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

Abstract

To enable provision of new content by utilizing content.SOLUTION: An information processing device disclosed herein comprises an acquisition unit, an extraction unit, and a generation unit. The acquisition unit acquires comments posted on a given topic. The extraction unit extracts a group of comments satisfying given conditions from among the comments acquired by the acquisition unit. The generation unit generates discussion content by editing the group of comments extracted by the extraction unit in a discussion format.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 content such as news articles. For example, Patent Document 1 discloses a technique for providing content including news articles and comments on the news articles as 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, in the conventional technology, comments on distributed content are merely posted in a comment section, and no consideration is given to providing new content that utilizes the comments.

[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 are capable of providing new content that utilizes comments. [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 acquisition unit, an extraction unit, and a generation unit. The acquisition unit acquires comments posted to a topic. The extraction unit extracts a group of comments that satisfy predetermined conditions from the comments acquired by the acquisition unit. The generation unit generates discussion content by editing the group of comments extracted by the extraction unit into a discussion format. [Effects of the Invention]

[0007] According to the present invention, new content that utilizes comments can be provided. [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 discussion content 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 the content information storage unit according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of information stored in an account information storage unit according to the embodiment. [Figure 6] FIG. 6 is a schematic diagram of a group of comments according to the embodiment. [Figure 7] FIG. 7 is a diagram showing an example of providing discussion content. [Figure 8] FIG. 8 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 9] FIG. 9 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 method is executed by, for example, an information processing device 1 shown in Fig. 1.

[0011] 1 is an information processing device that provides various services to a user U via the Internet. In the present disclosure, the information processing device 1 provides various services related to news sites to the user U. Note that the information processing device 1 is realized by, for example, a server device, a cloud system, or the like.

[0012] The user terminal 50 is a terminal device owned by the user U, and acquires various information from the information processing device 1 through data communication with the information processing device 1. In the present disclosure, the user terminal 50 provides news articles distributed from the information processing device 1 to the user U. Examples of the user terminal 50 include a smartphone, a tablet terminal, a personal computer, and a wearable terminal.

[0013] Meanwhile, some news sites offer services that accept comments on news articles from users U and provide the comments attached to the news articles. In such services, comments posted in the comment section of a news article can also be considered as part of the content.

[0014] In the present disclosure, the information processing device 1 provides new content that utilizes comments posted in a comment section of a news article. An overview of the information processing according to the present application will be described below.

[0015] 1, the information processing device 1 first distributes distribution content to the user terminal 50 (step S1). The distribution content includes news articles and comments posted to each news article.

[0016] Next, the information processing device 1 accepts a comment posted by the user U through the user terminal 50 (step S2). At this time, the information processing device 1 accepts a comment on the news article provided to the user U through the user terminal 50.

[0017] Such comments are provided as distribution content to other users U together with the news article. At this time, the information processing device 1 can also accept ratings from other users U for the comments posted on the news article. Specifically, the information processing device 1 displays, for example, a like button and a dislike button for each comment and accepts ratings from other users U through the like button and the dislike button.

[0018] By performing the processes of steps S1 and S2 on other users U, the information processing device 1 accumulates comments posted by the users U on news articles related to a predetermined topic.

[0019] The information processing device 1 extracts a group of comments that satisfy a predetermined condition from the accumulated comments (step S3). Specifically, for example, the information processing device 1 extracts a group of comments that satisfy a predetermined condition from a group of comments posted to a news article related to a predetermined topic.

[0020] In the following, an example will be described in which the predetermined topic is “gender wage gap.” For example, in this case, the information processing device 1 acquires comments posted to multiple news articles related to “gender wage gap,” and extracts from these comments a group of comments (hereinafter simply referred to as a group of comments) that satisfy a predetermined condition.

[0021] Examples of the specified conditions include the following (1) to (3): (1) The constructive score must be above a certain level. (2) The discomfort index must be low. (3) The number of past reports to the poster must be below a certain level.

[0022] Here, "constructive" refers to satisfying conditions such as "being objective and providing evidence where necessary" and "offering new ways of thinking, solutions, and insights," and the constructive score is the value given to constructive comments. For example, the constructive score is determined by a natural language processing model (AI) using deep learning.

[0023] The discomfort index indicates the degree to which other users U feel uncomfortable when viewing a comment, and is a value obtained by scoring an unpleasant comment. For example, the discomfort index is determined by a natural language processing model (AI) using deep learning.

[0024] Furthermore, news sites have a reporting function for comments distributed as content, so that, for example, user U can report a comment that he or she finds offensive to the news site's management. Comments for which the poster has received a certain number of reports in the past fall under the category of comments that satisfy the condition (3) above.

[0025] After extracting the group of comments, the information processing device 1 generates discussion content (step S4). The discussion content is content in which the group of comments is edited into a discussion format. The information processing device 1 generates the discussion content using a sentence generation model that generates answers to input sentences.

[0026] For example, the information processing device 1 generates a prompt including a content group and an instruction prompt, and inputs the generated prompt to the sentence generation model. The instruction prompt is in natural language, such as "Generate discussion content that meets the following conditions from the following comment group. For the following conditions, assign and arrange comments according to five categories: 1. Evidence-based opinions. 2. Logical opinions. 3. Opinions based on actual experiences. 4. Opinions from multiple perspectives. 5. Opinions of experts (knowledgeable people)."

[0027] In the text generation model, discussion content is generated from the group of comments based on these input prompts. After that, the information processing device 1 provides the generated discussion content via the user terminal 50 (step S5).

[0028] 2 is a diagram showing an example of discussion content according to the embodiment. As shown in FIG. 2, the discussion content is composed of comments from multiple users U on the topic "gender wage gap."

[0029] Each comment has a speech bubble that displays the main points of the comment, and below that, the category, good button, and bad button are displayed. In addition, the discussion content has an introduction section where the user U who posted the comment is introduced as a "discussion member," and a comment section where comments on the discussion content are displayed.

[0030] In this way, the information processing device 1 generates discussion content from comments posted on a predetermined topic. As a result, the information processing device 1 according to the embodiment can provide new content that utilizes comments.

[0031] [2. Configuration example of information processing device] Next, a configuration example of the information processing device 1 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing a configuration example of the information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a storage unit 3, and a control unit 4.

[0032] The communication unit 2 is realized by, for example, a network interface card (NIC), etc. The communication unit 2 transmits and receives information to and from an external device via a network such as various wireless communication networks, such as 4G (Generation), 5G, LTE (Long Term Evolution), WiFi (registered trademark), or wireless LAN (Local Area Network), or various wired communication networks.

[0033] The storage unit 3 is realized by, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 3 also has a content information storage unit 31, an account information storage unit 32, and a sentence generation model storage unit 33.

[0034] The content information storage unit 31 stores content information. Fig. 4 is a diagram showing an example of information stored in the content information storage unit 31 according to the embodiment. As shown in Fig. 4, the content information storage unit 31 stores information on items such as "content ID," "category," "content data," and "comments" in association with each other.

[0035] The "Content ID" field stores an identifier for identifying each piece of content (news article). The "Category" field stores the category of the content (news article) identified by the corresponding content ID. The category may indicate the field of the corresponding content, such as "Economy," "Entertainment," or "Sports," or may indicate the topic of the content.

[0036] The "content data" item stores content data identified by the corresponding content ID. The content data is data related to news articles, and includes the title, thumbnail image, main text, summary, etc. of the news article.

[0037] The "Comment" item stores comments posted to the content identified by the corresponding content ID. The comments are comments posted on news sites, but also include comments posted when posting news articles on social media.

[0038] Returning to the explanation of Fig. 3, the account information storage unit 32 will be explained. The account information storage unit 32 stores account information. The account information is information relating to the account of each user U.

[0039] 5 is a diagram illustrating an example of information stored in the account information storage unit 32 according to the embodiment. As shown in FIG. 5, the account information storage unit 32 stores information items such as "account ID," "registration information," "comment history," and "genre" in association with each other.

[0040] The "account ID" item stores the account ID. The account ID is an identifier for identifying each user U. The "registration information" item stores the registration information. The registration information is information that the user U identified by the corresponding account ID has registered on a news site provided by the information processing device 1.

[0041] The registration information includes information on demographic attributes such as name, age, address, and occupation, as well as information on psychographic attributes such as hobbies and preferences. The registration information may also include information registered by the user U on other services affiliated with the news site. The other services may include various e-commerce sites such as shopping sites and flea market sites, reservation sites for restaurants, hotels, and flights, and electronic payment services that offer credit card and QR code (registered trademark) payments.

[0042] The "comment history" item stores the comment history of a user U identified by the corresponding account ID. The comment history includes information on items such as the news article to which the user U posted the comment, the comment, and the posting date and time. The comment history may also include evaluations by other users U of the comments posted by the user U. The evaluations by other users U include, for example, "good," "bad," "report," etc.

[0043] The "genre" item stores information about the genre of the user U identified by the corresponding account ID. For example, if the corresponding user U is an expert, information about the field of expertise is stored as "genre" in the "genre" item. Note that "genre" is assigned to authenticated accounts that have been approved in advance by the news site as experts (knowledgeable persons).

[0044] Returning to the explanation of FIG. 3, the sentence generation model storage unit 33 will be explained. The sentence generation model storage unit 33 stores a sentence generation model. The sentence generation model is a large-scale language model trained to generate a response sentence to an input natural language sentence. For example, the sentence generation model is a GPT (Generative Pre-trained Transformer).

[0045] Next, we will explain the control unit 4. The control unit 4 is, for example, a controller, and is realized by a CPU (Central Processing Unit), an MPU (Micro Processing Unit), or the like, executing various programs stored in a storage device inside the information processing device 1 using RAM as a working area.

[0046] As shown in FIG. 3, the control unit 4 includes a distribution unit 41, an acquisition unit 42, an extraction unit 43, a generation unit 44, and a provision unit 45.

[0047] The distribution unit 41 distributes distribution content to each user terminal 50. For example, the distribution unit 41 distributes news articles and comments posted to the news articles as distribution content.

[0048] Specifically, the distribution unit 41 distributes information about the top page of the news site to each user terminal 50, and then distributes distribution content corresponding to the news article selected by the user U.

[0049] Furthermore, the distribution unit 41 accepts comments posted by the user U through the distribution content, and registers the comments posted by the user U in the content information storage unit 31, and distributes them to the user U as distribution content from the next time onwards.

[0050] The acquisition unit 42 acquires comments posted on a predetermined topic. First, the acquisition unit 42 determines the topic of the discussion content. For example, the topic of the discussion content may be determined based on the number of comments or page views for a news article distributed as distribution content.

[0051] For example, in this case, the acquisition unit 42 tallies the number of comments and the number of page views of the distribution content by topic, and determines the top-ranked topic as the topic of the discussion content. Note that the topic of the discussion content may be determined by an administrator.

[0052] Next, the acquisition unit 42 acquires comments corresponding to the topic from the comments registered in the content information storage unit 31. For example, the acquisition unit 42 acquires comments posted to a news article corresponding to the topic.

[0053] The extraction unit 43 extracts a group of comments that satisfy predetermined conditions from among the comments acquired by the acquisition unit 42. The extraction unit 43 extracts a group of comments that satisfy predetermined conditions (1) to (3).

[0054] Examples of the predetermined conditions (1) to (3) include: (1) the constructive score is above a certain level; (2) the discomfort index is low; and (3) the number of past reports to the poster is below a certain level.

[0055] The construction score and discomfort index are calculated using a natural language processing model (AI) that uses deep learning. The natural language processing model that calculates the construction score here is a model trained to output a constructive score using constructive and non-constructive comments as training data.

[0056] Furthermore, the natural language processing model that scores the discomfort index is a model that is trained to output a discomfort index using unpleasant comments and non-unpleasant comments as training data.

[0057] The extraction unit 43 then extracts a group of comments that satisfy the above-mentioned predetermined conditions (1) to (3) from among the comments acquired by the acquisition unit 42. The predetermined conditions (1) to (3) correspond to examples of discussion conditions.

[0058] In this case, the acquisition unit 42 acquires comments posted to a plurality of news articles on the same topic, and the extraction unit 43 extracts a group of comments that satisfy a predetermined condition from among the comments posted to the plurality of news articles.

[0059] Here, the relationship between news articles and comment groups will be described with reference to Fig. 6. Fig. 6 is a schematic diagram of a comment group according to the embodiment. It is assumed that articles A to C shown in Fig. 6 are all news articles on the same topic.

[0060] As shown in Figure 6, the group of comments includes comments on multiple articles A to C. In other words, since multiple articles A to C have different article distributors (article creators), even if they are on the same topic, the content will be different depending on the article distributor.

[0061] Therefore, the comments posted to the multiple articles A to C are likely to be from different perspectives because they are posted to the respective articles. In other words, the extraction unit 43 can easily extract comments posted from different perspectives by extracting a group of comments across multiple articles.

[0062] Therefore, the group of comments extracted by the extraction unit 43 is likely to include comments from multiple perspectives, in other words, it is possible to easily generate discussion content that allows for multifaceted discussion.

[0063] The generation unit 44 generates discussion content by editing the group of comments extracted by the extraction unit 43 into a discussion format. Specifically, the generation unit 44 generates a prompt including a group of content and an instruction prompt, and inputs the generated prompt into the sentence generation model. The instruction prompt is in natural language, such as "Please generate discussion content that meets the following conditions from the group of comments below. For the following conditions, please assign and arrange comments according to five categories: 1. Evidence-based opinions. 2. Logical opinions. 3. Opinions based on actual experience. 4. Opinions from multiple perspectives. 5. Opinions of experts (knowledgeable people)." Note that 1 to 5 above correspond to examples of each pre-set category.

[0064] Based on the input prompt, the sentence generation model extracts comments to be adopted as discussion content from among the comments included in the group of comments and generates a response sentence that determines the display order, etc.

[0065] In this case, the generation unit 44 may generate discussion content in which the attributes of the posters who posted the comments satisfy a predetermined condition. For example, the predetermined condition here includes that at least one of the posters of comments posted in the discussion content is an expert (knowledgeable person) on the corresponding topic.

[0066] Then, the generation unit 44 generates discussion content (see FIG. 2) by editing the comments into a discussion format based on the response sentences output from the sentence generation model.

[0067] The providing unit 45 provides the discussion content generated by the generating unit 44. For example, the providing unit 45 provides the discussion content through a news site. For example, the providing unit 45 changes the manner in which the discussion content is provided in accordance with user evaluations of the discussion content.

[0068] An example of providing discussion content will now be described with reference to Fig. 7. Fig. 7 is a diagram showing an example of providing discussion content. The example shown in Fig. 7 shows a case where discussion content is provided through the top screen of a news site.

[0069] If the user evaluation of the discussion content is high, the providing unit 45 provides the discussion content through the top screen of the news site. In this case, a banner Tp of the discussion content is displayed on the top screen of the news site, and when the banner Tp is selected, the providing unit 45 provides the corresponding discussion content.

[0070] For example, in such a case, the providing unit 45 displays a banner Tp on the top screen for discussion content that has received high user ratings. The discussion content that has received high user ratings is determined based on the number of likes and bads for the discussion content, the number of comments for the discussion content, etc.

[0071] In this way, the providing unit 45 displays the discussion content on the top page according to the user evaluation. In other words, the providing unit 45 provides the discussion content evaluated by the user as content through the top screen of the news site.

[0072] This allows the providing unit 45 to provide the discussion content that has been evaluated as content to a wide range of users, thereby enabling the discussion content to gain recognition. The providing unit 45 may, for example, display a banner Tp of the discussion content on a news article as a related article to a news article on the same topic. The providing unit 45 may also provide the discussion content not only through a news site, but also through various push-type notifications.

[0073] [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. 8. Fig. 8 is a flowchart showing an example of information processing according to the embodiment.

[0074] As shown in Fig. 7, first, the information processing device 1 acquires comments on content (step S101). Next, the information processing device 1 determines whether or not the extraction condition for a comment group is met (step S102). The extraction condition for a comment group is determined based on whether or not the number of comments posted on the same topic exceeds a threshold. That is, in this case, the information processing device 1 determines that the extraction condition for a comment group is met for a topic on which the number of comments posted exceeds the threshold.

[0075] If the information processing device 1 determines that the extraction conditions are met (step S102; Yes), it extracts a group of comments that meet the predetermined conditions (step S103). If the information processing device 1 determines that the extraction conditions are not met (step S102; No), it returns to the processing of step S101.

[0076] Next, the information processing device 1 generates discussion content based on the extracted comment group (step S104), provides the generated discussion content (step S105), and ends the process.

[0077] [4. Modifications] In the above-described embodiment, the case where discussion content is generated based on comments corresponding to news articles has been described, but the present invention is not limited to this. For example, the present invention may be applied to various services where users U post word-of-mouth or reviews (i.e., comments), such as gourmet sites or product review sites, to generate discussion content.

[0078] [5. Effects] The information processing device 1 according to the embodiment described above includes an acquisition unit 42 that acquires comments posted on a predetermined topic, an extraction unit 43 that extracts a group of comments that satisfy predetermined conditions from the comments acquired by the acquisition unit 42, and a generation unit 44 that generates discussion content by editing the group of comments extracted by the extraction unit 43 into a discussion format.

[0079] Furthermore, the acquisition unit 42 acquires the comments posted to a plurality of news articles on the same topic, and the extraction unit 43 extracts a group of comments that satisfy a predetermined condition from the comments posted to the plurality of news articles.

[0080] The extraction unit 43 also extracts a group of comments that satisfy the discussion conditions of the hypothetical set theme. The extraction unit 43 also extracts comments that fall into categories set in the discussion conditions as a group of comments.

[0081] The extraction unit 43 also extracts a group of comments according to the attributes of the poster who posted the comment. The generation unit 44 also generates discussion content by rearranging the comments extracted as a group of comments according to a predetermined condition.

[0082] The generation unit 44 also generates discussion content that includes poster information about the poster who posted the comment. The information processing device 1 also includes a provision unit 45 that provides the discussion content generated by the generation unit 44, and the provision unit 45 provides the discussion content through a news site.

[0083] The generation unit 44 also inputs a prompt, which includes a group of comments and an instruction sentence for generating discussion content from the group of comments, into the sentence generation model to generate discussion content.

[0084] By performing any one or a combination of the above-described processes, the information processing device according to the present application can provide new content that utilizes comments.

[0085] [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. 9. Fig. 9 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device 1 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.

[0086] 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.

[0087] 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.

[0088] 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. 9, 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.

[0089] 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.

[0090] For example, when the computer 1000 functions as the information processing device 1 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.

[0091] Although some of the embodiments of the present application have been described in detail above with reference to the drawings, these are merely examples, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have undergone various modifications and improvements based on the knowledge of those skilled in the art.

[0092] [7. Other] Furthermore, among the processes described in the above embodiments and modifications, 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 known methods. 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.

[0093] 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.

[0094] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0095] 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]

[0096] 1. Information processing equipment 2. Communications Department 3 Storage section 4. Control section 31 Content information storage unit 32 Account information storage unit 33 Sentence generation model memory section 41 Distribution Department 42 Acquisition Department 43 Extraction part 44 Generation part 45 Providing Department 50 User Terminals

Claims

1. an acquisition unit that acquires comments posted on a predetermined topic; an extraction unit that extracts a group of comments that satisfy a predetermined condition from the comments acquired by the acquisition unit; a generation unit that generates discussion content by editing the group of comments extracted by the extraction unit into a discussion format; An information processing device comprising:

2. The acquisition unit Obtaining the comments posted to multiple news articles on the same topic; The extraction unit extracting the group of comments that satisfy the predetermined condition from the comments posted to the plurality of news articles; 2. The information processing device according to claim 1,

3. The extraction unit Extracting the group of comments that satisfy predetermined discussion conditions.

2. The information processing device according to claim 1,

4. The generation unit generating the discussion content including comments corresponding to each category of discussion; 4. The information processing device according to claim 3,

5. The generation unit generating the discussion content by rearranging the comments extracted as the group of comments according to a predetermined condition; 2. The information processing device according to claim 1,

6. The generation unit generating the discussion content in which the attributes of the poster who posted the comment satisfy a predetermined condition; 2. The information processing device according to claim 1,

7. The generation unit generating the discussion content including poster information of the poster who posted the comment; 2. The information processing device according to claim 1,

8. a providing unit that provides the discussion content generated by the generating unit; Equipped with The providing unit Providing said discussion content through news sites 2. The information processing device according to claim 1,

9. The generation unit A prompt including the group of comments and an instruction sentence for generating discussion content from the group of comments is input to a sentence generation model to generate the discussion content.

2. The information processing device according to claim 1,

10. 1. A computer-implemented information processing method, comprising: an acquisition step of acquiring comments posted on a predetermined topic; an extraction step of extracting a group of comments that satisfy a predetermined condition from the comments acquired by the acquisition step; a generation step of generating discussion content by editing the group of comments extracted by the extraction step into a discussion format; An information processing method comprising:

11. A retrieval procedure for retrieving comments posted on a given topic; an extraction step of extracting a group of comments that satisfy a predetermined condition from the comments acquired by the acquisition step; a generation step of generating discussion content by editing the group of comments extracted by the extraction step into a discussion format; An information processing program characterized by causing a computer to execute the above.

Images