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

Abstract

To make it easier for users to post comments.SOLUTION: An information processing device according to the present invention comprises an extraction unit, a generation unit, and a provision unit. The extraction unit extracts matching comments satisfying given conditions from among comments posted by users. The generation unit generates a posting format to be used when other users post comments on the basis of the comments extracted by the extraction unit. The provision unit provides the posting format generated by the generation unit.SELECTED DRAWING: Figure 3

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 user comments on 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, the conventional technology leaves room for improvement in terms of making it easier for users to post 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 make it easy for users to post 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 extraction unit, a generation unit, and a provision unit. The extraction unit extracts matching comments that meet predetermined conditions from among comments posted by users. The generation unit generates a posting format to be used when other users post comments based on the comments extracted by the extraction unit. The provision unit provides the posting format generated by the generation unit. [Effects of the Invention]

[0007] According to the present invention, it is possible to make it easier for users to post comments. [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 matching comment according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of a posting format according to the embodiment. [Figure 4] FIG. 4 is a block diagram illustrating an example of the configuration of the information processing device 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 diagram illustrating an example of information stored in a format information storage unit according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of a processing procedure for information processing 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 method is executed by 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] Incidentally, some news sites post comments on news articles from users U. For example, such comments by users U can be considered as part of the content.

[0014] Therefore, when the comments section of a news article becomes popular, it is expected that the number of page views (PV) of the corresponding news article will increase. On the other hand, it is not easy for beginners who are unfamiliar with posting comments to post a comment from scratch.

[0015] Therefore, the information processing device 1 according to the embodiment generates a posting format to be used when the user U posts a comment, based on comments posted in the past.

[0016] 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.

[0017] Next, the information processing device 1 acquires comments posted by the user U through the user terminal 50 (step S2). At this time, the information processing device 1 acquires comments on the news article provided to the user U through the user terminal 50. The information processing device 1 can also acquire, for example, a user rating for each comment. For example, the user rating includes items such as "I empathize," "I see," and "Hmm," and the user U selects the appropriate item for each comment.

[0018] Such comments are provided to other users U along with the distribution content. That is, every time a comment is posted, the comment section of the news article distributed as the distribution content is updated.

[0019] The information processing device 1 also performs the processes of steps S1 and S2 for multiple users U. Next, the information processing device 1 performs an extraction process for the acquired comments (step S3). The extraction process here is a process of extracting matching comments that meet predetermined conditions from the acquired comments. More specifically, the extraction process is a process of extracting matching comments that are comments that are suitable for a posting format.

[0020] The information processing device 1 extracts matching comments using a sentence generation model that generates answers to input sentences. The information processing device 1 generates a prompt including information about the acquired comment and an instruction sentence, and inputs the generated prompt to the sentence generation model.

[0021] The instruction sentence is, for example, "Please extract comments that satisfy the following conditions from the following comments." An example of the following conditions is as follows: (1) Highly rated comments. (2) The purpose and points are clear and easy to understand. (3) The comments have an introduction, development, twist, and conclusion. (4) The number of characters must be between 100 and 500. (5) The unpleasantness index of the posted comments is not high. (6) Your writing style is not similar to that of other users. (7) The poster has not been notified more than three times within the past six months.

[0022] Based on these prompts, the sentence generation model extracts matching comments that meet the conditions specified by the prompts. Then, based on the extracted matching comments, the information processing device 1 generates a posting format to be used when other users post comments (step S4).

[0023] Here, examples of matching comments and posting formats will be described with reference to Fig. 2 and Fig. 3. Fig. 2 is a diagram showing an example of matching comments according to an embodiment. Fig. 3 is a diagram showing an example of a posting format according to an embodiment.

[0024] The example shown in Figure 2 shows a case where the comment poster is an experienced swimmer who posted a comment about his or her own experience. The example also shows user ratings for the comment, such as "I empathize," "I see," and "Hmm."

[0025] A posting format is generated based on the comment. The example in Figure 3 shows a case where in addition to the posting format, a description of the posting format, the scope of use, the genre, etc. are also displayed.

[0026] 3, in the posting format, the edited portion edited by another user U is indicated as "#○○." In other words, in such a case, the other user U can post a comment in accordance with the posting format.

[0027] In this way, the information processing device 1 can make it easier for users to post comments by generating a posting format.

[0028] [2. Configuration example of information processing device] Next, a configuration example of the information processing device 1 will be described with reference to Fig. 4. Fig. 4 is a block diagram showing a configuration example of the information processing device 1 according to an embodiment. As shown in Fig. 4, the information processing device 1 has a communication unit 2, a storage unit 3, and a control unit 4.

[0029] 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.

[0030] 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, a format information storage unit 32, and a sentence generation model storage unit 33.

[0031] The content information storage unit 31 stores content information. Fig. 5 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.

[0032] 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.

[0033] 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.

[0034] The "Comment" field stores comments posted to the content identified by the corresponding content ID. The comments are those posted on news sites, but also include comments posted when posting news articles on social media.

[0035] Fig. 6 is a diagram showing an example of information stored in the format information storage unit 32 according to the embodiment. As shown in Fig. 6, the format information storage unit 32 stores information on items such as "format ID," "contributor," "format," "description," and "range of use" in association with each other.

[0036] The "Format ID" field stores the format ID. The format ID is an identifier for identifying each format. The "Contributor" field stores information about the poster of the comment that is the source of the format identified by the corresponding format ID.

[0037] The "Format" field stores the format identified by the corresponding format ID. Here, the format refers to the posting format. The "Description" field stores a description of the format identified by the corresponding format ID. The "Scope of Use" field stores information about the scope of application of the format identified by the corresponding format ID.

[0038] Returning to the explanation of FIG. 4, 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).

[0039] 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.

[0040] As shown in FIG. 4, 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.

[0041] The distribution unit 41 distributes distribution content to each user terminal 50. For example, the distribution unit 41 distributes news articles and comments on the news articles as distribution content.

[0042] 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.

[0043] 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.

[0044] The acquisition unit 42 acquires comments posted on news articles through the distribution content. Note that the acquisition unit 42 may also acquire comments posted on social media sites on news articles, for example.

[0045] The extraction unit 43 extracts matching comments that match predetermined conditions from among comments posted by users. Specifically, the extraction unit 43 extracts matching comments using a sentence generation model.

[0046] At this time, the extraction unit 43 extracts matching comments by inputting a prompt including the comment and an instruction sentence for extracting matching comments to the sentence generation model. That is, the extraction unit 43 extracts matching comments suitable for the posting format using the sentence generation model. Note that the above (1) to (7) are examples of conditions for matching comments. That is, the extraction unit 43 extracts matching comments based on the user's evaluation of the comment, elements related to the beginning, development, twist, and conclusion of the comment, etc.

[0047] The generation unit 44 generates a posting format to be used when another user U posts a comment, based on the matching comments extracted by the extraction unit 43. Specifically, the generation unit 44 generates the posting format using a sentence generation model.

[0048] For example, the generation unit 44 generates a prompt including a matching comment and an instruction sentence for generating a posting format from the matching comment, and inputs the prompt to the sentence generation model to generate a posting format.

[0049] The instruction sentence in this case is, for example, "Please generate a posting format that can be used when other users post comments from the following comments." At this time, the generation unit 44 inputs a prompt including an instruction document for generating an explanation of the posting format and its applicable range to the sentence generation model.

[0050] In this case, the answer sentence generated by the sentence generation model will include an explanation of the posting format and its scope of application. After completing the generation process for the posting format through the above process, the generation unit 44 registers information about the generated posting format in the format information storage unit 32.

[0051] The providing unit 45 provides the posting format generated by the generating unit 44. Before providing the posting format, the providing unit 45 obtains permission to use the posting format from the poster who posted the matching comment.

[0052] For example, when the generation unit 44 generates a new post format, the providing unit 45 obtains permission to use the post format from the user U who will be the poster of the matching comment on which the post format is based. The poster who has been granted permission to use the post format may be given an incentive. The incentive may be electronic money in an amount corresponding to the number of times the post format is used. In other words, by designing such an incentive, the incentive is paid when the post format is adopted, which makes it possible to encourage each user U to post comments.

[0053] When a poster approves the use of a posting format, the posting format can be provided. For example, the providing unit 45 may display a tag of the posting format for an original comment posted to a news article (i.e., a matching comment), and when such a tag is selected, the providing unit 45 may provide the corresponding posting format.

[0054] In other words, in such a case, user U can post his / her own comment through the posting format, referring to the original comment. This allows user U to post a comment that compares the original comment with his / her own opinion, etc. In the example shown in Figure 2, the "Format Available" button corresponds to the tag.

[0055] The providing unit 45 may also provide a posting format according to the browsing history of a news site by the user U to whom the posting format is to be provided. For example, when the browsing history of the news site by the user U falls within the usage range set for the posting format, the providing unit 45 provides the posting format to the user U.

[0056] 3, the first use range is “reading 10 sports articles in one month,” and the second use range is “limited to sports.” Of these, the providing unit 45 determines the first use range based on the browsing history of the user U.

[0057] Additionally, the providing unit 45 may provide the user U with a posting format of a poster who posted a matching comment that is the basis of the posting format used by the user U so that the posting format can be viewed.

[0058] [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. 7. Fig. 7 is a flowchart showing an example of the processing procedure of information processing according to the embodiment.

[0059] 7, first, the information processing device 1 acquires comments on content (step S101), and then determines whether the acquired comments satisfy a predetermined condition (step S102).

[0060] Specifically, the information processing device 1 determines whether the acquired comment satisfies the conditions for a matching comment. If the information processing device 1 determines that the comment satisfies the predetermined conditions (step S102; Yes), that is, if the comment is determined to be a matching comment, it generates a posting format (step S103). If the information processing device 1 determines that the acquired comment does not satisfy the predetermined conditions (step S102; No), it ends the process.

[0061] Next, the information processing device 1 determines whether or not permission has been obtained from the poster of the matching comment that is the basis of the posting format (step S104). If it is determined that permission has been obtained from the poster (step S104; Yes), the information processing device 1 makes the posting format public (step S105) and ends the process.

[0062] Furthermore, if the information processing device 1 determines in step S104 that the permission from the poster has been denied (step S104; No), it skips the process of step S105 and ends the process.

[0063] [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.

[0064] [5. Effects] The information processing device 1 according to the embodiment described above includes an extraction unit 43 that extracts matching comments that meet predetermined conditions from among the comments posted by users, a generation unit 44 that generates a posting format to be used when other users post comments based on the matching comments extracted by the extraction unit 43, and a provision unit 45 that provides the posting format generated by the generation unit 44.

[0065] The extraction unit 43 extracts matching comments by inputting a prompt including a comment and an instruction sentence for extracting matching comments to the sentence generation model. The extraction unit 43 also extracts matching comments based on user evaluations of the comments.

[0066] The extracting unit 43 extracts matching comments based on elements related to the beginning, development, twist, and conclusion of the comments. The providing unit 45 provides a posting format after obtaining permission from the poster who posted the matching comment.

[0067] The extraction unit 43 also extracts matching comments from comments posted to the news site, and the provision unit 45 provides a posting format through the news site. The provision unit 45 also displays a tag of the posting format for the matching comment posted to the news site, and provides the posting format when the tag is selected. The provision unit 45 also provides a posting format according to the browsing history of the news site of the user to whom the posting format is to be provided.

[0068] By performing any one or a combination of the above-described processes, the information processing device according to the present application can simplify the process of users posting comments.

[0069] [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 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] [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.

[0077] 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.

[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 Unit 31 Content information storage unit 32 Format 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 extraction unit that extracts matching comments that meet predetermined conditions from among comments posted by users; a generation unit that generates a posting format to be used when other users post the comments, based on the matching comments extracted by the extraction unit; a providing unit that provides the posting format generated by the generating unit; An information processing device comprising:

2. The extraction unit A prompt including the comment and an instruction sentence for extracting the matching comment is input to a sentence generation model, thereby extracting the matching comment.

2. The information processing device according to claim 1,

3. The extraction unit Extracting the matching comments based on user ratings of the comments.

2. The information processing device according to claim 1,

4. The extraction unit Extracting the matching comments based on elements related to the beginning, development, turn, and conclusion of the comments.

2. The information processing device according to claim 1,

5. The providing unit Providing the posting format after obtaining permission from the poster who posted the matching comment.

2. The information processing device according to claim 1,

6. The extraction unit extracting the matching comments from comments posted on a news site; The providing unit Providing said posting format through said news site 2. The information processing device according to claim 1,

7. The providing unit Displaying a tag of the posting format for the matching comment posted on the news site, and providing the posting format when the tag is selected.

7. The information processing device according to claim 6,

8. The providing unit To provide the posting format according to the browsing history of the news site of the user to whom the posting format is to be provided.

7. The information processing device according to claim 6,

9. 1. A computer-implemented information processing method, comprising: an extraction step of extracting matching comments that meet predetermined conditions from among comments posted by users; a generating step of generating a posting format to be used when other users post the comments based on the comments extracted by the extracting step; a providing step of providing the posting format generated by the generating step; An information processing method comprising:

10. An extraction step of extracting matching comments that meet predetermined conditions from among comments posted by users; a generating step of generating a posting format to be used when other users post the comments, based on the comments extracted by the extracting step; a providing step of providing the posting format generated by the generating step; An information processing program characterized by causing a computer to execute the above.

Images