Information processing apparatus, information processing method, and information processing program

Abstract

To provide high-value-added summary content.SOLUTION: An information processing apparatus according to the present invention includes an extraction unit and a provision unit. The extraction unit extracts a concerned party comment which is a comment of a concerned party related to a theme among comments corresponding to a predetermined theme. The providing unit provides a summary content that summarizes the involved party comment extracted by the extracting unit.SELECTED DRAWING: Figure 2

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 technologies for providing various web media such as news sites, etc. In this technical field, a technology for providing summary content that summarizes comments posted on news articles has been disclosed (for example, see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2024-25959 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional technology does not mention anything about selecting the posters of the comments to be summarized, and there is room for improvement in providing high-value-added summarized 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 are capable of providing summary content with high added value. [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 and a provision unit. The extraction unit extracts party comments, which are comments from parties related to a given theme, from among comments corresponding to the theme. The provision unit provides summary content that summarizes the party comments extracted by the extraction unit. [Effects of the Invention]

[0007] According to the present invention, it is possible to provide summary content with high added value. [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 summary 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 a content storage unit according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of a comment from a party according to the embodiment. [Figure 6] FIG. 6 is a flowchart illustrating an example of a processing procedure of the reception processing according to the embodiment. [Figure 7] FIG. 7 is a flowchart illustrating an example of a processing procedure of the providing 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] 1 is an information processing device that operates various web media such as news sites, etc. The information processing device 1 is realized by, for example, a cloud system or a server.

[0012] The user terminal 100 shown in Fig. 1 is a terminal device owned by a user U. For example, the user U operates the user terminal 100 to provide the user U with various contents such as news articles through various web media. Note that while Fig. 1 illustrates an example in which the user terminal 100 is a smartphone, the user terminal 100 may be other devices such as a PC (Personal Computer).

[0013] As shown in FIG. 1, the user terminal 100 can post a comment on a content (for example, a news article) provided by the information processing device 1 through a news site (step S1).

[0014] The information processing device 1 accepts comments posted by each user U on a news article, and provides the comments posted by each user U together with the news article as news content to each user U.

[0015] That is, the information processing device 1 provides each user U with a news article including a comment posted by that user as content. In this way, the information processing device 1 receives comments from each user U on each news article, thereby aggregating the comments and the like from each user U on each news article.

[0016] In the present disclosure, the information processing device 1 provides content that aggregates comments posted by users U from parties related to the theme of a news article, thereby providing content with high added value.

[0017] Specifically, as shown in FIG. 1, the information processing device 1 extracts, from among the comments posted by each user U, comments by the parties involved that are related to a predetermined theme (step S2).

[0018] As will be described later, the information processing device 1 extracts comments from the parties using a text generation model such as GPT. For example, if the theme is "real estate investment," the parties may be users U who are actually investing in real estate, users U who have invested in real estate in the past, or businesses that sell real estate for investment.

[0019] For example, the information processing device 1 uses a sentence generation model to analyze the comments of each user U and determine whether the user U is a party to the investment. Specifically, the information processing device 1 inputs a prompt to the sentence generation model, such as, "Please extract comments from the following comments that are from parties to the real estate investment," along with the comments of each user.

[0020] Then, the information processing device 1 extracts the comments extracted by the sentence generation model in response to the input prompt as party comments. Subsequently, the information processing device 1 generates summary content that summarizes the extracted party comments (step S3).

[0021] For example, the information processing device 1 generates summary content using a sentence generation model. Specifically, the information processing device 1 inputs a prompt such as "Please generate content that summarizes the extracted comments of the parties involved" to the sentence generation model.

[0022] Then, the information processing device 1 generates the sentence output by the sentence generation model as summary content. After that, the information processing device 1 provides the generated summary content to the user terminals 100 of other users U, etc. (step S4).

[0023] Next, an example of summary content will be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of summary content according to an embodiment. As shown in Fig. 2, the summary content is content including the theme of the summary content, an outline, experiencer information, Q&A information, etc. The experiencer information corresponds to an example of summary content, and the Q&A information corresponds to an example of question and answer content.

[0024] The information on those who have experienced the property is a summary of the comments made by the parties involved. The information on those who have experienced the property is a summary of the actual experiences and opinions of those who have actually invested in the property.

[0025] In this way, by providing content including experiencer information, the information processing device 1 can deliver the experiences and honest feedback of the experiencers to other users U. In other words, the information processing device 1 can provide summary content that aggregates the experiences of the people involved, thereby providing summary content with high added value.

[0026] The Q&A information is information about general doubts and questions related to a theme and their answers. For example, the information processing device 1 extracts doubts and questions and their answers from each news article and its comments.

[0027] Specifically, the information processing device 1 generates Q&A information using a sentence generation model, and inputs instruction prompts such as "Please tell me questions and answers about real estate investment" from the following news articles and comments into the sentence generation model.

[0028] The information processing device 1 then generates sentences output from the sentence generation model as Q&A information. In this way, the information processing device 1 can provide the user U with appropriate questions and answers to those questions by providing content including Q&A information. In other words, by providing these contents, the information processing device 1 can promote the user U's understanding of the topic.

[0029] [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.

[0030] 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.

[0031] 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 includes a content storage unit 31 and a model storage unit 32.

[0032] The content storage unit 31 stores content. In the present disclosure, the content is a news article distributed through a news site. Fig. 4 is a diagram showing an example of information stored in the content storage unit 31 according to the embodiment.

[0033] As shown in FIG. 4, the content storage unit 31 stores information items such as "content ID," "content body," "theme," and "comments" in association with one another.

[0034] The "Content ID" field stores an identifier for identifying each piece of content. The "Content Body" field stores the body of the content (news article) identified by the corresponding content ID. The content body may include a title, summary, etc.

[0035] The "Theme" item stores information about the theme of the content identified by the corresponding content ID. For example, the theme is determined based on keywords extracted from the content body. Information processing related to the theme will be described later.

[0036] The "comment" item stores comments from each user U regarding the content identified by the corresponding content ID.

[0037] Returning to the explanation of FIG. 3, the model storage unit 32 will be explained. The model storage unit 32 stores a model. The model is, for example, a sentence generation model such as GPT. The sentence generation model is a model trained to generate a natural language sentence response to an input natural language sentence.

[0038] Next, a description will be given of the control unit 4. 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).

[0039] As shown in Fig. 2, the control unit 4 includes a reception unit 41, a classification 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. 2, 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. 2, and may be other connection relationships.

[0040] The reception unit 41 receives comments on content from each user U through each user terminal 100. More specifically, the reception unit 41 receives comments from the user U on each news article provided to each user terminal 100 through a news site by the provision unit 45, which will be described later. The reception unit 41 stores the comments received from each user U in the content storage unit 31.

[0041] The classification unit 42 classifies the news articles by theme. Specifically, the classification unit 42 uses text mining technology or the like to extract key keywords from each news article. For example, the classification unit 42 identifies the theme of each news article by identifying words and phrases that appear frequently in each news article, and classifies each news article by theme.

[0042] Specifically, the classification unit 42 sets a theme based on keywords extracted from news articles using text mining technology, etc. If the keywords extracted from the news articles are "real estate," "investment," and "rental," the classification unit 42 sets the theme as "real estate investment."

[0043] Next, the classification unit 42 evaluates the relationship value between each keyword extracted from the news article and the theme, and calculates a score. For example, if the keywords "new construction," "price," and "rising prices" have a high relationship value with "real estate investment," the classification unit 42 sets a high score for each keyword with respect to the theme.

[0044] Then, if the sum of the relation values ​​of the keywords exceeds a certain threshold, the classification unit 42 classifies the news article into the corresponding theme.

[0045] The extraction unit 43 extracts comments from parties related to a specific theme from among comments corresponding to the theme. First, the extraction unit 43 extracts news articles corresponding to a specific theme, and then extracts comments from parties related to the theme from among comments posted on the extracted news articles.

[0046] The extraction unit 43 extracts the comments of the parties using a sentence generation model. For example, in such a case, the extraction unit 43 inputs a prompt such as, "Please extract comments of the parties on the following themes from the following comments," together with the comments of each user U.

[0047] In this case, the extraction unit 43 may extract a comment that indicates that the commenter is a party to the transaction as a party comment. An example of a party comment will now be described with reference to Fig. 5. Fig. 5 is a diagram showing an example of a party comment according to the embodiment.

[0048] As shown in Figure 5, in a comment by a party, the first part A1 may make it clear that the person is a party. In other words, in such a comment by a party, it is possible to determine whether the comment is made by a party by analyzing the first part A1.

[0049] That is, the extraction unit 43 can extract the party comments with high accuracy by extracting the comments that state that the commenter is a party to the matter as the party comments.

[0050] In addition to the above, the extraction unit 43 may extract comments that describe specific experiences or knowledge as related party comments. The extraction unit 43 may also extract related party comments based on the score of the account of the comment poster.

[0051] In this case, a score is calculated for each user U's account for each item such as the credibility of the comment, the reliability of the comment, and the logic of the comment. The extraction unit 43 may then extract party comments from among the comments of accounts whose scores exceed a threshold. In this way, the extraction unit 43 can ensure the reliability of party comments by extracting party comments based on the account scores.

[0052] The generation unit 44 generates summary content that summarizes the comments of the parties extracted by the extraction unit 43. The generation unit 44 uses a sentence generation model to generate a summary sentence that outlines the theme, summary content of the comments of the parties, and Q&A information.

[0053] The generation unit 44 inputs a prompt such as "Please briefly explain the outline of the following theme" to the sentence generation model, and generates the response as a summary sentence that outlines the theme. The generation unit 44 also inputs a prompt such as "Please briefly summarize the following comments in accordance with the following theme" to the sentence generation model, along with the comments of the parties involved, and generates the response as summary content. In this case, the generation unit 44 may also generate the summary content by inputting a prompt such as "Please list points that are particularly noteworthy among the following comments" along with the comments of the parties involved. The generation unit 44 may also generate the summary content by inputting a prompt such as "Please summarize the comments of the participants from the following comments and clarify similarities and differences" along with the comments of the parties involved.

[0054] When generating Q&A information, the generation unit 44 first inputs a prompt to the sentence generation model, such as, "Please list specific doubts and questions related to the theme from these sentences," along with news articles and their comments corresponding to the theme, to create a list of doubts and questions.

[0055] Next, the generation unit 44 generates questions and answers related to the theme by inputting news articles and comments corresponding to the theme, as well as prompts such as "Please tell me specific questions and their answers from these sentences."

[0056] Next, the generation unit 44 inputs prompts such as "Please tell me the particularly important points among the questions and answers related to the theme" into the sentence generation model, and generates sentences that summarize the important points based on the answers.

[0057] The generation unit 44 then inputs prompts such as "Please summarize the questions and answers and organize the overall flow" to the sentence generation model, and generates the answers as Q&A information. Note that the above prompts are merely examples and are not limiting.

[0058] The providing unit 45 provides summary content that summarizes the party comments extracted by the extracting unit 43. Specifically, the providing unit 45 provides the summary content generated by the generating unit 44 to the user terminal 100 of each user U.

[0059] For example, the providing unit 45 may provide the summary content as one of the news articles provided through a news site, or may provide the summary content as supplementary information to the news article.

[0060] For example, when providing summary content as supplementary information to a news article, the providing unit 45 provides the summary content that matches the theme of the news article on the same screen as the news article.

[0061] The providing unit 45 may also cooperate with a search site to provide summary content. For example, the providing unit 45 may provide summary content on a theme corresponding to a search query entered by the user U as a search result.

[0062] In this way, the providing unit 45 can provide summary content that summarizes the comments of the parties, thereby providing the experiences of the parties to other users U. In other words, by providing summary content, the providing unit 45 can provide content with high added value.

[0063] [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 the processing procedure of the reception processing according to the embodiment. Fig. 7 is a flowchart showing an example of the processing procedure of the provision processing according to the embodiment. Note that the processing shown below is repeatedly executed by the information processing device 1 at a predetermined cycle.

[0064] 6, the information processing device 1 distributes a news article to each user U (step S101). Next, the information processing device 1 accepts comments on the news article from the user U (step S102). Then, the information processing device 1 updates the comment section of the corresponding news article (step S103) and ends the process.

[0065] Next, the processing flow of the provision processing will be described with reference to Fig. 6. As shown in Fig. 6, the information processing device 1 first classifies news articles by theme (step S111). Next, the information processing device 1 sets the theme for which summary content is to be generated (step S112).

[0066] Next, the information processing device 1 extracts comments from the parties related to the theme from the news articles corresponding to the set theme (step S113). Next, the information processing device 1 generates summary content by summarizing the extracted comments from the parties according to the theme (step S114).

[0067] Then, the information processing device 1 provides the generated summary content to each user U (step S115), and ends the process.

[0068] [4. Modifications] In the above-described embodiment, the information processing device 1 extracts comments from the parties involved from comments posted to a news article, but the present invention is not limited to this. For example, the extraction target may be comments posted in the comment section of the social networking site to which the news article is posted.

[0069] [5. Effects] The information processing device 1 according to the embodiment includes an extraction unit 43 that extracts party comments, which are comments from parties related to a specific theme, from among comments corresponding to the theme, and a provision unit 45 that provides summary content that summarizes the party comments extracted by the extraction unit 43.

[0070] The extraction unit 43 also extracts, as a party comment, a comment that indicates that the person is a party to the comment.The extraction unit 43 also extracts, as a party comment, a comment that indicates that the person is a party to the comment at the beginning of the comment.

[0071] The extraction unit 43 also extracts party comments based on the score information of the poster who posted the comment. The information processing device 1 also includes a classification unit 42 that classifies news articles by theme, and the extraction unit 43 extracts party comments from comments posted to news articles on the same theme.

[0072] The providing unit 45 also provides question and answer content including questions on the anticipated theme and answers to the questions. The information processing device 1 also includes a generating unit 44 that generates summary content, and the generating unit 44 generates the summary content from the comments of the parties using a sentence generation model trained to generate answer sentences for input sentences.

[0073] By performing any one or a combination of the above-described processes, the information processing device according to the present application can provide high-value-added content.

[0074] [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.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] [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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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]

[0085] 1. Information processing equipment 2. Communications Department 3 Storage section 4. Control Unit 31 Content storage unit 32 Model memory section 41 Reception 42 Classification Department 43 Extraction part 44 Generation part 45 Providing Department 100 user terminals

Claims

1. an extraction unit that extracts, from among comments corresponding to a predetermined theme, related-party comments that are comments from related parties related to the theme; a providing unit that provides summary content that summarizes the comments of the party extracted by the extracting unit; An information processing device comprising:

2. The extraction unit Extracting the comment in which the person is stated as a party comment 2. The information processing device according to claim 1,

3. The extraction unit A comment that states at the beginning that the person is a party to the comment is extracted as a party comment.

3. The information processing device according to claim 2, wherein:

4. The extraction unit Extracting the comments of the parties based on score information of the posters who posted the comments.

2. The information processing device according to claim 1,

5. a classification unit for classifying news articles by said theme; Equipped with The extraction unit Extracting the comments from the parties posted to news articles with the same theme.

2. The information processing device according to claim 1,

6. The providing unit To provide question and answer content that includes anticipated questions on the above-mentioned theme and answers to those questions.

2. The information processing device according to claim 1,

7. a generation unit for generating the summary content; Equipped with The generation unit generating the summary content from the comments of the parties using a sentence generation model trained to generate response sentences to input sentences; 2. The information processing device according to claim 1,

8. 1. A computer-implemented information processing method, comprising: an extraction step of extracting party comments, which are comments from parties related to a predetermined theme, from among comments corresponding to the theme; a providing step of providing summary content that summarizes the comments of the party extracted by the extracting step; An information processing method comprising:

9. an extraction step of extracting party comments, which are comments from parties related to a predetermined theme, from among comments corresponding to the theme; a providing step of providing summary content that summarizes the comments of the parties extracted by the extracting step; An information processing program characterized by causing a computer to execute the above.

Images