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

Abstract

To appropriately provide users with questions and answers regarding news articles. [Solution] The information processing device according to the present invention comprises: an acquisition unit that collects comments on news articles; a generation unit that estimates pairs of events that users are curious about and answers to those questions based on the collected comments, and generates QA content from the estimated question-answer pairs; and a provision unit that provides the QA content together with the news articles.

Description

Technical Field

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

Background Art

[0002] Conventionally, technologies related to information distribution via the Internet are known. As an example of such a technology, there is known a technology for providing comments posted by users on news articles to other users who have viewed the news articles.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, when a user is viewing a news article, a question regarding the news article may arise. In such a case, the user viewing the news article browses related articles or posts the question as a comment. Therefore, it is required to appropriately provide questions and answers regarding the news article for the user.

[0005] The present application has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of appropriately providing questions and answers regarding a news article for a user.

Means for Solving the Problems

[0006] The information processing device according to the present invention comprises: an acquisition unit for collecting comments on news articles; a generation unit for estimating pairs of events that users are curious about and answers to those questions based on the collected comments, and generating QA content from the estimated pairs of questions and answers; and a provision unit for providing the QA content together with the news articles. [Effects of the Invention]

[0007] According to one embodiment, the system has the effect of appropriately providing users with questions and answers regarding news articles. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows the process performed by the information processing device according to the embodiment. [Figure 2] Figure 2 shows an example of how QA content is displayed. [Figure 3] Figure 3 shows an example of how QA content is displayed. [Figure 4] Figure 4 is a block diagram showing an example configuration of an information processing system according to the embodiment. [Figure 5] Figure 5 shows an example of the configuration of an information processing device according to the embodiment. [Figure 6] Figure 6 shows an example of user information. [Figure 7] Figure 7 shows an example of article information. [Figure 8] Figure 8 shows an example of comment information. [Figure 9] Figure 9 shows an example of QA content information. [Figure 10] Figure 10 is a flowchart showing the processing procedure of the information processing device executed by the information processing device according to the embodiment. [Figure 11] Figure 11 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, embodiments for implementing the information processing device, information processing method, and information processing program according to the present application (hereinafter referred to as "embodiments"). Note that these embodiments do not limit the information processing device, information processing method, and information processing program according to the present application. Furthermore, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.

[0010] (Embodiment) First, the processing performed by the information processing device according to the embodiment will be explained using Figure 1. Figure 1 is a diagram showing the processing performed by the information processing device according to the embodiment. Note that Figure 1 shows an example of the operation of the information processing system S including the information processing device 1 according to the embodiment.

[0011] As shown in Figure 1, the information processing system S according to this embodiment includes an information processing device 1 and a user terminal 100.

[0012] As shown in Figure 1, the information processing system S according to this embodiment collects comments from news articles, extracts questions based on the collected comments, generates Q&A content that shows the questions and answers to those questions, and provides the Q&A content together with the news articles.

[0013] Specifically, the information processing device 1 collects comments from news articles (step S1). For example, the information processing device 1 may collect comments Cm from one news article, or it may collect comments Cm from multiple news articles. The events (content) of the news articles may be events that indicate categories such as sports, politics, finance, events, etc., or events that indicate unique events such as a job hunting event held in AA on month B.

[0014] Subsequently, based on the collected comments, the information processing device 1 estimates pairs of events that the user is doubtful about and answers to those doubts, and generates QA content from the estimated pairs of questions and answers (step S2). For example, the information processing device 1 inputs, together with the collected comment Cm, a prompt instructing the estimation of pairs of events that the user is doubtful about and answers to those doubts to the generation AI, and uses the pairs of questions and answers output from the generation AI as estimation results. For example, when there are comments such as "I don't understand the part AA in the article" in the comment Cm, or explanatory comments or supplementary comments regarding some content in the article, the information processing device 1 estimates the corresponding part in the comment as a question. At this time, the information processing device 1 may estimate a plurality of questions, and in this case, may estimate answers for each question. The information processing device 1 identifies the comment Cm that mentions an answer to the question from the collected comment Cm, and generates an answer to the question. That is, the information processing device 1 estimates pairs of the user's questions regarding news articles and answers to those questions, and generates QA content.

[0015] As an example of a prompt for generating QA content, there is "The following are comments on a news article. From the following comments, estimate pairs of events that the user is doubtful about and answers to those doubts, and create QA based on the estimated pairs of questions and answers. XXXXXXX (the following comments) XXXXX".

[0016] In addition, the information processing device 1 estimates, as questions, technical terms with insufficient explanations, sentences with insufficient sentence structures, etc. by performing natural language processing on the collected comment Cm. Also, when the comment Cm contains information referring to another news article (sentences such as links, "introduced in a past article", or "an incident that occurred at the meeting on the A-th day of the B-th month"), the information processing device 1 estimates such information as a question. The information processing device 1 may estimate a plurality of questions.

[0017] In addition, the information processing device 1 may generate an answer to a question based on the result of natural language processing of the comment Cm. Note that when the information processing device 1 generates a plurality of answers with different semantic contents from a plurality of comments Cm for one question, all the plurality of answers may be provided to the user as the generation result. Also, the information processing device 1 generates an answer to a question based on the result of natural language processing of the comment Cm. Further, the information processing device 1 may perform natural language processing and generate an answer by narrowing down to explanatory comments or supplementary comments among the comments Cm.

[0018] Note that the information processing device 1 may estimate the answer first and then estimate the question. For example, the information processing device 1 may estimate the content that is the topic from the collected comment Cm, and estimate the question based on the estimated content. Also, the prompt for generating the QA content may include that the answer may be estimated first and then the question may be estimated.

[0019] Subsequently, the information processing device 1 provides the QA content indicating the question and the answer to the user terminal 100 together with the news article (step S3).

[0020] For example, as shown in FIG. 1, when the information processing device 1 generates a plurality of QA contents, it displays them side by side. The information processing device 1 displays the QA content C2 in consideration of the order. The information processing device 1 displays the QA content C2 on the user terminal 100 side by side with the news article C1 and the comment Cm. Specifically, the information processing device 1 displays the QA content C2 side by side at the upper part (the head part) of the news article C1. Thereby, the user can check the QA content C2 before reading the news article. Note that the information processing device 1 may display the QA content C2 between the news article C1 and the comment Cm. Also, the information processing device 1 may display the QA content C2 displayed in the news article C1 side by side in a plurality of news articles related to the news article C1.

[0021] Here, with reference to Figures 2 and 3, other examples of how QA content C2 is displayed will be described. Figures 2 and 3 are diagrams showing examples of how QA content is displayed.

[0022] As shown in Figure 2, the information processing device 1 may display the QA content C2 in a ranked order. When generating multiple QA content items, the information processing device 1 calculates a question score indicating the magnitude of the question and displays the ranking based on the question score. For example, the information processing device 1 calculates the question score from the context of the comment Cm and displays questions with higher scores in the ranking. The information processing device 1 extracts the context contained in each collected comment and calculates a higher score for an expression the more context (e.g., the number of expressions) is extracted. Also, as shown in Figure 3, for example, the information processing device 1 displays the QA content C2 as supplementary information below the related article content in the article list. Note that in the ranking display of QA content C2, only the top 3 QA content items are shown, but this is not limited to that.

[0023] In the above embodiment, it is preferable that the information processing device 1 collects keywords of popular (trending) events and comments on corresponding news articles. For example, the information processing device 1 collects comments on multiple news articles corresponding to keywords of popular events. In this case, the information processing device 1 extracts articles in which comments corresponding to keywords of popular events have been posted and collects the comments. The information processing device 1 displays QA content C2 on multiple news articles corresponding to keywords of popular events.

[0024] In this disclosure, questions are extracted based on comments on news articles, and Q&A content is generated that provides answers to those questions, allowing users to review the Q&A content. This enables users to get a general understanding of the questions they have. Furthermore, even if the information contained in the news article is insufficient, the Q&A content can supplement the missing information, eliminating the need for users to read other articles to obtain additional information. Thus, the information processing device 1 can appropriately provide users with questions and answers regarding news articles.

[0025] Next, an example of the configuration of the information processing system S according to the embodiment will be described using Figure 4. Figure 4 is a block diagram showing an example of the configuration of the information processing system S according to the embodiment. As shown in Figure 4, in the information processing system S according to the embodiment, the information processing device 1 and a plurality of user terminals 100 are connected to a network N by wire or wireless. The network N is, for example, a network such as the Internet, a WAN (Wide Area Network), or a LAN (Local Area Network).

[0026] The information processing device 1 is a server device that executes the information processing method according to the embodiment. The information processing device 1 collects comments on news articles, extracts questions based on the comments, generates answers to the questions, and provides the questions and answers together with the news articles.

[0027] Furthermore, the information processing device 1 is an information processing device that interacts with multiple user terminals 100 and provides various API (Application Programming Interface) services for various applications (hereinafter referred to as "apps") and various data to the multiple user terminals 100, and is realized by a server device or a cloud system.

[0028] Furthermore, the information processing device 1 may be an information processing device that provides some kind of web service online to multiple user terminals 100. For example, the information processing device 1 may provide services such as internet connection, search services, SNS (Social Networking Service), e-commerce (EC), electronic payment, online games, online banking, online trading, accommodation / ticket reservations, video / music distribution, news, maps, route search, route guidance, route information, service information, and weather forecasts as web services. In practice, the information processing device 1 may cooperate with various servers that provide the above-mentioned web services and act as an intermediary for web services, or it may be responsible for processing web services.

[0029] User terminal 100 is a terminal device owned by a user who is a target recipient of news articles and related information. User terminal 100 can be any type of terminal device, such as a smartphone, desktop PC, notebook PC, or tablet PC. User terminal 100 transmits various types of information to the information processing device 1, etc., and receives information provided by the information processing device 1, etc.

[0030] Next, with reference to Figure 5, an example of the configuration of the information processing device 1 will be described.

[0031] Figure 5 shows an example of the configuration of an information processing device 1 according to an embodiment. As shown in Figure 5, the information processing device 1 has a communication unit 2, a control unit 3, and a storage unit 4. The control unit 3 includes an acquisition unit 31, a generation unit 32, and a provision unit 33. The storage unit 4 stores user information 41, article information 42, comment information 43, and QA content information 44.

[0032] The communication unit 2 is implemented, for example, by a NIC (Network Interface Card). The communication unit 2 is connected to the network by wire or wireless connection.

[0033] The control unit 3 is a controller and is implemented by a processor such as a CPU (Central Processing Unit) or MPU (Micro Processing Unit) executing various programs (corresponding to an example of an information processing program) stored in the memory device inside the information processing device 1, using RAM or the like as a working area. Alternatively, the control unit 3 is a controller and may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), FPGA (Field Programmable Gate Array), or GPGPU (General Purpose Graphic Processing Unit).

[0034] The memory unit 4 is implemented by, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory, or by storage devices such as hard disks and optical discs.

[0035] User information 41 is information about the user.

[0036] Figure 6 shows an example of user information 41. As shown in Figure 6, user information 41 includes items such as "User ID," "Attribute Information," and "Behavioral Information."

[0037] "User ID" is identification information that identifies a user. "Attribute information" is information about the user's attributes. Attribute information includes, for example, psychographic attributes and demographic attributes. "Behavioral information" is information about the user's behavioral history, including the history of various actions such as search behavior, purchase behavior, visit behavior, news article viewing behavior, and news article evaluation behavior. Evaluation behavior includes, for example, the action of selecting whether to be positive or negative about a news article, or the action of posting comments on a news article.

[0038] Article information 42 is information about a news article.

[0039] Figure 7 shows an example of article information 42. As shown in Figure 7, article information 42 includes items such as "article ID," "article content," and "QA information."

[0040] "Article ID" is identification information that identifies a news article. "Article Content" is information about the content of the news article, including text, image information, and comments on the news.

[0041] Comment information 43 is information about the comment.

[0042] Figure 8 shows an example of comment information 43. As shown in Figure 8, comment information 43 includes items such as "Comment ID" and "Comment Content".

[0043] "Comment ID" is identification information that identifies a comment. "Comment Content" is information about the content of the comment, such as text information.

[0044] QA Content Information 44 is information about QA content.

[0045] Figure 9 shows an example of QA content information 44. As shown in Figure 9, QA content information 44 includes items such as "QA content ID" and "QA content details".

[0046] "QA Content ID" is identification information that identifies the QA content. "QA Content Details" is information about the content of the QA content, such as the hypothesized question and the answer to that question.

[0047] Note that QA content information 44 may be included in article information 42.

[0048] Next, we will describe the functions of the control unit 3 of the information processing device 1 (acquisition unit 31, generation unit 32, and provision unit 33).

[0049] The acquisition unit 31 acquires various types of information. The acquisition unit 31 acquires news articles. The acquisition unit 31 also accepts ratings and comments on news articles from users who distributed the news articles. The acquisition unit 31 also collects comments on news articles. Preferably, the acquisition unit 31 collects comments on news articles corresponding to keywords of popular (trending) events. For example, the acquisition unit 31 collects comments on multiple news articles corresponding to keywords of popular events. In this case, the acquisition unit 31 extracts articles in which comments corresponding to keywords of popular events have been posted and collects the comments.

[0050] The generation unit 32 estimates pairs of events that users are curious about and their answers based on the collected comments, and generates Q&A content from the estimated question-answer pairs. For example, the generation unit 32 inputs a prompt to the generation AI, along with the collected comments, instructing it to estimate pairs of events that users are curious about and their answers, and uses the questions output by the generation AI as the estimation result. The generation unit 32 may estimate multiple questions, in which case it generates an answer for each question and generates multiple Q&A contents. Specifically, if the comments include comments such as "I don't understand the AA part in the article," or explanatory or supplementary comments about parts of the article, the generation unit 32 estimates the relevant parts of the comments as questions. In addition, the generation unit 32 uses natural language processing on the collected comments to estimate insufficiently explained technical terms or poorly structured sentences as questions. Furthermore, the generation unit 32 infers information that refers to another news article (such as links or phrases like "as mentioned in a previous article" or "an incident that occurred at a meeting on A / B") as a question. The generation unit 32 identifies comments that mention the question from the collected comments and infers the answer to the question. In other words, the generation unit 32 infers pairs of the user's question about the news article and the answer to that question, and generates Q&A content.

[0051] Furthermore, the generation unit 32 may generate answers to questions based on the results of natural language processing of the comments. If multiple answers with different meanings are generated from multiple comments for a single question, the generation unit 32 may provide all of these answers to the user as generated results. The generation unit 32 also generates answers to questions based on the results of natural language processing of the comments. Additionally, the generation unit 32 may focus on natural language processing of explanatory and supplementary comments to generate answers.

[0052] Furthermore, the generation unit 32 may first estimate the answer and then estimate the question. For example, the generation unit 32 may estimate the topic of discussion from the collected comments Cm and then estimate the question based on the estimated content.

[0053] The generation unit 32 may calculate a degree of doubt indicating the magnitude of a question when generating multiple QA contents and provide this to the user in a ranking display. For example, the generation unit 32 extracts expressions contained in each collected comment and calculates that the more expressions extracted, the higher the degree of doubt regarding that expression. The generation unit 32 may also calculate the degree of doubt from the context of the comment Cm and provide the user with questions that have a higher degree of doubt as the top of the ranking.

[0054] The provision unit 33 provides Q&A content, which includes questions and answers, to the user terminal 100 along with news articles. If the generation unit generates multiple Q&A content items, the provision unit 33 displays the multiple Q&A content items side by side.

[0055] For example, as shown in Figure 1, the display unit 33 displays the QA content C2 alongside the news article C1 on the user terminal 100. Specifically, the display unit 33 displays the QA content C2 alongside the news article C1 at the top (beginning) of the article.

[0056] Furthermore, the provisioning unit 33 displays multiple pieces of content in a ranked order based on their level of suspicion.

[0057] The provision section 33 may provide QA content C2 as supplementary information below the list of related articles. The provision section 33 may also provide QA content C2 between related article contents.

[0058] Furthermore, the provisioning unit 33 displays QA content in multiple news articles. For example, the provisioning unit 131 may display QA content C2 in multiple news articles corresponding to keywords of popular events.

[0059] Next, the processing procedure of the information processing device 1 according to the embodiment will be described using Figure 10. Figure 10 is a flowchart showing the processing procedure of the information processing device 1 according to the embodiment.

[0060] As shown in Figure 10, the control unit 3 first collects and obtains comments on the news article (step S101).

[0061] Next, the control unit 3 estimates questions and answers based on the collected comments and generates QA content that shows the questions and answers (step S102).

[0062] Next, the control unit 3 provides the QA content along with the news article to the user terminal 100 (step S103), and then terminates the process.

[0063] 〔others〕 Furthermore, some of the processes described as being performed automatically in the above embodiments can be performed manually. Alternatively, all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above documents and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0064] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0065] For example, some or all of the storage unit 4 shown in Figure 5 may be stored in a storage server or the like, rather than being held by each device. In this case, each device obtains various information by accessing the storage server.

[0066] [Hardware configuration] Furthermore, the information processing device 1 according to the above embodiment is realized by a computer 1000 having a configuration such as that shown in Figure 11. Figure 11 is a diagram showing an example of a hardware configuration. The computer 1000 is connected to an output device 1010 and an input device 1020, and has a configuration in which an arithmetic unit 1030, a primary storage device 1040, a secondary storage device 1050, an output IF (Interface) 1060, an input IF 1070, and a network IF 1080 are connected by a bus 1090.

[0067] The arithmetic unit 1030 operates based on programs stored in the primary storage device 1040 and the secondary storage device 1050, as well as programs read from the input device 1020, and executes various processes. The primary storage device 1040 is a memory device, such as RAM, that temporarily stores data used by the arithmetic unit 1030 for various calculations. The secondary storage device 1050 is a storage device where data used by the arithmetic unit 1030 for various calculations and various databases are registered, and is implemented using ROM (Read Only Memory), HDD (Hard Disk Drive), flash memory, etc.

[0068] Output IF1060 is an interface for transmitting information to be output to output devices 1010, such as monitors and printers, and is implemented using connectors of standards such as USB (Universal Serial Bus), DVI (Digital Visual Interface), and HDMI (High Definition Multimedia Interface). Input IF1070 is an interface for receiving information from various input devices 1020, such as mice, keyboards, and scanners, and is implemented using, for example, USB.

[0069] The input device 1020 may also be a device that reads information from, for example, an optical recording medium such as a CD (Compact Disc), DVD (Digital Versatile Disc), or PD (Phase Change Rewritable Disk), a magneto-optical recording medium such as an MO (Magneto-Optical disk), tape media, magnetic recording media, or semiconductor memory. Furthermore, the input device 1020 may also be an external storage medium such as a USB memory stick.

[0070] Network IF1080 receives data from other devices via network N and sends it to the arithmetic unit 1030, and also transmits data generated by the arithmetic unit 1030 to other devices via network N.

[0071] The arithmetic unit 1030 controls the output device 1010 and the input device 1020 via the output IF 1060 and the input IF 1070. For example, the arithmetic unit 1030 loads a program from the input device 1020 or the secondary storage device 1050 onto the primary storage device 1040 and executes the loaded program.

[0072] For example, when computer 1000 functions as information processing device 1, the arithmetic unit 1030 of computer 1000 realizes the functions of control unit 3 by executing a program loaded on primary storage device 1040.

[0073] 〔effect〕 As described above, the information processing device 1 according to the embodiment includes an acquisition unit 31 that collects comments on news articles, a generation unit 32 that estimates pairs of events that users are curious about and answers to those questions based on the collected comments, and generates QA content from the estimated question-answer pairs, and a provision unit 33 that provides the QA content together with the news article.

[0074] This configuration allows us to appropriately provide users with questions and answers regarding news articles.

[0075] Although some embodiments of the present invention have been described in detail above with reference to the drawings, these are illustrative examples, and the present invention can be implemented in various other forms with modifications and improvements based on the knowledge of those skilled in the art, starting with the embodiments described in the disclosure section of the invention.

[0076] 〔others〕 Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically by known methods. In addition, the processing procedures, specific names, and various data and parameters shown in the above document and drawings can be changed at will unless otherwise specified. For example, the various information shown in each figure is not limited to the information shown.

[0077] Furthermore, the components of each illustrated device are functionally conceptual and do not necessarily need to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions.

[0078] Furthermore, each of the processes described in the embodiments above can be combined as appropriate, provided that the processing content does not contradict each other.

[0079] Furthermore, the terms "section, module, unit" used above can be replaced with "means" or "circuit," etc. For example, control unit 3 can be replaced with control means or control circuit. [Explanation of Symbols]

[0080] 1. Information Processing Device 2 Communications Department 3. Control Unit 4 Storage section 31 Acquisition Department 32 Generation part 33 Providing Department 41 User Information 42 Article Information 43 Comment Information 44 Q&A Content Information 100 user terminals S Information Processing System

Claims

1. A data acquisition unit that collects comments on news articles, Based on the collected comments, a generation unit estimates pairs of events that users are wondering about and their answers, and generates Q&A content from the estimated pairs of questions and answers. A provision unit that provides the aforementioned Q&A content together with the aforementioned news article. An information processing device equipped with the following features.

2. The generation unit generates multiple QA contents, The aforementioned provisioning unit displays the multiple Q&A contents side by side. The information processing apparatus according to claim 1.

3. The generation unit calculates a degree of doubt indicating the magnitude of the question when generating the multiple QA contents, The aforementioned provisioning unit displays the multiple Q&A content in a ranked order based on the level of doubt. The information processing apparatus according to claim 2.

4. The acquisition unit collects keywords related to popular events and comments from multiple news articles corresponding to them. The aforementioned provisioning unit displays the Q&A content in the multiple news articles. The information processing apparatus according to claim 1 or claim 2.

5. The acquisition unit extracts news articles in which comments corresponding to the keywords of the popular events have been posted, and collects the comments. The information processing apparatus according to claim 4.

6. A method of information processing performed by a computer, The process of collecting comments on news articles, Based on the collected comments, the process involves estimating pairs of events that users are curious about and their answers, and generating Q&A content from the estimated pairs of questions and answers. The provision process for providing the aforementioned QA content Information processing methods including

7. Procedures for collecting comments on news articles, A generation procedure that estimates pairs of events that users are wondering about and their answers based on the collected comments, and generates Q&A content from the estimated pairs of questions and answers, The procedure for providing the aforementioned Q&A content An information processing program that causes a computer to execute something.

Images