Information processing device, information processing method, and information processing program
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- LY CORP
- Filing Date
- 2024-12-20
- Publication Date
- 2026-07-02
Smart Images
Figure 2026110133000001_ABST
Abstract
Description
Technical Field
[0001] This application relates to an information processing apparatus, an information processing method, and an information processing program.
Background Art
[0002] Conventionally, there are online services that provide various contents such as news articles, columns, product reviews, etc. to service users. In relation to such services, for example, technologies for automating news articles by selecting representative articles for each issue have also been proposed (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, the conventional technology has room for improvement in terms of improving the usability when providing content.
[0005] This application has been made in view of the above, and an object thereof is to improve the usability when providing content.
Means for Solving the Problems
[0006] The information processing device according to the present application comprises an acquisition unit, a first processing unit, a second processing unit, and a provision unit. The acquisition unit acquires posted information, including articles and comments on articles. The first processing unit instructs a generating AI, which has been trained to generate answers to input questions, to estimate the content of an article containing the information it should originally have, based on multiple perspectives, by inputting the posted information and instruction information. The second processing unit instructs the generating AI to infer missing information in an article by inputting the posted information, the inference result from the first processing unit, and instruction information. The second processing unit instructs the generating AI to estimate information that is desirable to supplement the article contained in the posted information. The provision unit provides information indicating the missing information obtained as a result of processing by the second processing unit. [Effects of the Invention]
[0007] According to one embodiment of the present invention, it is possible to improve the usability when providing content. [Brief explanation of the drawing]
[0008] [Figure 1] Figure 1 is a diagram illustrating the overview of the information processing according to the embodiment. [Figure 2] Figure 2 is a diagram illustrating the overview of the information obtained by the information processing according to this embodiment. [Figure 3] Figure 3 shows an example of the system configuration of an information processing system according to the embodiment. [Figure 4] Figure 4 shows an example of the configuration of an information processing device according to the present invention. [Figure 5] Figure 5 shows an example of post information stored in the post information storage unit according to this embodiment. [Figure 6] Figure 6 shows an example of expert information stored in the expert information storage unit according to this embodiment. [Figure 7]Figure 7 is a flowchart showing an example of the processing procedure for information processing performed by the information processing apparatus according to the present invention. [Figure 8] Figure 8 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 apparatus, 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 apparatus, information processing method, and information processing program according to the present application. Furthermore, each embodiment can be appropriately combined as long as the processing content is not inconsistent. Also, the same parts are denoted by the same reference numerals in each of the following embodiments, and redundant descriptions are omitted.
[0010] [Embodiment] [1. An example of information processing] An example of information processing according to the embodiment will be described below with reference to the drawings. Figure 1 is a diagram illustrating the overview of the information processing according to the embodiment. The information processing according to the embodiment described below aims to improve usability when providing content such as news articles.
[0011] The information processing according to this embodiment is realized by an information processing system SYS (see, for example, Figure 3) which includes a plurality of terminal devices 10, such as terminal device 10-1 and terminal device 10-2 shown in Figure 1, and an information processing device 100 shown in Figure 1. The plurality of terminal devices 10, such as terminal device 10-1 and terminal device 10-2, and the information processing device 100 are each connected to a network N (see, for example, Figure 3) by wired or wireless means. The plurality of terminal devices 10, such as terminal device 10-1 and terminal device 10-2, and the information processing device 100 can communicate with other devices through the network N.
[0012] The terminal device 10-1 is used by the user U-1 who posts articles related to a predetermined topic to news sites or the like. The terminal device 10-2 is used by the user U-2 who posts comments on articles viewed on news sites. In the following description, when it is not necessary to particularly distinguish and describe the terminal device 10-1 and the terminal device 10-2, they will be collectively described as "terminal device 10". Also, in the following description, when it is not necessary to particularly distinguish and describe the user U-1 and the user U-2, they will be collectively described as "user U".
[0013] The user U-1 posts an article to a news site by operating the terminal device 10-1. Articles posted by the user U-1 may include, in addition to news articles, columns, essays, interviews, product reviews, feature articles, or personality articles, etc. Also, various forms of articles posted by the user U-1 are assumed, such as text, images including moving images, audio, or combinations thereof. The terminal device 10-1 transmits the information of the article created by the user U-1 to the information processing device 100 (step S01).
[0014] The information processing device 100 internally stores and manages the articles posted by the user U-1. The information processing device 100 publishes the articles posted by the user U-1 to the news site at a predetermined timing.
[0015] The user U-2 posts a comment on an article viewed on a news site. The terminal device 10-2 transmits the comment posted by the user U-2 to the information processing device 100 (step S02).
[0016] The information processing device 100 internally stores and manages the comments posted by the user U-2 in association with the corresponding articles. The information processing device 100 publishes the comments posted by the user U-2 to the news site in association with the corresponding articles at a predetermined timing.
[0017] The information processing device 100 acquires posting information including articles stored internally and comments on the articles at a predetermined timing (step S03).
[0018] The information processing device 100 executes an article content inference process for inferring, by a generation AI (Artificial Intelligence), the content of an article that should originally be included in the article included in the acquired posting information (step S04).
[0019] Specifically, the information processing device 100 causes the generation AI to infer the content of an article that should originally be included by inputting the posting information and instruction information for instructing the generation AI to estimate the content of an article that should originally be included in the article included in the posting information based on a plurality of viewpoints.
[0020] For example, the information processing device 100 can use, as the instruction information input to the generation AI, instruction information for estimating the content of an article that should originally be included from at least any one of the viewpoints of the topic targeted by the article included in the posting information, the pattern of comments included in the posting information, the consistency between the content of the article included in the posting information and the content of the comments included in the posting information, and the opinions of experts in the field corresponding to the topic.
[0021] The information processing device 100 can instruct the generation AI to specify, through the instruction information, the topic targeted by the article included in the posting information (hereinafter, appropriately referred to as "target article") and to check whether information related to the specified topic is included in the article. For example, if the target article is an article about population, the information processing device 100 can incorporate, in the instruction information, points such as the original population, the decrease rate, and the effects of population decline as possible related information.
[0022] In addition, the information processing device 100 can instruct the generation AI to aggregate information frequently mentioned in comments on the target article and to identify information lacking in the content of the article, through the instruction information.
[0023] Furthermore, the information processing device 100 can, through the instruction information, verify whether the content of the target article and the content of the comments on the article are consistent, and can instruct the generating AI to identify any missing or contradictory information in the article's content.
[0024] Furthermore, the information processing device 100 can, through the instruction information, refer to the opinions of experts in the field corresponding to the topic covered by the article, as well as existing data, and instruct the generating AI to identify any missing information or information that should be included in the article's content.
[0025] Generative AI can be implemented using, for example, a language model such as GPT (Generative Pre-trained Transformer), which is capable of generating text using natural language processing techniques. The information processing device 100 can use text generation AI as the generative AI.
[0026] Furthermore, after completing the article content inference process, the information processing device 100 performs a missing information inference process (step S05) in which it causes the generating AI (Artificial Intelligence) to infer any missing information about the article contained in the acquired posted information.
[0027] Specifically, the information processing device 100 inputs the posting information, the inference results from the article content inference process, and instruction information that instructs the AI to estimate information that is desirable to supplement the target article by comparing the target article with the inference results, thereby causing the generating AI to infer missing information in the target article.
[0028] For example, the information processing device 100 can instruct the generating AI to extract important keywords and phrases from target articles and comments based on the instruction information. Furthermore, the information processing device 100 can instruct the generating AI to prioritize the analysis of comments related to numerical and statistical information, and to understand the context and units of those numerical values, based on the instruction information.
[0029] Furthermore, the information processing device 100 can, through instruction information, understand the context of the target article based on the information in the comments and instruct the generating AI to identify information related to a specific year or a specific event. The information processing device 100 can also aggregate frequently occurring topics and numerical values in the comments and, by comparing the aggregated results with the content of the target article, instruct the generating AI to identify information missing from the target article.
[0030] Furthermore, the information processing device 100 can instruct the generating AI to estimate missing information in the target article by analyzing the relationships between the information shown in the comments through the instruction information.
[0031] Furthermore, the information processing device 100 can instruct the generating AI to refer to reliable external databases and statistical information through the instruction information and to verify the accuracy of the information indicated in the comments.
[0032] Furthermore, the information processing device 100 can, through instruction information, present to the generating AI as a hint for inference that if many comments mention the same lack of information, the relevant information may be missing information. Also, through instruction information, the information processing device 100 can, if there is a discrepancy between the information shown in the comments and the information published in the target article, present to the generating AI that the discrepancy should be considered as missing information.
[0033] After completing the missing information inference process, the information processing device 100 can provide the information indicated by the missing information to, for example, the poster of the target article. Alternatively, the information processing device 100 may provide the information indicated by the missing information to an expert corresponding to the topic covered by the target article and obtain feedback on the accuracy of the information indicated by the missing information.
[0034] Furthermore, the information processing device 100 can provide information indicating missing information in association with the relevant section of the target article. For example, the information processing device 100 can identify the location where information indicating missing information should be inserted in an article on a news website and provide it as part of the article. Alternatively, instead of providing it as part of the article, the information processing device 100 may provide information indicating missing information as supplementary information at the end of the article or elsewhere.
[0035] Furthermore, the information processing device 100 can reflect information indicating missing information in the target article, subject to obtaining approval from the poster of the target article or from an expert corresponding to the topic the target article concerns.
[0036] An example of information obtained by the information processing performed by the information processing device 100 will be explained using Figure 2. Figure 2 is a diagram illustrating the overview of the information obtained by the information processing according to this embodiment.
[0037] Figure 2 illustrates examples of posted information on a news website, including an article on the topic of population and comments on that article. When the information processing according to the embodiment is performed on such posted information by the information processing device 100, for example, it can be identified that the original population information is insufficient in the article content. Furthermore, as a result of the information processing according to the embodiment, the original population is identified from the content of the comments, as well as the current population.
[0038] As described above, the information processing device 100 according to the embodiment can, for example, provide information that should be present in an article published on a news site as missing information. Furthermore, the information processing device 100 according to the embodiment can provide an article through the news site that reflects the information that should be present, which has been estimated as missing information. In this way, the information processing device 100 according to the embodiment can improve the usability when providing content.
[0039] [2. System Configuration] The configuration of the information processing system SYS according to the embodiment will be described in detail below with reference to Figure 3. Figure 3 is a diagram showing an example of the system configuration of the information processing system SYS according to the embodiment.
[0040] As shown in Figure 3, the information processing system SYS according to this embodiment includes a plurality of terminal devices 10, such as terminal device 10-1 and terminal device 10-2, and an information processing device 100. Note that Figure 3 is merely an example of the configuration of the information processing system SYS according to this embodiment, and it may have other devices such as terminal devices 10 used by user U, who is an expert in the field corresponding to the topic of the article.
[0041] The terminal device 10 and the information processing device 100 are connected to the network N by wire or wireless connection. Each of the terminal device 10 and the information processing device 100 can communicate with other devices through the network N.
[0042] Network N includes, for example, WANs (Wide Area Networks) such as the Internet, and mobile communication networks such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: 5th Generation Mobile Communication System).
[0043] The terminal device 10 connects to the network N via a mobile communication network or short-range wireless communication such as Bluetooth® or Wi-Fi (Local Area Network), and can communicate with other devices such as the information processing device 100 through the network N.
[0044] Furthermore, terminal device 10 is used by user U, who is a user of the news site. Terminal device 10 may be, for example, a notebook PC (personal computer), a desktop PC, a smartphone, or a tablet PC.
[0045] Furthermore, the terminal device 10 can display content such as news articles provided by the information processing device 100, for example, using a dedicated application or web browser. When the terminal device 10 receives control information from the information processing device 100 to perform information display processing, it performs the display processing according to the control information.
[0046] Control information is described using, for example, scripting languages such as JavaScript (registered trademark), stylesheet languages such as CSS (Cascading Style Sheets), programming languages such as Java (registered trademark), or markup languages such as HTML (HyperText Markup Language). Alternatively, a predetermined application distributed from the information processing device 100 may be considered as control information.
[0047] The information processing device 100 is operated and managed by a service provider that operates a news site. The information processing device 100 performs various processes related to the embodiment regarding the provision of content such as news articles. The information processing device 100 is typically a server device, but may be implemented by a mainframe or workstation. Furthermore, if the information processing device 100 is implemented by a server device, it may be implemented by a single server device, or by a cloud system in which multiple server devices and multiple storage devices work together.
[0048] [3. Equipment configuration] Hereinafter, an example of the functional configuration of the information processing device 100 in the information processing system SYS according to the embodiment will be described using Figure 4. Figure 4 is a diagram showing an example of the configuration of the information processing device 100 according to the embodiment. As shown in Figure 4, the information processing device 100 has a communication unit 110, a storage unit 120, and a control unit 130.
[0049] (Communications Department 110) The communication unit 110 is implemented, for example, by a communication module or a NIC (Network Interface Card). The communication unit 110 is connected to the network N by wire or wireless connection. The information processing device 100 transmits and receives information with other devices, such as the terminal device 10, through the network N.
[0050] For example, the communication unit 110 can receive information about articles and comments posted by user U from the terminal device 10. The communication unit 110 stores the received articles and comments in the storage unit 120, which will be described later.
[0051] (Storage unit 120) The storage unit 120 stores, for example, programs and data used for control and calculations by the control unit 130. For example, the storage unit 120 can be implemented using semiconductor memory elements such as RAM (Random Access Memory) or flash memory, or storage devices such as hard disks or optical discs. For example, the storage unit 120 has a posting information storage unit 121 and an expert information storage unit 122. Note that the storage unit 120 is not particularly limited to the example shown in Figure 4, and can appropriately store data necessary for executing the information processing according to the embodiment.
[0052] (Posting Information Storage Unit 121) The posting information storage unit 121 stores posting information such as articles and comments posted by user U. Figure 5 is a diagram showing an example of posting information stored in the posting information storage unit 121 according to this embodiment.
[0053] As shown in Figure 5, the post information stored in the post information storage unit 121 has multiple fields, such as "Post ID," "Poster," "Article Information," and "Comment Information." These fields of post information are interconnected.
[0054] The "Post ID" field stores identification information to identify the post. The "Poster" field stores identification information to identify user U, the poster who posted the article. The "Article Information" field stores information indicating the content of the article posted by user U. The "Comment Information" field stores information about comments posted on the article. The comment information includes identification information to identify user U who posted the comment, and information indicating the content of the comment.
[0055] The post information stored in the post information storage unit 121 is used for the article content inference process and missing information inference process described above (see Figure 1).
[0056] (Expert Information Storage Unit 122) The expert information storage unit 122 stores expert information about experts in fields corresponding to topics that may become articles. Figure 6 shows an example of expert information stored in the expert information storage unit 122 according to this embodiment.
[0057] As shown in Figure 6, the expert information stored in the expert information storage unit 122 has multiple items, such as a "topic" item, an "expert" item, and a "reference information" item. These items in the expert information are interconnected.
[0058] The "Topic" field stores information to categorize topics that could become articles. The "Expert" field stores information about experts in the field corresponding to the topic. The "Reference Information" field stores information such as articles posted by experts and various publications.
[0059] The expert information stored in the expert information storage unit 122 is used to select experts to request feedback from when requesting feedback from experts regarding the accuracy of the information indicated by the missing information.
[0060] (Control unit 130) The control unit 130 is a controller, and is realized by the execution of various programs (an example of an "information processing program") stored in the memory device inside the information processing device 100 by a CPU (Central Processing Unit) or MPU (Micro Processing Unit), using RAM as the working area.
[0061] Furthermore, the control unit 130 may be implemented by an integrated circuit such as an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or a GPGPU (General Purpose Graphic Processing Unit).
[0062] As shown in Figure 4, the control unit 130 includes an acquisition unit 131, a first processing unit 132, a second processing unit 133, and a providing unit 134. These units realize or execute the information processing functions and operations described below.
[0063] The control unit 130 may have multiple internally divided components that realize or execute the functions and operations of the information processing described below. Furthermore, the control unit 130 is not limited to the configuration shown in Figure 4, and may have other configurations as long as they perform the information processing described later, and may have other functional units other than those shown in Figure 4.
[0064] (Acquisition part 131) The acquisition unit 131 acquires posting information, including articles and comments on those articles. For example, at a predetermined timing, the acquisition unit 131 acquires posting information from the posting information storage unit 121 that has not undergone the information processing according to the embodiment. The acquisition unit 131 then passes the acquired posting information to the first processing unit 132 and the second processing unit 133.
[0065] (First Processing Unit 132) The first processing unit 132 inputs the post information received from the acquisition unit 131 and instruction information that instructs the generation AI, which has been trained to generate answers to input questions, to estimate the content of an article that contains the information it should originally have, based on multiple perspectives, thereby executing an article content inference process that causes the generation AI to infer the content of an article that contains the information it should originally have.
[0066] For example, the first processing unit 132 can use instruction information to input to the generating AI that instructs the AI to estimate the content of an article that should contain the information it should have, from the perspective of at least one of the following: the topic the target article is concerned with, the pattern of comments included in the posted information, the consistency between the content of the target article and the content of the comments included in the posted information, and the opinion of experts in the field corresponding to the topic.
[0067] The first processing unit 132 can, through instruction information, instruct the generating AI to identify the topic the target article is concerned with and to check whether the article contains information related to the identified topic. For example, if the target article is about population, the information processing device 100 can include in the instruction information that information such as the original population, the rate of decline, and the impact of population decline may be relevant information.
[0068] Furthermore, the first processing unit 132 can instruct the generating AI to aggregate information that is frequently mentioned in comments on the target article and to identify information that is missing from the article's content, based on the instruction information.
[0069] Furthermore, the first processing unit 132 can, through the instruction information, check whether the content of the target article and the content of the comments on the article are consistent, and can instruct the generating AI to identify any missing or contradictory information in the article's content.
[0070] Furthermore, the first processing unit 132 can, through instruction information, refer to the opinions of experts in the field corresponding to the topic covered by the article, as well as existing data, and instruct the generating AI to identify any missing information or information that should be included in the article.
[0071] Generative AI can be implemented using, for example, a language model such as GPT (Generative Pre-trained Transformer), which is capable of generating text using natural language processing techniques. The information processing device 100 can use text generation AI as the generative AI.
[0072] The first processing unit 132 passes the inference result to the second processing unit 133.
[0073] (Second Processing Unit 133) The second processing unit 133 performs a missing information inference process that causes the generating AI to infer missing information in articles by inputting the post information acquired by the acquisition unit 131, the inference result from the first processing unit 132, and instruction information that instructs the AI to estimate information that is desirable to fill in for the articles included in the post information.
[0074] For example, the second processing unit 133 can instruct the generating AI to extract important keywords and phrases from the target article and comments based on the instruction information. Furthermore, the second processing unit 133 can instruct the generating AI to prioritize the analysis of comments related to numerical and statistical information, and to understand the context and units of those numerical values, based on the instruction information.
[0075] Furthermore, the second processing unit 133 can, through instruction information, understand the context of the target article based on the information in the comments and instruct the generating AI to identify information related to a specific year or a specific event. The second processing unit 133 can also aggregate frequently occurring topics and numerical values in the comments and, by comparing the aggregated results with the content of the target article, instruct the generating AI to identify information missing from the target article.
[0076] Furthermore, the second processing unit 133 can instruct the generating AI to estimate missing information in the target article by analyzing the relationships between the information shown in the comments through the instruction information.
[0077] Furthermore, the second processing unit 133 can instruct the generating AI to refer to reliable external databases and statistical information through instruction information and to verify the accuracy of the information indicated in the comments.
[0078] Furthermore, the second processing unit 133 can, through instruction information, present to the generating AI as a hint for inference that if many comments mention the same lack of information, the relevant information may be missing information. Also, through instruction information, the second processing unit 133 can present to the generating AI, through instruction information, that if there is a discrepancy between the information shown in the comments and the information published in the target article, the discrepancy should be considered as missing information.
[0079] The second processing unit 133 passes the missing information obtained by the missing information inference process to the providing unit 134.
[0080] (Provider 134) The providing unit 134 provides information indicating missing information obtained as a result of processing by the second processing unit 133. For example, the providing unit 134 provides the information indicating missing information to user U, the poster, by transmitting it to the terminal device 10 used by user U, the poster who posted the article included in the posted information, via the communication unit 110.
[0081] Furthermore, the providing unit 134 may provide information indicating missing information in association with the relevant section of the article included in the posted information.
[0082] Furthermore, the provisioning unit 134 may reflect missing information in articles included in the posted information, provided that it obtains approval from user U, the author of the article included in the posted information, or from an expert corresponding to the topic the article addresses.
[0083] Furthermore, the provision unit 134 may provide the information indicated by the missing information to experts corresponding to the topic covered by the article, and obtain feedback from the experts regarding the accuracy of the information indicated by the missing information.
[0084] [4. Processing procedure according to the embodiment] The following describes the information processing procedure performed by the information processing device 100 according to this embodiment, using Figure 7 as a reference. Figure 7 is a flowchart of an example of the information processing procedure performed by the information processing device according to this embodiment. The procedure shown in Figure 7 is performed by the control unit 130 of the information processing device 100. The procedure shown in Figure 7 is repeatedly performed while the information processing device 100 is running.
[0085] As shown in Figure 7, the acquisition unit 131 acquires post information, including articles and comments on those articles (step S101).
[0086] Furthermore, the first processing unit 132 inputs the post information received from the acquisition unit 131 and the instruction information to the generating AI, thereby performing a process (article content inference process) that causes the generating AI to infer the content of the article that should contain the information it should originally have (step S102).
[0087] Furthermore, the second processing unit 133 inputs the post information received from the acquisition unit 131, the inference result from step S102, and the instruction information to the generating AI and performs a process to cause the generating AI to infer missing information in the article (missing information inference process) (step S103).
[0088] The providing unit 134 provides information indicating the missing information acquired in step S103 (step S104), and then terminates the processing procedure shown in Figure 7.
[0089] [5. Hardware Configuration] Furthermore, the information processing device 100 according to the above embodiment can be implemented by a computer 1000 having a configuration such as that shown in Figure 8. Figure 8 is a hardware configuration diagram showing an example of a computer that implements the functions of the information processing device 100 according to the embodiment.
[0090] 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 interface 1060, an input interface 1070, and a network interface 1080 are connected by a bus 1090.
[0091] 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, flash memory, etc.
[0092] The 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). The 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.
[0093] 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 be an external storage medium such as a USB memory stick.
[0094] 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.
[0095] 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.
[0096] For example, when the computer 1000 functions as the information processing device 100 according to the embodiment, the arithmetic unit 1030 of the computer 1000 realizes the same functions as the control unit 130 by executing a program (for example, an information processing program) loaded on the primary storage device 1040. That is, the arithmetic unit 1030 realizes the processing by the information processing device 100 according to the embodiment in cooperation with the program (for example, an information processing program) loaded on the primary storage device 1040.
[0097] [6. Others] Of 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 information including various data and parameters shown in the above documents and drawings can be changed at will unless otherwise specified.
[0098] 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.
[0099] Furthermore, the embodiments described above can be combined as appropriate, provided that the processing content is not contradictory.
[0100] Although embodiments of the present application have been described in detail above with reference to several 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.
[0101] Furthermore, the terms "section, module, unit" mentioned above can be replaced with "means" or "circuit," etc. For example, a control unit can be replaced with a control means or a control circuit.
[0102] [7. Effects] The information processing device 100 according to this embodiment includes an acquisition unit 131, a first processing unit 132, a second processing unit 133, and a providing unit 134. The acquisition unit 131 acquires posted information, including articles and comments on articles. The first processing unit 132 instructs a generating AI, which has been trained to generate answers to input questions, to infer the content of an article containing the information it should have, based on multiple perspectives, by inputting the posted information and instruction information. The second processing unit 133 instructs the generating AI to infer missing information about an article by inputting the posted information, the inference result from the first processing unit 132, and instruction information instructing the generating AI to estimate missing information about the article contained in the posted information. The providing unit 134 provides information indicating the missing information estimated by the second processing unit 133.
[0103] Furthermore, the first processing unit 132 inputs instruction information to the generating AI, instructing it to estimate the content of an article that should contain the information it should have, from the perspective of at least one of the following: the topic the article in the posted information is targeting, the pattern of comments in the posted information, the consistency between the content of the article in the posted information and the content of the comments in the posted information, and the opinion of experts in the field corresponding to the topic.
[0104] Furthermore, the provision unit 134 provides information indicating missing information to the poster who posted the article included in the posted information.
[0105] Furthermore, the provisioning unit 134 provides information indicating missing information, associating it with the relevant section of the article included in the posted information.
[0106] Furthermore, the provisioning unit 134 reflects missing information in articles included in the posted information, subject to obtaining approval from the author of the article included in the posted information, or from an expert corresponding to the topic the article addresses.
[0107] In this way, the information processing device 100 according to the embodiment can, for example, provide information that should be present in an article published on a news site as missing information. Furthermore, the information processing device 100 according to the embodiment can provide an article that reflects the information that should be present, which has been estimated as missing information. As a result, the information processing device 100 according to the embodiment can improve the usability when providing content.
[0108] Furthermore, the effects described above can also be achieved by any combination of the processes performed by each of the parts described above, or by any combination of the processes performed by each of the parts. [Explanation of symbols]
[0109] SYS Information Processing System N Network 10 Terminal devices 100 Information Processing Devices 110 Communications Department 120 Storage section 121 Post Information Storage Unit 122 Expert Information Storage Unit 130 Control Unit 131 Acquisition Department 132 First Processing Unit 133 Second Processing Unit 134 Provision Department
Claims
1. A unit that retrieves posting information including articles and comments on articles, A first processing unit, which causes a generating AI that has been trained to generate answers to input questions to infer the content of an article containing the information it should originally contain by inputting the posted information and instruction information that instructs the AI to estimate the content of an article containing the information it should originally contain based on multiple perspectives, A second processing unit provides the generating AI with the posted information, the inference results from the first processing unit, and instruction information that instructs the generating AI to estimate information that is desirable to supplement the articles contained in the posted information, thereby causing the generating AI to infer missing information in the articles. A providing unit that provides information indicating the missing information obtained as a result of processing by the second processing unit, An information processing device characterized by comprising:
2. The first processing unit is, Instructions are input to the generating AI instructing it to estimate the content of an article that should contain the information it should have, based on at least one of the following: the topic the article in the posted information is concerned with, the pattern of comments in the posted information, the consistency between the content of the article in the posted information and the content of the comments in the posted information, and the opinion of an expert in the field corresponding to the topic. The information processing apparatus according to feature 1.
3. The aforementioned supply unit is, Information indicating the missing information will be provided to the poster who posted the article included in the posted information. The information processing apparatus according to feature 1.
4. The aforementioned supply unit is, Information indicating the missing information is provided in association with the relevant section of the article included in the posted information. The information processing apparatus according to claim 3.
5. The aforementioned supply unit is, Subject to obtaining approval from the author of the article included in the aforementioned posted information, or from an expert corresponding to the topic covered by the article, the missing information will be reflected in the article included in the aforementioned posted information. The information processing apparatus according to feature 1.
6. A method of information processing performed by a computer, The acquisition process involves obtaining post information, including articles and comments on those articles, A first processing step involves inputting the posted information and instruction information that instructs the generating AI, which has been trained to generate answers to input questions, to estimate the content of an article containing the information it should originally contain, based on multiple perspectives, thereby causing the generating AI to infer the content of an article containing the information it should originally contain. A second processing step involves inputting the posting information, the inference result from the first processing step, and instruction information that instructs the generating AI to estimate information that is desirable to supplement the article contained in the posting information, thereby causing the generating AI to infer missing information in the article. A providing step that provides information indicating missing information obtained as a result of processing by the second processing step, An information processing method characterized by including
7. On the computer, Procedure for retrieving posted information, including articles and comments on those articles, A first processing step involves inputting the posted information and instruction information that instructs the generating AI, which has been trained to generate answers to input questions, to estimate the content of an article containing the information it should originally contain, based on multiple perspectives, thereby causing the generating AI to infer the content of an article containing the information it should originally contain. A second processing step involves inputting the posting information, the inference result from the first processing step, and instruction information that instructs the generating AI to estimate information that is desirable to supplement the article contained in the posting information, thereby causing the generating AI to infer missing information in the article. A procedure for providing information indicating missing information obtained as a result of processing by the second processing procedure described above, and An information processing program characterized by causing the execution of [a specific action].