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 apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, there has been a technique for delivering distribution content such as news articles to users. For example, Patent Document 1 discloses a technique for providing search results for corresponding keywords when keywords embedded in distribution content are selected (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, in the prior art, there has been room for improvement in enhancing the user's understanding.

[0005] The present invention 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 improving the user's understanding.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, an information processing apparatus according to the present invention includes a generation unit, a specification unit, and a provision unit. The generation unit generates a flow for explaining an event to be explained. The specification unit specifies news articles corresponding to each stage of the flow generated by the generation unit. The provision unit provides explanatory content in which the news articles specified by the specification unit are summarized together with the flow.

Effects of the Invention

[0007] According to the present invention, it is possible to improve the user's level of understanding. [Brief explanation of the drawing]

[0008] [Figure 1] Figure 1 shows an example of information processing according to the embodiment. [Figure 2] Figure 2 shows an example of explanatory content according to this embodiment. [Figure 3] Figure 3 is a block diagram showing an example configuration of an information processing apparatus according to the embodiment. [Figure 4] Figure 4 shows an example of information stored in the content information storage unit according to this embodiment. [Figure 5] Figure 5 is a flowchart showing an example of information processing according to the present invention. [Figure 6] Figure 6 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device according to the embodiment. [Modes for carrying out the invention]

[0009] The following describes in detail, with reference to the drawings, the embodiments for implementing the information processing device, information processing method, and information processing program relating to this application (hereinafter referred to as "embodiments"). However, these embodiments do not limit the information processing device, information processing method, and information processing program relating to this application.

[0010] [Embodiment] [1. Information Processing] First, an example of information processing according to the embodiment will be explained using Figure 1. Figure 1 is a diagram showing an example of information processing according to the embodiment. This information processing method is performed, for example, by the information processing device 1 shown in Figure 1.

[0011] The information processing device 1 shown in Figure 1 is an information processing device that provides various services to user U via the internet. In this disclosure, the information processing device 1 provides various services related to news sites to user U. The information processing device 1 is implemented by, for example, a server device or a cloud system.

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

[0013] By the way, even if user U reads only one article, they may not be able to fully understand the events described in the news article.

[0014] To address these challenges, the information processing device 1 according to this embodiment provides explanatory content that explains the events in the news article. The outline of the information processing according to this embodiment will be described below.

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

[0016] For example, a request for explanation can be made by specifying keywords within the news content or by inputting questions about the news content. When the information processing device 1 receives an 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 an event to be explained. That is, by explaining the event along the explanation flow, it is expected to improve the user U's understanding of the event. An example of the explanation flow will be described later using FIG. 2.

[0018] Subsequently, the information processing apparatus 1 identifies news articles corresponding to each stage of the explanation flow (step S4), and provides explanation content that combines the identified news articles with the explanation flow (step S5).

[0019] Here, an example of the explanation content will be described using FIG. 2. FIG. 2 is a diagram showing an example of the explanation content according to the embodiment. Note that the case where the topic of the event to be explained in the example of FIG. 2 is "Regarding the Bank of Japan's negative interest rate" is shown.

[0020] In the example of FIG. 2, the case where the explanation flow has three stages of "1. Overview and background of the negative interest rate policy", "2. Effects and issues of the negative interest rate policy", and "3. Impact of the removal" is shown, and for each stage, the headlines of the corresponding news articles are published.

[0021] When the user U clicks on the headline of each news article, the corresponding news article will be displayed on the user terminal 50. The information processing apparatus 1 performs, for example, using a text generation model, the generation of the explanation flow and the identification of news articles corresponding to each stage of the explanation flow. The text generation model is a natural language processing model trained to generate a response article for an input natural language article, and is GPT (Generative Pre-trained Transformer).

[0022] The information processing apparatus 1 generates a prompt at the time of generating the explanation flow and at the time of identifying news articles corresponding to each stage of the explanation flow, and inputs the prompt to the text generation model.

[0023] For example, the prompts when generating the explanation flow include instructional text such as, "Generate the explanation flow for the event to be explained in the following order: overall overview, individual points, and points that everyone has questions about," along with each piece of news content. The news content includes news articles and comments posted on those articles. The "points that everyone has questions about" mentioned above can be inferred from the comments posted on the news articles.

[0024] Furthermore, the prompts used when identifying news articles corresponding to each stage of the explanation flow include instructional text such as "Please identify the news articles corresponding to each stage of the explanation flow," along with the respective news content.

[0025] The text generation model outputs responses to these input prompts, and the information processing device 1 provides explanatory content, such as that shown in Figure 2. User U can then deepen their understanding of the event for which they requested an explanation (in this case, "negative interest rate policy") by viewing each news article.

[0026] Furthermore, as shown in Figure 2, the explanatory content displays a comment section for that content. This means that user U can immediately output what they have learned after viewing the explanatory content. In addition, the information processing device 1 can use the content of user U's comments to understand user U's level of comprehension and to improve the explanatory content.

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

[0028] Therefore, according to the information processing device 1 of this embodiment, it is possible to improve the user's level of understanding.

[0029] [2. Example of Information Processing Device Configuration] Next, an example of the configuration of the information processing device 1 will be described using Figure 3. Figure 3 is a block diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in Figure 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 implemented, for example, by a NIC (Network Interface Card). The communication unit 2 transmits and receives information with external devices via 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 memory unit 3 is implemented by, for example, semiconductor memory elements such as RAM and flash memory, or storage devices such as hard disks and optical discs. The memory unit 3 also includes a content information storage unit 31 and a text generation model storage unit 32.

[0032] The content information storage unit 31 stores content information. Figure 4 shows an example of the information stored in the content information storage unit 31 according to this embodiment. As shown in Figure 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 to identify 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 it may indicate the topic of the content.

[0034] The "Content Data" field stores content data identified by the corresponding content ID. This content data pertains to news articles and includes the article's title, thumbnail image, body text, summary, etc.

[0035] The "Comments" section stores comments posted to content identified by its corresponding content ID. These comments include those posted on news websites, as well as comments made when sharing news articles on social media.

[0036] Returning to the explanation of Figure 3, let's describe the text generation model storage unit 32. The text generation model storage unit 32 stores the text generation model. The text generation model is a large-scale language model that has been trained to generate response sentences to input natural language sentences. For example, the text generation model is a GPT (Generative Pre-trained Transformer).

[0037] Next, the control unit 4 will be described. The control unit 4 is, for example, a controller, and is realized by the execution of various programs stored in the memory device inside the information processing device 1 using RAM as the working area by the CPU (Central Processing Unit) or MPU (Micro Processing Unit), etc.

[0038] As shown in Figure 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 the source of the news articles and registers them in the content information storage unit 31.

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

[0041] Specifically, the distribution unit 42 distributes information about the news site's top page to each user terminal 50, and then distributes content corresponding to the news article selected by user U.

[0042] Furthermore, the distribution unit 42 accepts comments from user U through the distributed content, registers the comments posted by user U in the content information storage unit 31, and distributes them to user U as content for future distributions.

[0043] The reception unit 43 receives explanation requests from user U. For example, the reception unit 43 receives distribution requests from user U through news articles displayed on user terminal 50. For example, user U can make an explanation request by specifying keywords that appear in the news article, or by entering keywords into the search box of the news article.

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

[0045] The generation unit 44 generates a prompt containing keywords, instructional text, and news content that indicate the event specified in the explanation request received by the reception unit 43. For example, the instructional text here might be something like, "Please generate an explanation flow for the event to be explained in the following order: overall overview, individual points, and points that everyone might be wondering about."

[0046] By inputting such prompts, the text generation model will generate an explanatory flow as shown in Figure 2. The generation unit 44 may also instruct the text generation model to estimate the "points everyone is wondering about" from comments posted in the comment section of the news article.

[0047] Furthermore, the generation unit 44 may be configured to include user information of user U, who is the source of the explanation request, in the prompt, and to instruct the generation unit to generate an explanation flow that is easy for user U to understand. The user information here may include, for example, information such as gender, age, occupation, and address, as well as user U's news article viewing history, comment history, and search history on search engines.

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

[0049] Specifically, the identification unit 45 first generates a prompt containing each news article, an explanation flow, and instruction text. The instruction text here might be, for example, "Identify the news article corresponding to each stage of the explanation flow."

[0050] In this process, the identification unit 45 may instruct the text generation model to identify multiple news articles at each stage. Furthermore, the identification unit 45 may prioritize the selection of news articles with high user ratings or newer news articles. User ratings are estimated based on the number of "likes" and comments on the news articles. For example, if a comment on a news article says, "This article was easy to understand," it can be estimated that this comment indicates a high user rating.

[0051] The identification unit 45 then inputs these prompts to the text generation model and, based on the model's response, identifies news articles corresponding to each stage of the explanation flow.

[0052] The provisioning unit 46 provides explanatory content that compiles the news articles identified by the identification unit 45 along with an explanatory flow. Specifically, for example, the identification unit 45 provides explanatory content to user U, who is the source of the explanatory request. As shown in Figure 2, the explanatory content displays the headlines of the news articles corresponding to each stage of the explanatory flow, as well as the comment section.

[0053] When user U selects a news article headline, the corresponding news article is delivered. Furthermore, user U can output what they have learned through the explanatory content by writing comments in the comment section.

[0054] For example, comments written by user U in the comment section may be used by the generation unit 44 to improve the explanation flow when generating the explanation flow in the future.

[0055] [3. Processing Flow] Next, the processing procedure executed by the information processing device 1 according to the embodiment will be described using Figure 5. Figure 5 is a flowchart showing an example of information processing according to the embodiment.

[0056] As shown in Figure 5, first, the information processing device 1 receives a request from user U for an explanation of the event to be explained (step S101). Next, based on the explanation request, the information processing device 1 generates an explanation flow for explaining the event to be explained (step S102).

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

[0058] [4. Variations] The embodiments described above describe a case where news articles corresponding to each flow of the explanation flow are identified and explanation content is provided, but the invention is not limited to this. For example, comments posted on news articles may be included in the explanation content. Comments posted on news articles may be, for example, comments from experts or specialists. In other words, explanation content may be provided that includes explanation comments posted on news articles by experts or specialists.

[0059] [5. Effects] The information processing device 1 according to the above embodiment includes a generation unit 44 that generates a flow for explaining an event 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 explanatory content that combines the news articles identified by the identification unit 45 with the flow.

[0060] Furthermore, the identification unit 45 identifies news articles corresponding to each stage based on user ratings of the news articles. The generation unit 44 generates a flow based on questions inferred from the news articles.

[0061] Furthermore, the provision unit 46 accepts comments from users through the provided explanatory content. Additionally, the identification unit 45, when multiple news articles are relevant, selects the news article prioritizing the newest one.

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

[0063] [6. 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 6. Figure 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, RAM 1200, ROM 1300, HDD 1400, communication interface (I / F) 1500, input / output interface (I / F) 1600, and media interface (I / F) 1700.

[0064] The CPU 1100 operates based on programs stored in the ROM 1300 or HDD 1400, controlling various components. The ROM 1300 stores boot programs executed by the CPU 1100 when the computer 1000 starts up, as well as programs that depend on the computer 1000's hardware.

[0065] The HDD1400 stores programs executed by the CPU1100, as well as data used by such programs. The communication interface1500 receives data from other devices via the network (communication network) N and sends it to the CPU1100, and transmits data generated by the CPU1100 to other devices via the network N.

[0066] The CPU 1100 controls output devices such as displays and printers, and input devices such as keyboards and mice (in Figure 6, 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 input devices via the input / output interface 1600. The CPU 1100 also outputs the generated data to output devices via the input / output interface 1600.

[0067] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads the program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or PD (Phase Change Rewritable Disk), 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 computer 1000 functions as an information processing device 1 according to the embodiment, the CPU 1100 of computer 1000 realizes the functions of control unit 4 by executing programs loaded on RAM 1200. The CPU 1100 of computer 1000 reads and executes these programs from recording medium 1800, but as another example, these programs may be obtained from other devices via network N.

[0069] 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.

[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 by known methods. In addition, the processing procedures, specific names, and information including 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.

[0071] 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.

[0072] Furthermore, the embodiments and modifications described above can be combined as appropriate, provided that the processing content is not inconsistent.

[0073] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, the acquisition unit can be replaced with acquisition means or acquisition circuit. [Explanation of Symbols]

[0074] 1. Information Processing Device 2 Communications Department 3 Storage section 4. Control Unit 31 Content Information Storage Unit 32 Text generation model memory unit 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 chart for explaining the phenomenon to be explained, A specification unit that identifies news articles corresponding to each stage of the flow generated by the generation unit, Based on the news articles identified by the aforementioned identification unit, a providing unit provides explanatory content that compiles the news articles corresponding to each stage of the flow. Equipped with, The generating unit is The flow is generated using the text generation model by inputting generation instructions to a text generation model that has been trained to generate a response to an input text. The specified part is, The news article is identified using the text generation model by inputting specific instructions to the text generation model to identify the news article corresponding to each stage of the flow. An information processing device characterized by the following:

2. The specified part is, Based on user ratings of the aforementioned news articles, identify the news articles corresponding to each of the aforementioned stages. The information processing apparatus according to claim 1, characterized by the following:

3. The generating unit is To generate the flow based on questions regarding the aforementioned event that can be inferred from the aforementioned news article. The information processing apparatus according to claim 1, characterized by the following:

4. The aforementioned supply unit is, The aforementioned explanatory content will be used to accept user comments. The information processing apparatus according to claim 1, characterized by the following:

5. The specified part is, If multiple news articles are applicable, the newest news article is given priority to identify the news article corresponding to each stage. The information processing apparatus according to claim 1, characterized by the following:

6. A method of information processing performed by a computer, A generation process that generates a flow chart for explaining the phenomenon to be explained, A process for identifying news articles that correspond to each stage of the flow generated by the generation process, A provisioning step provides explanatory content that compiles the news articles identified by the aforementioned specific step along with the aforementioned flow chart. Includes, The aforementioned generation step is The flow is generated using the text generation model by inputting generation instructions to a text generation model that has been trained to generate a response to an input text. The aforementioned specific step is, The news article is identified using the text generation model by inputting specific instructions to the text generation model to identify the news article corresponding to each stage of the flow. An information processing method characterized by the following:

7. The generation procedure for generating a flowchart to explain the phenomenon to be explained, A procedure for identifying news articles corresponding to each stage of the flow generated by the above generation procedure, A provision procedure for providing explanatory content that compiles the news articles identified by the aforementioned identification procedure along with the aforementioned flow chart. Have the computer run it, The aforementioned generation procedure is: The flow is generated using the text generation model by inputting generation instructions to a text generation model that has been trained to generate a response to an input text. The aforementioned identification procedure is, The news article is identified using the text generation model by inputting specific instructions to the text generation model to identify the news article corresponding to each stage of the flow. An information processing program characterized by the following features.

Images