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

Abstract

To provide a user with better understanding.SOLUTION: An information processing device according to the present invention comprises a generation unit, an identification unit, and a provision unit. The generation unit generates a flow for explaining an event to be explained. The identification unit identifies a news article corresponding to each step of the flow generated by the generation unit. The provision unit provides explanation content summarizing the news articles identified by the identification unit together with the flow.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 distributing distribution content such as news articles to users. For example, Patent Document 1 discloses a technology for providing search results for a keyword when a keyword embedded in distribution content is selected (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2020-47090 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the conventional techniques leave room for improvement in terms of improving the user's understanding.

[0005] The present invention has been made in view of the above, and has an object to provide an information processing device, an information processing method, and an information processing program that can improve the user's understanding. [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 a generation unit, an identification unit, and a provision unit. The generation unit generates a flow for explaining an event to be explained. The identification unit identifies news articles corresponding to each stage of the flow generated by the generation unit. The provision unit provides commentary content that summarizes the news articles identified by the identification unit together with the flow. [Effects of the Invention]

[0007] According to the present invention, it is possible to improve the user's understanding. [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 guidance content according to the embodiment. [Figure 3] FIG. 3 is a block diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of information stored in the content information storage unit according to the embodiment. [Figure 5] FIG. 5 is a flowchart illustrating an example of information processing according to the embodiment. [Figure 6] FIG. 6 is a hardware configuration diagram showing an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an information processing device, an information processing method, and an information processing program according to the present application will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to the embodiments.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment. Note that the information processing method is executed by, for example, an information processing device 1 shown in Fig. 1.

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

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

[0013] However, there are cases where user U cannot fully understand the events in a news article even after reading only one article.

[0014] To address this issue, the information processing device 1 according to the embodiment provides commentary content that explains the events in the news article. An overview of the information processing according to the embodiment will be described below.

[0015] 1, first, the information processing device 1 provides news content to the user terminal 50 of the user U (step S1). If the user U does not understand an event in the provided news content, the user U can request an explanation from the information processing device 1 via the user terminal 50 (step S2).

[0016] For example, a request for explanation is made by specifying a keyword in the news content or inputting a question about the news content. When the information processing device 1 receives the explanation request from the user terminal 50, it generates an explanation flow for the explanation request (step S3).

[0017] The explanation flow is a flow for explaining the event to be explained. In other words, by explaining the event according to the explanation flow, it is expected that the user U will have an improved understanding of the event. An example of the explanation flow will be described later with reference to FIG. 2.

[0018] Next, the information processing device 1 identifies news articles corresponding to each stage of the commentary flow (step S4), and provides commentary content that summarizes the identified news articles together with the commentary flow (step S5).

[0019] An example of commentary content will now be described with reference to Fig. 2. Fig. 2 is a diagram showing an example of commentary content according to the embodiment. The example in Fig. 2 shows a case where the topic of the event to be commented on is "Bank of Japan negative interest rates."

[0020] The example in Figure 2 shows a case where the explanatory flow has three stages: "1. Overview of the negative interest rate policy and the history of its introduction," "2. Effects and challenges of the negative interest rate policy," and "3. Impact of lifting the policy." For each stage, a corresponding news article headline is posted.

[0021] When the user U clicks on the headline of each news article, the corresponding news article is displayed on the user terminal 50. The information processing device 1 generates the commentary flow and identifies the news article corresponding to each stage of the commentary flow, for example, by using a sentence generation model. The sentence generation model is a natural language processing model trained to generate a sentence that serves as a response to an input natural language sentence, and is a GPT (Generative Pre-trained Transformer).

[0022] The information processing device 1 generates a prompt when generating a commentary flow and when identifying a news article corresponding to each stage of the commentary flow, and inputs the prompt to the sentence generation model.

[0023] For example, the prompt for generating an explanation flow includes an instruction such as "Please generate an explanation flow for the event to be explained in the following order: overall overview, individual points, and points that people are wondering about," along with each news content. Note that the news content includes news articles and comments posted on the news articles. Note that the above-mentioned "points that people are wondering about" can be inferred from the comments posted on the news articles.

[0024] Furthermore, the prompt for identifying a news article corresponding to each stage of the commentary flow includes an instruction sentence such as "Please identify a news article corresponding to each stage of the commentary flow" and each news content.

[0025] The sentence generation model outputs answers to these input prompts, and the information processing device 1 provides, for example, commentary content as shown in Fig. 2. By viewing each news article, the user U can deepen his or her understanding of the phenomenon (here, "negative interest rate policy") for which he or she requested an explanation.

[0026] 2, the comment section for the commentary content is displayed in the commentary content. That is, the user U can view the commentary content and immediately output what he / she has learned. Furthermore, the information processing device 1 can grasp the user U's level of understanding and improve the commentary content based on the content of the user U's comments.

[0027] In this way, the information processing device 1 according to the embodiment generates an explanation flow and identifies news articles corresponding to each stage of the explanation flow based on an explanation request from the user U, and provides explanation content.

[0028] Therefore, the information processing device 1 according to the embodiment can improve the user's understanding.

[0029] [2. Configuration example of information processing device] Next, a configuration example of the information processing device 1 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing a configuration example of the information processing device 1 according to an embodiment. As shown in Fig. 3, the information processing device 1 has a communication unit 2, a storage unit 3, and a control unit 4.

[0030] 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.

[0031] 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 and a sentence generation model storage unit 32.

[0032] The content information storage unit 31 stores content information. Fig. 4 is a diagram showing an example of information stored in the content information storage unit 31 according to the embodiment. As shown in Fig. 4, the content information storage unit 31 stores information on items such as "content ID," "category," "content data," and "comments" in association with each other.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] Returning to the explanation of FIG. 3, the sentence generation model storage unit 32 will be explained. The sentence generation model storage unit 32 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).

[0037] 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.

[0038] As shown in FIG. 3, the control unit 4 includes an acquisition unit 41, a distribution unit 42, a reception unit 43, a generation unit 44, a specification unit 45, and a provision unit 46.

[0039] The acquisition unit 41 acquires news articles from their creators and registers them in the content information storage unit 31.

[0040] The distribution unit 42 distributes distribution content to each user terminal 50. For example, the distribution unit 42 distributes news articles and comments posted to the news articles as distribution content.

[0041] Specifically, the distribution unit 42 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.

[0042] Furthermore, the distribution unit 42 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.

[0043] The reception unit 43 receives an explanation request from the user U. For example, the reception unit 43 receives a delivery request from the user U through a news article displayed on the user terminal 50. For example, the user U can make an explanation request by specifying a keyword that appears in the news article, or by inputting a keyword into a search box in the news article.

[0044] The generation unit 44 generates a flow for explaining the phenomenon to be explained (hereinafter referred to as an explanation flow). For example, the generation unit 44 generates the explanation flow using a sentence generation model.

[0045] The generating unit 44 generates a prompt including keywords, instruction sentences, and news content indicating the event specified in the explanation request received by the receiving unit 43. For example, the instruction sentence here is a sentence such as "Please generate an explanation flow for the event to be explained in the following order. The following order is the overall overview, individual points, and points that everyone is wondering about."

[0046] By inputting such a prompt, the sentence generation model will generate an explanation flow as shown in Fig. 2. Note that the generation unit 44 may instruct the sentence generation model to infer the above-mentioned "questions that people are wondering about" from comments posted in the comment section of the news article.

[0047] The generation unit 44 may also instruct the prompt to include user information about the user U who is the source of the explanation request, and to generate an explanation flow that is easy for the user U to understand. Note that the user information here includes, for example, information such as gender, age, occupation, and address, as well as the user U's browsing history and comment history of news articles, and search history on search sites.

[0048] The identification unit 45 identifies a news article corresponding to each stage of the commentary flow generated by the generation unit 44. For example, the identification unit 45 uses a sentence generation model to identify a news article corresponding to each stage of the commentary flow.

[0049] Specifically, the identification unit 45 first generates a prompt including each news article, a commentary flow, and an instruction sentence. The instruction sentence here is, for example, "Please identify the news article corresponding to each stage of the commentary flow."

[0050] At this time, the identification unit 45 may instruct the sentence generation model to identify multiple news articles at each stage. Also, at this time, the identification unit 45 may preferentially select news articles with high user ratings or new news articles. User ratings are estimated based on the number of "likes" and comments on a news article. For example, if a comment on a news article includes a comment such as "This article was easy to understand," it can be estimated that the comment has a high user rating.

[0051] The identification unit 45 then inputs these prompts to the sentence generation model, and identifies the news articles corresponding to each stage of the commentary flow based on the responses from the sentence generation model.

[0052] The providing unit 46 provides commentary content that summarizes the news articles identified by the identifying unit 45 together with commentary flows. Specifically, for example, the identifying unit 45 provides the commentary content to a user U who is the source of the commentary request. As shown in FIG. 2, the commentary content displays the headlines of news articles corresponding to each stage of the commentary flow and a comment section.

[0053] When user U selects a news article headline, the corresponding news article is delivered. User U can also output what they learned through the commentary content by writing in the comments field.

[0054] For example, the comments written by the user U in the comment field may be used by the generating unit 44 to improve the explanation flow when generating the explanation flow next time onwards.

[0055] [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. 5. Fig. 5 is a flowchart showing an example of information processing according to the embodiment.

[0056] 5, first, the information processing device 1 receives a commentary request for an event to be commented on from the user U (step S101). Next, based on the commentary request, the information processing device 1 generates a commentary flow for commenting on the event to be commented on (step S102).

[0057] Next, the information processing device 1 identifies news articles corresponding to each stage of the commentary flow (step S103), and provides commentary content that summarizes the identified news articles together with the commentary flow (step S104).Then, the information processing device 1 ends the process.

[0058] [4. Modifications] In the above-described embodiment, a case has been described in which a news article corresponding to each flow of the commentary flow is identified and commentary content is provided, but this is not limited to this. For example, comments posted on a news article may be included in the commentary content. The comments posted on a news article may be, for example, comments by experts or specialists. In other words, commentary content including commentary comments posted by experts or specialists on a news article may be provided.

[0059] [5. Effects] The information processing device 1 according to the embodiment described above includes a generation unit 44 that generates a flow for explaining the phenomenon to be explained, an identification unit 45 that identifies news articles corresponding to each stage of the flow generated by the generation unit 44, and a provision unit 46 that provides commentary content that summarizes the news articles identified by the identification unit 45 together with the flow.

[0060] The specifying unit 45 specifies news articles corresponding to each stage based on user ratings of the news articles. The generating unit 44 generates a flow based on questions estimated from the news articles.

[0061] Furthermore, the providing unit 46 accepts comments from users through the commentary content that it has provided. Furthermore, when multiple news articles match, the identifying unit 45 selects a news article by prioritizing newer news articles.

[0062] By performing any one or a combination of the above-described processes, the information processing device according to the present application can improve the user's understanding.

[0063] [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. 6. Fig. 6 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.

[0064] 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.

[0065] 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.

[0066] 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. 6, the output devices and input devices are collectively referred to as "input / output devices") via an 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.

[0067] 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.

[0068] 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.

[0069] 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.

[0070] [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.

[0071] 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.

[0072] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0073] 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]

[0074] 1. Information processing equipment 2. Communications Department 3 Storage section 4. Control Unit 31 Content information storage unit 32 Sentence generation model memory 41 Acquisition Department 42 Distribution Department 43 Reception Department 44 Generation part 45 Specific part 46 Providing Department 50 User Terminals

Claims

1. a generation unit that generates a flow for explaining an event to be explained; an identification unit that identifies a news article corresponding to each stage of the flow generated by the generation unit; a providing unit that provides commentary content that summarizes the news article identified by the identifying unit together with the flow; An information processing device comprising:

2. The identification unit Identifying news articles corresponding to each of the stages based on user ratings of the news articles.

2. The information processing device according to claim 1,

3. The generation unit generating the flow based on questions about the event inferred from the news article; 2. The information processing device according to claim 1,

4. The providing unit Accepting user comments through the commentary content 2. The information processing device according to claim 1,

5. The identification unit and identifying a news article corresponding to each of the stages, giving priority to the newest news article when multiple news articles are applicable.

2. The information processing device according to claim 1,

6. 1. A computer-implemented information processing method, comprising: a generation step of generating a flow for explaining an event to be explained; an identifying step of identifying a news article corresponding to each stage of the flow generated by the generating step; a providing step of providing commentary content that summarizes the news article identified by the identifying step together with the flow; An information processing method comprising:

7. A generation procedure for generating a flow for explaining a phenomenon to be explained; an identification procedure for identifying news articles corresponding to each stage of the flow generated by the generation procedure; a providing step of providing commentary content that summarizes the news article identified by the identifying step together with the flow; An information processing program characterized by causing a computer to execute the above.

Images