted information” item of the content information storage unit 32.

[0049] The extraction unit 43 extracts posted information that has been favorably rated by users from the posted information posted for each content. Specifically, the extraction unit 43 extracts posted information that has been favorably rated by users by inputting a prompt, user information of the target user, and content information into the generative model.

[0050] More specifically, the extraction unit 43 extracts posted information that the user has "liked" or "highlighted." In addition to the posted information, the extraction unit 43 also inputs content information into the generative model, thereby extracting the article content of the news article that the user has "liked."

[0051] The generation unit 44 generates summary content that matches the user's preference trends based on the posted information extracted by the extraction unit 43. For example, the generation unit 44 generates summary content after causing the generation model to estimate the user's empathy axis from the multiple pieces of posted information extracted by the extraction unit 43.

[0052] At this time, the generation unit 44 generates summary content that summarizes multiple pieces of posted information that the user has given a favorable rating, summary content that summarizes the content of the posted information that the user has given a favorable rating to, or summary content that summarizes the content of a sentence that the user has focused on (highlighted) in the posted information that the user has given a favorable rating to, etc.

[0053] Furthermore, for example, the generation unit 44 may generate summary content for each news article category. For example, the generation unit 44 may generate summary content that summarizes the posted information or content included in a news article category that the user frequently views.

[0054] The providing unit 45 provides the summary content generated by the generating unit 44. For example, the providing unit 45 provides the summary content generated for each user to the user terminal 100 of each user by push notification.

[0055] For example, by providing summary content via push notification, the rate at which users open the content can be increased. In other words, by providing summary content that resonates with users via push notification, users can be efficiently guided to the content (news site).

[0056] The providing unit 45 may provide the summary content to the user by, for example, displaying the summary content on the top screen of a news site. However, the means for providing the summary content is not limited to this.

[0057] [3. Processing flow] Next, a processing procedure executed by the information processing device 1 according to the embodiment will be described with reference to Fig. 6 and Fig. 7. Fig. 6 is a flowchart showing an example of a collection process according to the embodiment. Fig. 7 is a flowchart showing an example of a generation process according to the embodiment.

[0058] First, a processing procedure for collecting user reactions to comments will be described with reference to Fig. 6. As shown in Fig. 6, the information processing device 1 provides (distributes) distribution content to each user terminal 100 (step S101). Next, the information processing device 1 accepts posted information regarding the distribution content (step S102).

[0059] Next, the information processing device 1 provides distribution content including the posted information accepted in step S102 to each user terminal 100 (step S103). Then, the information processing device 1 collects each user's reaction to the posted information (step S104) and ends the process.

[0060] Next, a generation flow of summary content will be described with reference to Fig. 7. As shown in Fig. 7, the information processing device 1 first uses a generation model to extract posted information that has been favorably rated by a user (step S111). Next, the information processing device 1 uses the generation model to estimate the user's empathy axis based on the extracted posted information, etc. (step S112).

[0061] Next, the information processing device 1 generates summary content based on the empathy axis and the extracted posted information and content information (step S113).Then, the information processing device 1 provides the generated summary content (step S114), and ends the process.

[0062] [4. Modifications] In the above-described embodiment, news articles have been used as examples of content, but the present invention is not limited to this. The content may be various types of content, including text, images, and videos posted on social networking sites. Furthermore, the content may be other content, such as store information or real estate information posted on websites introducing restaurants, real estate, etc., as long as the media allows users to post comments.

[0063] [5. Effects] The information processing device 1 according to the embodiment includes an extraction unit 43 that extracts posted information that has been favorably rated by users from among the posted information posted for each piece of content, a generation unit 44 that generates summary content that matches the user's preferences based on the posted information extracted by the extraction unit 43, and a provision unit 45 that provides the summary content generated by the generation unit 44.

[0064] The generation unit 44 also generates summary content that summarizes a plurality of pieces of posted information that have been favorably rated by the user. The generation unit 44 also generates summary content that summarizes the content to which the posted information that has been favorably rated by the user has been posted.

[0065] The generating unit 44 generates summary content that summarizes the content of a sentence that the user focused on from the posted information that the user has given a favorable rating. The generating unit 44 generates summary content for each content category, and the providing unit 45 provides the summary content generated for each category.

[0066] The information processing device 1 also includes a distribution unit 41 that distributes distribution content in which the content including the posted information similar to the summary content is preferentially displayed. The information processing device 1 also includes a distribution unit 41 that distributes distribution content in which posted information similar to the summary content is preferentially displayed within the content. The providing unit 45 also provides the summary content to the user by push notification.

[0067] By performing any one of the above processes or a combination thereof, the information processing device according to the present application can efficiently guide the user to content.

[0068] [6. Hardware Configuration] The information processing device 1 according to the embodiment described above is realized by, for example, a computer 1000 configured as shown in Fig. 8. Fig. 8 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, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0069] The CPU 1100 operates and controls each unit based on programs 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 starts up, programs that depend on the hardware of the computer 1000, and the like.

[0070] 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.

[0071] 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. 8, the output devices and input devices are collectively referred to as "input / output devices") via the 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.

[0072] Media interface 1700 reads a program or data stored in recording medium 1800 and provides it to CPU 1100 via RAM 1200. CPU 1100 loads the program or data from recording medium 1800 onto RAM 1200 via media interface 1700 and executes the loaded program. 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.

[0073] For example, when the computer 1000 functions as the 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.

[0074] [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. Furthermore, 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 scope of so-called equivalents. Furthermore, the above-described components can be combined as appropriate. Furthermore, various omissions, substitutions, or modifications of the components can be made without departing from the spirit of the above-described embodiments.

[0075] 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 using 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 as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0076] Furthermore, the components of each device shown in the figure are conceptual functional components and do 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 depending on various loads, usage conditions, etc.

[0077] For example, the above-mentioned information processing device may be realized using multiple server computers, and depending on the function, the configuration can be flexibly changed, such as by calling an external platform using an API (Application Programming Interface) or network computing.

[0078] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0079] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0080] 1. Information processing equipment 2. Communications Department 3 Storage section 4. Control section 31 User information storage unit 32 Content information storage unit 41 Distribution Department 42 Reception Department 43 Extraction part 44 Generation part 45 Providing Department 100 user terminals

Claims

1. an extraction unit that extracts posted information that has been favorably rated by a user from posted information posted for each piece of content; a generation unit that generates summary content that matches the user's preferences based on the posted information extracted by the extraction unit; a providing unit that provides the summary content generated by the generating unit; Equipped with The generation unit The summary content is generated by summarizing the posted information posted by other users and satisfying the user's taste tendency estimated from the posted information that the user has favorably rated.

1. An information processing device comprising:

2. The generation unit The posted information that the user has given a favorable rating satisfies the user's taste tendency estimated from the posted content, and the summarized content is generated by summarizing the posted information posted by other users.

2. The information processing device according to claim 1,

3. The generation unit Generate the summary content by summarizing the posted information posted by other users, which is posted information that the user has given a favorable evaluation and which satisfies the user's taste tendency estimated from the content of a sentence that the user has focused on.

2. The information processing device according to claim 1,

4. The generation unit generating the summary content for each category of content; The providing unit providing the summary content generated for each of the categories; 2. The information processing device according to claim 1,

5. a distribution unit that distributes distribution content in which the content including the posted information similar to the summarized content is preferentially displayed; To be prepared 2. The information processing device according to claim 1,

6. a distribution unit that distributes distribution content in which the posted information similar to the summary content is preferentially displayed within the content; To be prepared 2. The information processing device according to claim 1,

7. The providing unit Providing the summarized content to the user via a push notification 2. The information processing device according to claim 1,

8. 1. A computer-implemented information processing method, comprising: an extraction step of extracting posted information that has been favorably rated by users from posted information posted for each piece of content; a generating step of generating summary content that matches the user's preferences based on the posted information extracted by the extracting step; a providing step of providing the summary content generated by the generating step; Including, The generating step includes: The summary content is generated by summarizing the posted information posted by other users and satisfying the user's taste tendency estimated from the posted information that the user has favorably rated.

1. An information processing method comprising:

9. an extraction step of extracting posted information that has been favorably rated by users from posted information posted to each piece of content; a generating step of generating summary content that matches the user's preferences based on the posted information extracted by the extracting step; a providing step of providing the summary content generated by the generating step; on the computer, The generating procedure includes: The summary content is generated by summarizing the posted information posted by other users and satisfying the user's taste tendency estimated from the posted information that the user has favorably rated. An information processing program characterized by:

Images