System

Abstract

To provide a system according to an embodiment that efficiently conducts the fact check of news articles.SOLUTION: A system according to an embodiment comprises a collection unit, a cross-check unit, and an alert unit. The collection unit collects news articles related to the same subject from a plurality of information sources. The cross-check unit conducts cross-check of the news articles collected by the collection unit between the plurality of information sources. The alert unit issues an alert to a journalist on the basis of a result of the cross-check conducted by the cross-check unit.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including a description and related instruction sentence regarding the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional techniques have the drawback that it is difficult to efficiently cross-check information from different sources when fact-checking news articles.

[0005] The system according to the embodiment aims to efficiently perform fact-checking of news articles. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, a cross-check unit, and an alert unit. The collection unit collects news articles on the same subject from each of a plurality of information sources. The cross-check unit cross-checks the news articles collected by the collection unit among the plurality of information sources. The alert unit issues an alert to a journalist based on the result of the cross-check by the cross-check unit. Effect of the Invention

[0007] The system according to the embodiment can efficiently perform fact checking of news articles. [Brief description of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0013] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0024] As shown in Fig. 2, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific process program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A news article fact-checking system according to an embodiment of the present invention is a system for making the fact-checking of news articles more efficient. The system collects news articles related to the same subject from multiple information sources, cross-checks the collected news articles, and detects inconsistencies and contradictions. An alert is issued to the journalist based on the results of the cross-check. For example, a collection unit collects news articles related to the same subject from multiple information sources. Next, a cross-check unit cross-checks the collected news articles to detect inconsistencies and contradictions. The cross-check unit issues an alert to the journalist based on the detected inconsistencies and contradictions. The cross-check unit further includes a determination unit that determines the importance of each element of the news article. The determination unit determines the importance of the detected inconsistencies and contradictions, and notifies the journalist of the result by including it in an alert. The system also includes a reception unit that receives a selection of a news article from a specific information source from the journalist. The cross-check unit further includes an evaluation unit that evaluates the reliability of each information source based on the cross-check result. This allows the news article fact-checking system to make the fact-checking of news articles more efficient and notify the journalist of information having an abnormal pattern.

[0029] The news article fact-checking system according to the embodiment includes a collection unit, a cross-check unit, and an alert unit. The collection unit collects news articles related to the same subject from each of a plurality of information sources. The collection unit can collect news articles from information sources such as newspapers, online news sites, and blogs. The collection unit can collect news articles using an API, or can collect news articles using scraping technology. The cross-check unit cross-checks the news articles collected by the collection unit between a plurality of information sources. The cross-check unit can compare the contents of the news articles using, for example, text matching technology to detect inconsistencies and contradictions. The cross-check unit can also verify the contents of the news articles using database matching technology. The alert unit issues an alert to a journalist based on the result of the cross-check by the cross-check unit. The alert unit can issue an alert to a journalist using, for example, an email notification or a pop-up notification. The alert unit can also issue an alert to a journalist using a real-time notification or a regular notification. This allows the news article fact-checking system to make the fact-checking of news articles more efficient and to notify the journalist of information having an abnormal pattern.

[0030] The collection unit collects news articles on the same subject from each of a plurality of information sources. The collection unit can collect news articles from information sources such as newspapers, online news sites, and blogs. Specifically, the latest news articles are automatically acquired using digital archives of newspapers, RSS feeds of online news sites, and public APIs of blogs. The collection unit can collect news articles using APIs, or can collect news articles using scraping technology. When using APIs, requests are periodically sent to API endpoints provided by each information source to acquire the latest news article data. When using scraping technology, the HTML structure of a webpage is analyzed to extract necessary information. For example, information such as article titles, text, and publication dates are extracted from webpages using libraries such as Python's BeautifulSoup and Scrapy. The collection unit can combine these technologies to efficiently and comprehensively collect news articles. Furthermore, the collection unit has a database for centrally managing collected news articles, and collected articles are stored in this database. The database stores the full text of the articles along with article metadata (e.g., publication date, source, author, etc.). This enables the collection section to efficiently collect a variety of news articles from a wide range of sources and make them available to the subsequent cross-check and alert sections.

[0031] The cross-check unit cross-checks the news articles collected by the collection unit across multiple sources. The cross-check unit, for example, uses text matching technology to compare the contents of the news articles and detect inconsistencies and contradictions. Specifically, it uses natural language processing (NLP) technology to tokenize the contents of the articles and extract important keywords and phrases. This makes it possible to compare the contents of articles collected from different sources and identify commonalities and differences. The cross-check unit can also verify the contents of the news articles using database matching technology. For example, it evaluates the credibility of the articles by matching them with existing reliable databases (for example, official government announcements and reliable news archives). In addition, the cross-check unit can introduce advanced analysis technology using AI. For example, it uses a generation AI to automatically summarize the contents of the collected articles and perform a cross-check based on the summarized contents. The generation AI extracts important points of the articles and evaluates the degree of agreement between different sources. This allows the cross-check unit to quickly and accurately compare the contents of the collected news articles and identify reliable information. In addition, the cross-check unit can learn from past cross-check results and continuously improve its accuracy. This enables the Cross-Check Department to efficiently fact-check news articles and provide highly reliable information.

[0032] The alert unit issues an alert to the journalist based on the result of the cross-check by the cross-check unit. The alert unit can issue an alert to the journalist using, for example, an email notification or a pop-up notification. Specifically, when the cross-check unit detects a discrepancy or inconsistency, the information is sent to the alert unit, and the alert unit immediately notifies the journalist. In the case of an email notification, detailed alert content is sent to the journalist's email address, and in the case of a pop-up notification, the notification is displayed in real time on the news editing system or browser used by the journalist. The alert unit can also issue an alert to the journalist using real-time notification or periodic notification. In the case of real-time notification, the notification is sent immediately as soon as the cross-check result is obtained, and in the case of periodic notification, the cross-check result is notified collectively at regular time intervals. Furthermore, the alert unit can set the priority of the notification. For example, when a significant discrepancy or inconsistency is detected, it is notified as a high-priority alert, so that the journalist can respond quickly. Furthermore, the alert unit can customize the notification content. For example, it notifies only highly relevant alerts based on the journalist's field of interest or the article he is in charge of. This allows the alert unit to quickly provide appropriate information to the journalist and to efficiently check the facts of news articles. In addition, the alert unit can save notification history and refer to past alert contents, allowing journalists to check past cross-check results and alert contents and continue fact-checking work.

[0033] The cross-check unit includes a unit for detecting inconsistencies or contradictions between multiple information sources of news articles. The cross-check unit, for example, uses text matching technology to compare the contents of the news articles and detects inconsistencies or contradictions. The cross-check unit can also verify the contents of the news articles using database matching technology. For example, the cross-check unit analyzes the text of the news articles and detects differences between different information sources. The cross-check unit can also compare a database of news articles and detect data inconsistencies. This improves the accuracy of fact-checking by detecting inconsistencies or contradictions in the news articles.

[0034] The alert unit can alert the journalist to the information including the inconsistencies or discrepancies detected by the detection unit. The alert unit can issue an alert to the journalist using, for example, an email notification or a pop-up notification. The alert unit can also issue an alert to the journalist using a real-time notification or a periodic notification. For example, the alert unit notifies the journalist of the information including the inconsistencies or discrepancies detected by the detection unit by email. The alert unit can also notify the journalist of the information including the inconsistencies or discrepancies detected by the detection unit by a pop-up notification. This makes it possible to quickly notify the journalist of important inconsistencies or discrepancies.

[0035] The cross-check unit may include a unit for determining the importance of each element of a news article. For example, the cross-check unit performs a determination based on the influence of the news and the interest of readers in order to determine the importance of each element of a news article. For example, the cross-check unit analyzes elements of a news article, such as time, place, person, numerical value, quote, and statement, and determines the importance of each. The cross-check unit can also evaluate the influence of a news article and determine its importance. For example, the cross-check unit analyzes the interest of readers in a news article and determines its importance. In this way, important information can be preferentially processed by determining the importance of each element of a news article.

[0036] The determination unit can alert the journalist to information including the determination result for the inconsistency or contradiction detected by the detection unit. The determination unit, for example, determines the importance of the inconsistency or contradiction detected by the detection unit, and notifies the journalist of the result by including it in an alert. For example, the determination unit scores the importance of the detected inconsistency or contradiction, and notifies the journalist of the score by including it in an alert. The determination unit can also notify the journalist of the reason for the determination of the detected inconsistency or contradiction by including it in the alert. This enables efficient fact-finding by determining the importance of the inconsistency or contradiction and notifying the journalist.

[0037] Each element of a news article can be an element relating to time, place, person, number, quote, or statement. Each element of a news article includes, for example, an element relating to time, an element relating to place, an element relating to person, an element relating to number, an element relating to quote, an element relating to statement, and the like. For example, an element relating to time includes the date and time when the news article occurred and the date and time when it was reported. An element relating to place includes the place where the news article occurred and the place where it was reported. An element relating to person includes the name and the title of a person appearing in the news article. An element relating to number includes numerical data written in the news article. An element relating to quote includes statements and documents quoted in the news article. An element relating to statement includes the content of statements written in the news article. This enables more accurate fact-checking by classifying each element of a news article in detail.

[0038] The information processing system may include a reception unit that receives a selection of news articles from a specific information source from a journalist. The reception unit, for example, provides an interface for receiving a selection of news articles from a specific information source from a journalist. For example, the reception unit provides an online form for the journalist to select the specific information source. The reception unit may also provide an email reception for the journalist to select the specific information source. This allows the journalist to customize the news articles to be collected by selecting a specific information source.

[0039] The collection unit can collect news articles on the same subject, including the news article whose selection has been accepted by the acceptance unit, from each of the multiple information sources. For example, the collection unit collects news articles from the multiple information sources using keywords related to the news article selected by the acceptance unit. The collection unit can also collect news articles from the multiple information sources based on topics related to the news article selected by the acceptance unit. This makes it possible to verify facts based on a specific information source by collecting the news articles selected by the acceptance unit.

[0040] The cross-check unit may include an evaluation unit that evaluates the reliability of each information source based on the cross-check result. The evaluation unit performs evaluation based on the past performance of the information source and the accuracy of the articles, for example, to evaluate the reliability of each information source based on the cross-check result. For example, the evaluation unit analyzes the accuracy of the information source's past news articles and evaluates the reliability. The evaluation unit can also evaluate the reliability based on the past performance of the information source. For example, the evaluation unit scores the accuracy of the information source's past news articles and evaluates the reliability based on the score. In this way, by evaluating the reliability of each information source, a highly reliable information source can be identified.

[0041] The collection unit can analyze the past collection history and select the optimal collection method. For example, the collection unit analyzes the trends of news articles collected in the past and preferentially collects news related to a specific topic. The collection unit can also adjust the type of news to be collected in a specific time period from the past collection history. Furthermore, the collection unit can also preferentially collect news from a specific information source based on the past collection history. This makes it possible to efficiently collect news articles by analyzing the past collection history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past collection history data to the generation AI and cause the generation AI to select the optimal collection method.

[0042] The collection unit can filter news articles based on a specific topic or keyword when collecting the news articles. For example, the collection unit filters news articles based on a specific keyword and collects only highly relevant articles. The collection unit can also preferentially collect news articles related to a specific topic. Furthermore, the collection unit can filter and collect news articles based on a keyword set by the user. This makes it possible to collect only highly relevant articles by filtering news articles based on a specific topic or keyword. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input a specific keyword to the generation AI and cause the generation AI to perform filtering based on the keyword.

[0043] When collecting news articles, the collection unit can preferentially collect highly relevant articles taking into account the geographical location information. For example, the collection unit preferentially collects local news articles based on the user's current location. The collection unit can also preferentially collect news articles related to a specific region. Furthermore, the collection unit can also collect highly relevant news articles based on a region set by the user. In this way, by taking into account the geographical location information, news articles that are highly relevant to the user can be preferentially collected. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect news articles based on the geographical location information.

[0044] The collection unit can analyze social media activities and collect related articles when collecting news articles. For example, the collection unit preferentially collects news articles related to topics that are trending on social media. The collection unit can also collect highly relevant news articles based on the user's social media activities. Furthermore, the collection unit can analyze social media trends and collect related news articles. In this way, news articles based on trends can be collected by analyzing social media activities. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without using AI. For example, the collection unit can input social media data to a generation AI and cause the generation AI to collect news articles based on trends.

[0045] The cross-check unit can improve the accuracy of the cross-check by considering the interrelationships between news articles during the cross-check. For example, the cross-check unit analyzes the interrelationships between news articles and cross-checks highly related articles. The cross-check unit can also detect inconsistencies by considering the interrelationships between news articles. Furthermore, the cross-check unit can improve the accuracy of the cross-check based on the interrelationships between news articles. As a result, the accuracy of the cross-check is improved by considering the interrelationships between news articles. A part or all of the above-mentioned processing in the cross-check unit may be performed, for example, using AI or may be performed without using AI. For example, the cross-check unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute the improvement of the accuracy of the cross-check based on the interrelationships.

[0046] The cross-check unit can perform the cross-check by taking into consideration the attribute information of the submitter of the news article. For example, the cross-check unit performs the cross-check by taking into consideration the reliability of the submitter of the news article. The cross-check unit can also perform the cross-check based on the past history of the submitter of the news article. Furthermore, the cross-check unit can improve the accuracy of the cross-check based on the attribute information of the submitter of the news article. As a result, the accuracy of the cross-check is improved by taking into consideration the attribute information of the submitter of the news article. A part or all of the above-mentioned processing in the cross-check unit may be performed using, for example, AI, or may be performed without using AI. For example, the cross-check unit can input the attribute information of the submitter of the news article to the generation AI and cause the generation AI to perform a cross-check based on the attribute information.

[0047] The cross-check unit can perform the cross-check while taking into consideration the geographical distribution of the news articles. For example, the cross-check unit analyzes the geographical distribution of the news articles and performs a cross-check between highly related regions. The cross-check unit can also detect inconsistencies while taking into consideration the geographical distribution of the news articles. Furthermore, the cross-check unit can improve the accuracy of the cross-check based on the geographical distribution of the news articles. As a result, the accuracy of the cross-check is improved by taking into consideration the geographical distribution of the news articles. A part or all of the above-mentioned processing in the cross-check unit may be performed, for example, using AI or may be performed without using AI. For example, the cross-check unit can input geographical distribution data of the news articles to the generation AI and cause the generation AI to perform a cross-check based on the geographical distribution.

[0048] The cross-check unit can improve the accuracy of the cross-check by referring to related literature during the cross-check. For example, the cross-check unit can evaluate the reliability of the news article by referring to related literature. The cross-check unit can also detect inconsistencies in the news article based on the related literature. Furthermore, the cross-check unit can improve the accuracy of the cross-check by referring to related literature. As a result, the accuracy of the cross-check is improved by referring to the related literature. A part or all of the above-mentioned processing in the cross-check unit may be performed, for example, using AI or may be performed without using AI. For example, the cross-check unit can input related literature data to the generation AI and cause the generation AI to execute a cross-check based on the literature.

[0049] The alert unit can adjust the level of detail of the alert based on the importance of the news article when issuing an alert. For example, the alert unit issues a detailed alert for a news article with high importance. The alert unit can also issue a concise alert for a news article with low importance. Furthermore, the alert unit can adjust the level of detail of the alert based on the importance of the news article. As a result, important information can be quickly notified by adjusting the level of detail of the alert based on the importance of the news article. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input the importance data of the news article to the generation AI and cause the generation AI to adjust the level of detail of the alert based on the importance.

[0050] The alert unit can apply different alert algorithms depending on the category of the news article when issuing an alert. For example, the alert unit applies a specific alert algorithm to political news. The alert unit can also apply a different alert algorithm to economic news. Furthermore, the alert unit can apply a dedicated alert algorithm to sports news. In this way, an appropriate alert can be issued by applying an alert algorithm depending on the category of the news article. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input category data of the news article to the generation AI and cause the generation AI to apply an alert algorithm based on the category.

[0051] The alert unit can determine the priority of the alert based on the submission time of the news article when issuing an alert. For example, the alert unit prioritizes issuing an alert for the latest news article. The alert unit can also lower the priority and issue an alert for an older news article. Furthermore, the alert unit can adjust the priority of the alert based on the submission time of the news article. This allows the latest information to be quickly notified by determining the priority of the alert based on the submission time of the news article. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input the submission time data of the news article to the generation AI and cause the generation AI to execute the determination of the priority of the alert based on the submission time.

[0052] The alert unit can adjust the order of alerts based on the relevance of news articles when issuing an alert. For example, the alert unit prioritizes issuing an alert for a highly relevant news article. The alert unit can also postpone the order of alerts for a less relevant news article. Furthermore, the alert unit can adjust the order of alerts based on the relevance of news articles. This allows important information to be quickly notified by adjusting the order of alerts based on the relevance of news articles. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input relevance data of news articles to the generation AI and cause the generation AI to adjust the order of alerts based on the relevance.

[0053] The detection unit can improve the accuracy of detection by considering the interrelationships between news articles at the time of detection. For example, the detection unit analyzes the interrelationships between news articles and detects inconsistencies between highly related articles. The detection unit can also detect contradictions by considering the interrelationships between news articles. Furthermore, the detection unit can improve the accuracy of detection based on the interrelationships between news articles. As a result, the accuracy of detection is improved by considering the interrelationships between news articles. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute the improvement of the accuracy of detection based on the interrelationships.

[0054] The detection unit can perform detection by taking into consideration attribute information of the submitter of the news article at the time of detection. For example, the detection unit performs detection by taking into consideration the reliability of the submitter of the news article. The detection unit can also perform detection based on the past history of the submitter of the news article. Furthermore, the detection unit can improve the accuracy of detection based on the attribute information of the submitter of the news article. As a result, the accuracy of detection is improved by taking into consideration the attribute information of the submitter of the news article. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the attribute information of the submitter of the news article to the generation AI and cause the generation AI to perform detection based on the attribute information.

[0055] The detection unit can perform detection by taking into account the geographic distribution of news articles. For example, the detection unit analyzes the geographic distribution of news articles and detects inconsistencies between highly related regions. The detection unit can also detect inconsistencies by taking into account the geographic distribution of news articles. Furthermore, the detection unit can improve the accuracy of detection based on the geographic distribution of news articles. As a result, the accuracy of detection is improved by taking into account the geographic distribution of news articles. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input geographic distribution data of news articles to the generation AI and cause the generation AI to perform detection based on the geographic distribution.

[0056] The detection unit can improve the accuracy of detection by referring to related literature at the time of detection. For example, the detection unit can evaluate the reliability of a news article by referring to related literature. The detection unit can also detect inconsistencies in a news article based on related literature. Furthermore, the detection unit can improve the accuracy of detection by referring to related literature. As a result, the accuracy of detection is improved by referring to related literature. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input related literature data to the generation AI and cause the generation AI to perform detection based on the literature.

[0057] The determination unit can improve the accuracy of the determination by considering the interrelationships between news articles at the time of determination. For example, the determination unit analyzes the interrelationships between news articles and determines the importance between highly related articles. The determination unit can also determine the importance of contradictions by considering the interrelationships between news articles. Furthermore, the determination unit can improve the accuracy of the determination based on the interrelationships between news articles. As a result, the accuracy of the determination is improved by considering the interrelationships between news articles. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or may be performed without using AI. For example, the determination unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute an improvement in the accuracy of the determination based on the interrelationships.

[0058] The determination unit can make a determination by taking into consideration attribute information of the submitter of the news article at the time of the determination. For example, the determination unit makes a determination by taking into consideration the reliability of the submitter of the news article. The determination unit can also make a determination based on the past history of the submitter of the news article. Furthermore, the determination unit can improve the accuracy of the determination based on the attribute information of the submitter of the news article. As a result, the accuracy of the determination is improved by taking into consideration the attribute information of the submitter of the news article. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or may be performed without using AI. For example, the determination unit can input attribute information of the submitter of the news article to the generation AI and cause the generation AI to perform a determination based on the attribute information.

[0059] The determination unit can make a determination taking into consideration the geographic distribution of news articles when making a determination. For example, the determination unit analyzes the geographic distribution of news articles and determines the importance between highly related regions. The determination unit can also determine the importance of a contradiction by taking into consideration the geographic distribution of news articles. Furthermore, the determination unit can improve the accuracy of the determination based on the geographic distribution of news articles. As a result, the accuracy of the determination is improved by taking into consideration the geographic distribution of news articles. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or may be performed without using AI. For example, the determination unit can input geographic distribution data of news articles to the generation AI and cause the generation AI to perform a determination based on the geographic distribution.

[0060] The judgment unit can improve the accuracy of the judgment by referring to the related literature at the time of judgment. For example, the judgment unit can evaluate the reliability of the news article by referring to the related literature. The judgment unit can also judge the importance of the contradictions in the news article based on the related literature. Furthermore, the judgment unit can improve the accuracy of the judgment by referring to the related literature. As a result, the accuracy of the judgment is improved by referring to the related literature. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input related literature data to the generation AI and cause the generation AI to execute a judgment based on the literature.

[0061] The reception unit can select the optimal reception method by referring to the user's past selection history at the time of reception. For example, the reception unit preferentially displays information sources that the user has frequently selected in the past. The reception unit can also preferentially suggest input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit can predict and suggest information sources to be used in a specific time period from the user's past selection history. This allows efficient reception by referring to the user's past selection history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past selection history data to the generation AI and cause the generation AI to select the optimal reception method based on the past selection history.

[0062] The reception unit can select the optimal reception method in consideration of the device information of the user at the time of reception. For example, when the user is using a smartphone, the reception unit provides a reception method that matches the screen size. In addition, when the user is using a tablet, the reception unit can also provide a reception method that is optimized for a large screen. Furthermore, when the user is using a smartwatch, the reception unit can also provide a simple and highly visible reception method. This enables efficient reception by considering the device information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the device information of the user to the generation AI and cause the generation AI to select the optimal reception method based on the device information.

[0063] The evaluation unit can improve the accuracy of the evaluation by considering the interrelationships between news articles during the evaluation. For example, the evaluation unit analyzes the interrelationships between news articles and evaluates the reliability between highly related articles. The evaluation unit can also evaluate the reliability by considering the interrelationships between news articles. Furthermore, the evaluation unit can improve the accuracy of the evaluation based on the interrelationships between news articles. As a result, the accuracy of the evaluation is improved by considering the interrelationships between news articles. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation based on the interrelationships.

[0064] The evaluation unit can perform the evaluation while taking into account the geographic distribution of the news articles. For example, the evaluation unit analyzes the geographic distribution of the news articles and evaluates the reliability between highly related regions. The evaluation unit can also evaluate the reliability while taking into account the geographic distribution of the news articles. Furthermore, the evaluation unit can improve the accuracy of the evaluation based on the geographic distribution of the news articles. As a result, the accuracy of the evaluation is improved by taking into account the geographic distribution of the news articles. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input geographic distribution data of the news articles to the generation AI and cause the generation AI to perform an evaluation based on the geographic distribution.

[0065] The evaluation unit can improve the accuracy of the evaluation by referring to related literature during the evaluation. For example, the evaluation unit can evaluate the reliability of a news article by referring to related literature. The evaluation unit can also evaluate the reliability of a news article based on the related literature. Furthermore, the evaluation unit can improve the accuracy of the evaluation by referring to related literature. As a result, the accuracy of the evaluation is improved by referring to the related literature. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input related literature data to the generation AI and cause the generation AI to perform an evaluation based on the literature.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] When collecting news articles, the collection unit can preferentially collect highly relevant articles by taking into account the user's past browsing history. For example, the collection unit preferentially collects news articles related to topics that the user has frequently browsed in the past. The collection unit can also collect articles related to news articles that the user has given high ratings in the past. Furthermore, the collection unit can adjust the type of news to be collected in a specific time period based on the user's past browsing history. This allows highly relevant news articles to be efficiently collected by taking into account the user's past browsing history.

[0068] The cross-check unit can generate a reliability score for evaluating the reliability of a news article when cross-checking the news article. For example, the cross-check unit generates a reliability score based on the reliability of the information source of the news article. The cross-check unit can also generate a reliability score based on the degree of agreement of the contents of the news articles. Furthermore, the cross-check unit can also generate a reliability score based on the past performance of the news article. In this way, by generating a reliability score for evaluating the reliability of a news article, a highly reliable news article can be identified.

[0069] When cross-checking a news article, the cross-check unit can apply different cross-check algorithms depending on the category of the news article. For example, the cross-check unit applies a specific cross-check algorithm to political news. The cross-check unit can also apply a different cross-check algorithm to economic news. Furthermore, the cross-check unit can also apply a dedicated cross-check algorithm to sports news. This allows for highly accurate cross-checking by applying a cross-check algorithm depending on the category of the news article.

[0070] The determination unit can take into account the social media response of the news article when determining the importance of the news article. For example, if the news article has received many shares and comments on social media, the determination unit determines the importance of the news article to be high. Also, if the news article has received little response on social media, the determination unit can determine the importance of the news article to be low. Furthermore, the determination unit can score the response of the news article on social media and determine the importance based on the score. In this way, by taking into account the response of the news article on social media, it is possible to determine the importance of the news article more accurately.

[0071] The cross-check unit can generate a reliability score for evaluating the reliability of a news article when cross-checking the news article. For example, the cross-check unit generates a reliability score based on the reliability of the information source of the news article. The cross-check unit can also generate a reliability score based on the degree of agreement of the contents of the news articles. Furthermore, the cross-check unit can also generate a reliability score based on the past performance of the news article. In this way, by generating a reliability score for evaluating the reliability of a news article, a highly reliable news article can be identified.

[0072] When cross-checking a news article, the cross-check unit can apply different cross-check algorithms depending on the category of the news article. For example, the cross-check unit applies a specific cross-check algorithm to political news. The cross-check unit can also apply a different cross-check algorithm to economic news. Furthermore, the cross-check unit can also apply a dedicated cross-check algorithm to sports news. This allows for highly accurate cross-checking by applying a cross-check algorithm depending on the category of the news article.

[0073] The determination unit can take into account the social media response of the news article when determining the importance of the news article. For example, if the news article has received many shares and comments on social media, the determination unit determines the importance of the news article to be high. Also, if the news article has received little response on social media, the determination unit can determine the importance of the news article to be low. Furthermore, the determination unit can score the response of the news article on social media and determine the importance based on the score. In this way, by taking into account the response of the news article on social media, it is possible to determine the importance of the news article more accurately.

[0074] The process flow of the first embodiment will be briefly described below.

[0075] Step 1: The collection unit collects news articles about the same subject from each of a plurality of information sources. The collection unit can collect news articles from information sources such as newspapers, online news sites, blogs, etc. The collection unit can collect news articles using an API or scraping technology. Step 2: The cross-checking unit cross-checks the news articles collected by the collecting unit across multiple sources. The cross-checking unit compares the contents of the news articles using, for example, text matching techniques to detect inconsistencies and contradictions. The cross-checking unit can also verify the contents of the news articles using database matching techniques. Step 3: The alert unit issues an alert to the journalist based on the result of the crosscheck by the crosscheck unit. The alert unit can issue an alert to the journalist using, for example, an email notification or a pop-up notification. The alert unit can also issue an alert to the journalist using a real-time notification or a periodic notification.

[0076] (Example 2) A news article fact-checking system according to an embodiment of the present invention is a system for making the fact-checking of news articles more efficient. The system collects news articles related to the same subject from multiple information sources, cross-checks the collected news articles, and detects inconsistencies and contradictions. An alert is issued to the journalist based on the results of the cross-check. For example, a collection unit collects news articles related to the same subject from multiple information sources. Next, a cross-check unit cross-checks the collected news articles to detect inconsistencies and contradictions. The cross-check unit issues an alert to the journalist based on the detected inconsistencies and contradictions. The cross-check unit further includes a determination unit that determines the importance of each element of the news article. The determination unit determines the importance of the detected inconsistencies and contradictions, and notifies the journalist of the result by including it in an alert. The system also includes a reception unit that receives a selection of a news article from a specific information source from the journalist. The cross-check unit further includes an evaluation unit that evaluates the reliability of each information source based on the cross-check result. This allows the news article fact-checking system to make the fact-checking of news articles more efficient and notify the journalist of information having an abnormal pattern.

[0077] The news article fact-checking system according to the embodiment includes a collection unit, a cross-check unit, and an alert unit. The collection unit collects news articles related to the same subject from each of a plurality of information sources. The collection unit can collect news articles from information sources such as newspapers, online news sites, and blogs. The collection unit can collect news articles using an API, or can collect news articles using scraping technology. The cross-check unit cross-checks the news articles collected by the collection unit between a plurality of information sources. The cross-check unit can compare the contents of the news articles using, for example, text matching technology to detect inconsistencies and contradictions. The cross-check unit can also verify the contents of the news articles using database matching technology. The alert unit issues an alert to a journalist based on the result of the cross-check by the cross-check unit. The alert unit can issue an alert to a journalist using, for example, an email notification or a pop-up notification. The alert unit can also issue an alert to a journalist using a real-time notification or a regular notification. This allows the news article fact-checking system to make the fact-checking of news articles more efficient and to notify the journalist of information having an abnormal pattern.

[0078] The collection unit collects news articles on the same subject from each of a plurality of information sources. The collection unit can collect news articles from information sources such as newspapers, online news sites, and blogs. Specifically, the latest news articles are automatically acquired using digital archives of newspapers, RSS feeds of online news sites, and public APIs of blogs. The collection unit can collect news articles using APIs, or can collect news articles using scraping technology. When using APIs, requests are periodically sent to API endpoints provided by each information source to acquire the latest news article data. When using scraping technology, the HTML structure of a webpage is analyzed to extract necessary information. For example, information such as article titles, text, and publication dates are extracted from webpages using libraries such as Python's BeautifulSoup and Scrapy. The collection unit can combine these technologies to efficiently and comprehensively collect news articles. Furthermore, the collection unit has a database for centrally managing collected news articles, and collected articles are stored in this database. The database stores the full text of the articles along with article metadata (e.g., publication date, source, author, etc.). This enables the collection section to efficiently collect a variety of news articles from a wide range of sources and make them available to the subsequent cross-check and alert sections.

[0079] The cross-check unit cross-checks the news articles collected by the collection unit across multiple sources. The cross-check unit, for example, uses text matching technology to compare the contents of the news articles and detect inconsistencies and contradictions. Specifically, it uses natural language processing (NLP) technology to tokenize the contents of the articles and extract important keywords and phrases. This makes it possible to compare the contents of articles collected from different sources and identify commonalities and differences. The cross-check unit can also verify the contents of the news articles using database matching technology. For example, it evaluates the credibility of the articles by matching them with existing reliable databases (for example, official government announcements and reliable news archives). In addition, the cross-check unit can introduce advanced analysis technology using AI. For example, it uses a generation AI to automatically summarize the contents of the collected articles and perform a cross-check based on the summarized contents. The generation AI extracts important points of the articles and evaluates the degree of agreement between different sources. This allows the cross-check unit to quickly and accurately compare the contents of the collected news articles and identify reliable information. In addition, the cross-check unit can learn from past cross-check results and continuously improve its accuracy. This enables the Cross-Check Department to efficiently fact-check news articles and provide highly reliable information.

[0080] The alert unit issues an alert to the journalist based on the result of the cross-check by the cross-check unit. The alert unit can issue an alert to the journalist using, for example, an email notification or a pop-up notification. Specifically, when the cross-check unit detects a discrepancy or inconsistency, the information is sent to the alert unit, and the alert unit immediately notifies the journalist. In the case of an email notification, detailed alert content is sent to the journalist's email address, and in the case of a pop-up notification, the notification is displayed in real time on the news editing system or browser used by the journalist. The alert unit can also issue an alert to the journalist using real-time notification or periodic notification. In the case of real-time notification, the notification is sent immediately as soon as the cross-check result is obtained, and in the case of periodic notification, the cross-check result is notified collectively at regular time intervals. Furthermore, the alert unit can set the priority of the notification. For example, when a significant discrepancy or inconsistency is detected, it is notified as a high-priority alert, so that the journalist can respond quickly. Furthermore, the alert unit can customize the notification content. For example, it notifies only highly relevant alerts based on the journalist's field of interest or the article he is in charge of. This allows the alert unit to quickly provide appropriate information to the journalist and to efficiently check the facts of news articles. In addition, the alert unit can save notification history and refer to past alert contents, allowing journalists to check past cross-check results and alert contents and continue fact-checking work.

[0081] The cross-check unit includes a unit for detecting inconsistencies or contradictions between multiple information sources of news articles. The cross-check unit, for example, uses text matching technology to compare the contents of the news articles and detects inconsistencies or contradictions. The cross-check unit can also verify the contents of the news articles using database matching technology. For example, the cross-check unit analyzes the text of the news articles and detects differences between different information sources. The cross-check unit can also compare a database of news articles and detect data inconsistencies. This improves the accuracy of fact-checking by detecting inconsistencies or contradictions in the news articles.

[0082] The alert unit can alert the journalist to the information including the inconsistencies or discrepancies detected by the detection unit. The alert unit can issue an alert to the journalist using, for example, an email notification or a pop-up notification. The alert unit can also issue an alert to the journalist using a real-time notification or a periodic notification. For example, the alert unit notifies the journalist of the information including the inconsistencies or discrepancies detected by the detection unit by email. The alert unit can also notify the journalist of the information including the inconsistencies or discrepancies detected by the detection unit by a pop-up notification. This makes it possible to quickly notify the journalist of important inconsistencies or discrepancies.

[0083] The cross-check unit may include a unit for determining the importance of each element of a news article. For example, the cross-check unit performs a determination based on the influence of the news and the interest of readers in order to determine the importance of each element of a news article. For example, the cross-check unit analyzes elements of a news article, such as time, place, person, numerical value, quote, and statement, and determines the importance of each. The cross-check unit can also evaluate the influence of a news article and determine its importance. For example, the cross-check unit analyzes the interest of readers in a news article and determines its importance. In this way, important information can be preferentially processed by determining the importance of each element of a news article.

[0084] The determination unit can alert the journalist to information including the determination result for the inconsistency or contradiction detected by the detection unit. The determination unit, for example, determines the importance of the inconsistency or contradiction detected by the detection unit, and notifies the journalist of the result by including it in an alert. For example, the determination unit scores the importance of the detected inconsistency or contradiction, and notifies the journalist of the score by including it in an alert. The determination unit can also notify the journalist of the reason for the determination of the detected inconsistency or contradiction by including it in the alert. This enables efficient fact-finding by determining the importance of the inconsistency or contradiction and notifying the journalist.

[0085] Each element of a news article can be an element relating to time, place, person, number, quote, or statement. Each element of a news article includes, for example, an element relating to time, an element relating to place, an element relating to person, an element relating to number, an element relating to quote, an element relating to statement, and the like. For example, an element relating to time includes the date and time when the news article occurred and the date and time when it was reported. An element relating to place includes the place where the news article occurred and the place where it was reported. An element relating to person includes the name and the title of a person appearing in the news article. An element relating to number includes numerical data written in the news article. An element relating to quote includes statements and documents quoted in the news article. An element relating to statement includes the content of statements written in the news article. This enables more accurate fact-checking by classifying each element of a news article in detail.

[0086] The information processing system may include a reception unit that receives a selection of news articles from a specific information source from a journalist. The reception unit, for example, provides an interface for receiving a selection of news articles from a specific information source from a journalist. For example, the reception unit provides an online form for the journalist to select the specific information source. The reception unit may also provide an email reception for the journalist to select the specific information source. This allows the journalist to customize the news articles to be collected by selecting a specific information source.

[0087] The collection unit can collect news articles on the same subject, including the news article whose selection has been accepted by the acceptance unit, from each of the multiple information sources. For example, the collection unit collects news articles from the multiple information sources using keywords related to the news article selected by the acceptance unit. The collection unit can also collect news articles from the multiple information sources based on topics related to the news article selected by the acceptance unit. This makes it possible to verify facts based on a specific information source by collecting the news articles selected by the acceptance unit.

[0088] The cross-check unit may include an evaluation unit that evaluates the reliability of each information source based on the cross-check result. The evaluation unit performs evaluation based on the past performance of the information source and the accuracy of the articles, for example, to evaluate the reliability of each information source based on the cross-check result. For example, the evaluation unit analyzes the accuracy of the information source's past news articles and evaluates the reliability. The evaluation unit can also evaluate the reliability based on the past performance of the information source. For example, the evaluation unit scores the accuracy of the information source's past news articles and evaluates the reliability based on the score. In this way, by evaluating the reliability of each information source, a highly reliable information source can be identified.

[0089] The collection unit can estimate the user's emotion and adjust the timing of collecting news articles based on the estimated user's emotion. The collection unit, for example, estimates the user's emotion and adjusts the timing of collecting news articles based on the estimated user's emotion. For example, when the user is stressed, the collection unit reduces the collection frequency and collects only important news. Also, when the user is relaxed, the collection unit can increase the collection frequency and collect a wide range of news. Furthermore, when the user is in a hurry, the collection unit preferentially collects important news in real time. This reduces the burden on the user by adjusting the timing of collecting news articles according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the collection timing based on the emotion.

[0090] The collection unit can analyze the past collection history and select the optimal collection method. For example, the collection unit analyzes the trends of news articles collected in the past and preferentially collects news related to a specific topic. The collection unit can also adjust the type of news to be collected in a specific time period from the past collection history. Furthermore, the collection unit can also preferentially collect news from a specific information source based on the past collection history. This makes it possible to efficiently collect news articles by analyzing the past collection history. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can input past collection history data to the generation AI and cause the generation AI to select the optimal collection method.

[0091] The collection unit can filter news articles based on a specific topic or keyword when collecting the news articles. For example, the collection unit filters news articles based on a specific keyword and collects only highly relevant articles. The collection unit can also preferentially collect news articles related to a specific topic. Furthermore, the collection unit can filter and collect news articles based on a keyword set by the user. This makes it possible to collect only highly relevant articles by filtering news articles based on a specific topic or keyword. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input a specific keyword to the generation AI and cause the generation AI to perform filtering based on the keyword.

[0092] The collection unit can estimate the user's emotion and determine the priority of the news articles to be collected based on the estimated user's emotion. For example, when the user is feeling stressed, the collection unit preferentially collects positive news articles. Also, when the user is relaxed, the collection unit can collect news articles of a wide range of topics. Furthermore, when the user is in a hurry, the collection unit can preferentially collect important news articles. In this way, by determining the priority of news articles according to the user's emotion, it is possible to preferentially collect news that is important to the user. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the collection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the collection unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of news articles based on emotion.

[0093] When collecting news articles, the collection unit can preferentially collect highly relevant articles taking into account the geographical location information. For example, the collection unit preferentially collects local news articles based on the user's current location. The collection unit can also preferentially collect news articles related to a specific region. Furthermore, the collection unit can also collect highly relevant news articles based on a region set by the user. In this way, by taking into account the geographical location information, news articles that are highly relevant to the user can be preferentially collected. A part or all of the above-mentioned processing in the collection unit may be performed, for example, using AI or may be performed without using AI. For example, the collection unit can input the user's geographical location information to the generation AI and cause the generation AI to collect news articles based on the geographical location information.

[0094] The collection unit can analyze social media activities and collect related articles when collecting news articles. For example, the collection unit preferentially collects news articles related to topics that are trending on social media. The collection unit can also collect highly relevant news articles based on the user's social media activities. Furthermore, the collection unit can analyze social media trends and collect related news articles. In this way, news articles based on trends can be collected by analyzing social media activities. Some or all of the above-mentioned processing in the collection unit can be performed, for example, using AI or without using AI. For example, the collection unit can input social media data to a generation AI and cause the generation AI to collect news articles based on trends.

[0095] The cross-check unit can estimate the user's emotions and adjust the cross-check criteria based on the estimated user's emotions. For example, when the user is stressed, the cross-check unit relaxes the cross-check criteria and detects only important discrepancies. In addition, when the user is relaxed, the cross-check unit can also tighten the cross-check criteria and detect detailed discrepancies. Furthermore, when the user is in a hurry, the cross-check unit can adjust the cross-check criteria and quickly detect discrepancies. This reduces the burden on the user by adjusting the cross-check criteria according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the cross-check unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the cross-check unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the cross-check criteria based on the emotion.

[0096] The cross-check unit can improve the accuracy of the cross-check by considering the interrelationships between news articles during the cross-check. For example, the cross-check unit analyzes the interrelationships between news articles and cross-checks highly related articles. The cross-check unit can also detect inconsistencies by considering the interrelationships between news articles. Furthermore, the cross-check unit can improve the accuracy of the cross-check based on the interrelationships between news articles. As a result, the accuracy of the cross-check is improved by considering the interrelationships between news articles. A part or all of the above-mentioned processing in the cross-check unit may be performed, for example, using AI or may be performed without using AI. For example, the cross-check unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute the improvement of the accuracy of the cross-check based on the interrelationships.

[0097] The cross-check unit can perform the cross-check by taking into consideration the attribute information of the submitter of the news article. For example, the cross-check unit performs the cross-check by taking into consideration the reliability of the submitter of the news article. The cross-check unit can also perform the cross-check based on the past history of the submitter of the news article. Furthermore, the cross-check unit can improve the accuracy of the cross-check based on the attribute information of the submitter of the news article. As a result, the accuracy of the cross-check is improved by taking into consideration the attribute information of the submitter of the news article. A part or all of the above-mentioned processing in the cross-check unit may be performed using, for example, AI, or may be performed without using AI. For example, the cross-check unit can input the attribute information of the submitter of the news article to the generation AI and cause the generation AI to perform a cross-check based on the attribute information.

[0098] The cross-check unit can estimate the user's emotions and adjust the order of displaying the cross-check results based on the estimated user's emotions. For example, when the user is feeling stressed, the cross-check unit can preferentially display important cross-check results. In addition, when the user is relaxed, the cross-check unit can also display detailed cross-check results. Furthermore, when the user is in a hurry, the cross-check unit can also preferentially display cross-check results that can be checked quickly. This reduces the burden on the user by adjusting the order of displaying the cross-check results according to the user's emotions. The estimation of emotions is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the cross-check unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the cross-check unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display order of the cross-check results based on the emotion.

[0099] The cross-check unit can perform the cross-check while taking into consideration the geographical distribution of the news articles. For example, the cross-check unit analyzes the geographical distribution of the news articles and performs a cross-check between highly related regions. The cross-check unit can also detect inconsistencies while taking into consideration the geographical distribution of the news articles. Furthermore, the cross-check unit can improve the accuracy of the cross-check based on the geographical distribution of the news articles. As a result, the accuracy of the cross-check is improved by taking into consideration the geographical distribution of the news articles. A part or all of the above-mentioned processing in the cross-check unit may be performed, for example, using AI or may be performed without using AI. For example, the cross-check unit can input geographical distribution data of the news articles to the generation AI and cause the generation AI to perform a cross-check based on the geographical distribution.

[0100] The cross-check unit can improve the accuracy of the cross-check by referring to related literature during the cross-check. For example, the cross-check unit can evaluate the reliability of the news article by referring to related literature. The cross-check unit can also detect inconsistencies in the news article based on the related literature. Furthermore, the cross-check unit can improve the accuracy of the cross-check by referring to related literature. As a result, the accuracy of the cross-check is improved by referring to the related literature. A part or all of the above-mentioned processing in the cross-check unit may be performed, for example, using AI or may be performed without using AI. For example, the cross-check unit can input related literature data to the generation AI and cause the generation AI to execute a cross-check based on the literature.

[0101] The alert unit can estimate the user's emotion and adjust the way of expressing the alert based on the estimated user's emotion. For example, the alert unit displays a simple and highly visible alert when the user is feeling stressed. The alert unit can also display an alert including detailed information when the user is relaxed. Furthermore, the alert unit can display an alert that can be quickly confirmed when the user is in a hurry. This reduces the burden on the user by adjusting the way of expressing the alert according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the alert unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the alert unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the way of expressing the alert based on the emotion.

[0102] The alert unit can adjust the level of detail of the alert based on the importance of the news article when issuing an alert. For example, the alert unit issues a detailed alert for a news article with high importance. The alert unit can also issue a concise alert for a news article with low importance. Furthermore, the alert unit can adjust the level of detail of the alert based on the importance of the news article. As a result, important information can be quickly notified by adjusting the level of detail of the alert based on the importance of the news article. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input the importance data of the news article to the generation AI and cause the generation AI to adjust the level of detail of the alert based on the importance.

[0103] The alert unit can apply different alert algorithms depending on the category of the news article when issuing an alert. For example, the alert unit applies a specific alert algorithm to political news. The alert unit can also apply a different alert algorithm to economic news. Furthermore, the alert unit can apply a dedicated alert algorithm to sports news. In this way, an appropriate alert can be issued by applying an alert algorithm depending on the category of the news article. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input category data of the news article to the generation AI and cause the generation AI to apply an alert algorithm based on the category.

[0104] The alert unit can estimate the user's emotion and adjust the length of the alert based on the estimated user's emotion. For example, the alert unit issues a short and to the point alert when the user is stressed. Also, the alert unit can issue a longer alert including detailed information when the user is relaxed. Furthermore, the alert unit can issue a short alert that can be quickly confirmed when the user is in a hurry. This reduces the burden on the user by adjusting the length of the alert according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the alert unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the alert unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the length of the alert based on the emotion.

[0105] The alert unit can determine the priority of the alert based on the submission time of the news article when issuing an alert. For example, the alert unit prioritizes issuing an alert for the latest news article. The alert unit can also lower the priority and issue an alert for an older news article. Furthermore, the alert unit can adjust the priority of the alert based on the submission time of the news article. This allows the latest information to be quickly notified by determining the priority of the alert based on the submission time of the news article. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input the submission time data of the news article to the generation AI and cause the generation AI to execute the determination of the priority of the alert based on the submission time.

[0106] The alert unit can adjust the order of alerts based on the relevance of news articles when issuing an alert. For example, the alert unit prioritizes issuing an alert for a highly relevant news article. The alert unit can also postpone the order of alerts for a less relevant news article. Furthermore, the alert unit can adjust the order of alerts based on the relevance of news articles. This allows important information to be quickly notified by adjusting the order of alerts based on the relevance of news articles. Some or all of the above-mentioned processing in the alert unit may be performed, for example, using AI or may be performed without using AI. For example, the alert unit can input relevance data of news articles to the generation AI and cause the generation AI to adjust the order of alerts based on the relevance.

[0107] The detection unit can estimate the user's emotion and adjust the detection criteria for mismatches and contradictions based on the estimated user's emotion. For example, when the user is stressed, the detection unit relaxes the detection criteria and detects only important mismatches. Also, when the user is relaxed, the detection unit can tighten the detection criteria and detect detailed mismatches. Furthermore, when the user is in a hurry, the detection unit can adjust the detection criteria and quickly detect mismatches. This reduces the burden on the user by adjusting the detection criteria according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the detection criteria based on the emotion.

[0108] The detection unit can improve the accuracy of detection by considering the interrelationships between news articles at the time of detection. For example, the detection unit analyzes the interrelationships between news articles and detects inconsistencies between highly related articles. The detection unit can also detect contradictions by considering the interrelationships between news articles. Furthermore, the detection unit can improve the accuracy of detection based on the interrelationships between news articles. As a result, the accuracy of detection is improved by considering the interrelationships between news articles. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute the improvement of the accuracy of detection based on the interrelationships.

[0109] The detection unit can perform detection by taking into consideration attribute information of the submitter of the news article at the time of detection. For example, the detection unit performs detection by taking into consideration the reliability of the submitter of the news article. The detection unit can also perform detection based on the past history of the submitter of the news article. Furthermore, the detection unit can improve the accuracy of detection based on the attribute information of the submitter of the news article. As a result, the accuracy of detection is improved by taking into consideration the attribute information of the submitter of the news article. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, AI, or may be performed without using AI. For example, the detection unit can input the attribute information of the submitter of the news article to the generation AI and cause the generation AI to perform detection based on the attribute information.

[0110] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, when the user is stressed, the detection unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the detection unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the detection unit can also provide a display method that focuses on the main points. This reduces the burden on the user by adjusting the display method of the detection result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the detection unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the detection unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the detection result based on the emotion.

[0111] The detection unit can perform detection by taking into account the geographic distribution of news articles. For example, the detection unit analyzes the geographic distribution of news articles and detects inconsistencies between highly related regions. The detection unit can also detect inconsistencies by taking into account the geographic distribution of news articles. Furthermore, the detection unit can improve the accuracy of detection based on the geographic distribution of news articles. As a result, the accuracy of detection is improved by taking into account the geographic distribution of news articles. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input geographic distribution data of news articles to the generation AI and cause the generation AI to perform detection based on the geographic distribution.

[0112] The detection unit can improve the accuracy of detection by referring to related literature at the time of detection. For example, the detection unit can evaluate the reliability of a news article by referring to related literature. The detection unit can also detect inconsistencies in a news article based on related literature. Furthermore, the detection unit can improve the accuracy of detection by referring to related literature. As a result, the accuracy of detection is improved by referring to related literature. A part or all of the above-mentioned processing in the detection unit may be performed, for example, using AI or may be performed without using AI. For example, the detection unit can input related literature data to the generation AI and cause the generation AI to perform detection based on the literature.

[0113] The determination unit can estimate the user's emotion and adjust the importance determination criteria based on the estimated user's emotion. For example, when the user is stressed, the determination unit relaxes the importance determination criteria and determines only important discrepancies. Also, when the user is relaxed, the determination unit can tighten the importance determination criteria and determine detailed discrepancies. Furthermore, when the user is in a hurry, the determination unit can adjust the importance determination criteria and quickly determine discrepancies. This reduces the burden on the user by adjusting the importance determination criteria according to the user's emotion. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the importance determination criteria based on the emotion.

[0114] The determination unit can improve the accuracy of the determination by considering the interrelationships between news articles at the time of determination. For example, the determination unit analyzes the interrelationships between news articles and determines the importance between highly related articles. The determination unit can also determine the importance of contradictions by considering the interrelationships between news articles. Furthermore, the determination unit can improve the accuracy of the determination based on the interrelationships between news articles. As a result, the accuracy of the determination is improved by considering the interrelationships between news articles. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or may be performed without using AI. For example, the determination unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute an improvement in the accuracy of the determination based on the interrelationships.

[0115] The determination unit can make a determination by taking into consideration attribute information of the submitter of the news article at the time of the determination. For example, the determination unit makes a determination by taking into consideration the reliability of the submitter of the news article. The determination unit can also make a determination based on the past history of the submitter of the news article. Furthermore, the determination unit can improve the accuracy of the determination based on the attribute information of the submitter of the news article. As a result, the accuracy of the determination is improved by taking into consideration the attribute information of the submitter of the news article. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or may be performed without using AI. For example, the determination unit can input attribute information of the submitter of the news article to the generation AI and cause the generation AI to perform a determination based on the attribute information.

[0116] The determination unit can estimate the user's emotion and adjust the display method of the determination result based on the estimated user's emotion. For example, when the user is feeling stressed, the determination unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the determination unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the determination unit can also provide a display method that focuses on the main points. This reduces the burden on the user by adjusting the display method of the determination result according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the determination unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the determination unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the determination result based on the emotion.

[0117] The determination unit can make a determination taking into consideration the geographic distribution of news articles when making a determination. For example, the determination unit analyzes the geographic distribution of news articles and determines the importance between highly related regions. The determination unit can also determine the importance of a contradiction by taking into consideration the geographic distribution of news articles. Furthermore, the determination unit can improve the accuracy of the determination based on the geographic distribution of news articles. As a result, the accuracy of the determination is improved by taking into consideration the geographic distribution of news articles. A part or all of the above-mentioned processing in the determination unit may be performed, for example, using AI or may be performed without using AI. For example, the determination unit can input geographic distribution data of news articles to the generation AI and cause the generation AI to perform a determination based on the geographic distribution.

[0118] The judgment unit can improve the accuracy of the judgment by referring to the related literature at the time of judgment. For example, the judgment unit can evaluate the reliability of the news article by referring to the related literature. The judgment unit can also judge the importance of the contradictions in the news article based on the related literature. Furthermore, the judgment unit can improve the accuracy of the judgment by referring to the related literature. As a result, the accuracy of the judgment is improved by referring to the related literature. A part or all of the above-mentioned processing in the judgment unit may be performed using, for example, AI, or may be performed without using AI. For example, the judgment unit can input related literature data to the generation AI and cause the generation AI to execute a judgment based on the literature.

[0119] The reception unit can estimate the user's emotion and adjust the reception method based on the estimated user's emotion. For example, when the user is stressed, the reception unit provides a simple interface and minimizes input procedures. Also, when the user is relaxed, the reception unit can provide detailed input options and suggest a customizable input method. Furthermore, when the user is in a hurry, the reception unit can prioritize voice input and enable the user to input information quickly. This reduces the burden on the user by adjusting the reception method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the reception method based on the emotion.

[0120] The reception unit can select the optimal reception method by referring to the user's past selection history at the time of reception. For example, the reception unit preferentially displays information sources that the user has frequently selected in the past. The reception unit can also preferentially suggest input methods (such as voice and text) that the user has used in the past. Furthermore, the reception unit can predict and suggest information sources to be used in a specific time period from the user's past selection history. This allows efficient reception by referring to the user's past selection history. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI or may be performed without using AI. For example, the reception unit can input the user's past selection history data to the generation AI and cause the generation AI to select the optimal reception method based on the past selection history.

[0121] The reception unit can estimate the user's emotion and determine the priority of reception based on the estimated user's emotion. For example, when the user is feeling stressed, the reception unit preferentially receives important information sources. Also, when the user is relaxed, the reception unit can also receive a wide range of information sources. Furthermore, when the user is in a hurry, the reception unit can preferentially receive information sources that can be quickly confirmed. In this way, by determining the priority of reception according to the user's emotion, it is possible to preferentially receive important information sources. The estimation of emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input the user's emotion data to the generation AI and cause the generation AI to execute the determination of the priority of reception based on the emotion.

[0122] The reception unit can select the optimal reception method in consideration of the device information of the user at the time of reception. For example, when the user is using a smartphone, the reception unit provides a reception method that matches the screen size. In addition, when the user is using a tablet, the reception unit can also provide a reception method that is optimized for a large screen. Furthermore, when the user is using a smartwatch, the reception unit can also provide a simple and highly visible reception method. This enables efficient reception by considering the device information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input the device information of the user to the generation AI and cause the generation AI to select the optimal reception method based on the device information.

[0123] The evaluation unit can estimate the user's emotion and adjust the reliability evaluation criteria based on the estimated user's emotion. For example, when the user is stressed, the evaluation unit relaxes the reliability evaluation criteria and evaluates only important information sources. Also, when the user is relaxed, the evaluation unit can tighten the reliability evaluation criteria and evaluate detailed information sources. Furthermore, when the user is in a hurry, the evaluation unit can adjust the reliability evaluation criteria and quickly evaluate information sources. This reduces the burden on the user by adjusting the reliability evaluation criteria according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the reliability evaluation criteria based on the emotion.

[0124] The evaluation unit can improve the accuracy of the evaluation by considering the interrelationships between news articles during the evaluation. For example, the evaluation unit analyzes the interrelationships between news articles and evaluates the reliability between highly related articles. The evaluation unit can also evaluate the reliability by considering the interrelationships between news articles. Furthermore, the evaluation unit can improve the accuracy of the evaluation based on the interrelationships between news articles. As a result, the accuracy of the evaluation is improved by considering the interrelationships between news articles. Some or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input interrelationship data between news articles to the generation AI and cause the generation AI to execute the improvement of the accuracy of the evaluation based on the interrelationships.

[0125] The evaluation unit can estimate the user's emotion and adjust the display method of the evaluation result based on the estimated user's emotion. For example, when the user is stressed, the evaluation unit provides a simple and highly visible display method. Furthermore, when the user is relaxed, the evaluation unit can also provide a display method including detailed information. Furthermore, when the user is in a hurry, the evaluation unit can also provide a display method that focuses on the main points. This reduces the burden on the user by adjusting the display method of the evaluation result according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the evaluation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the evaluation unit can input the user's emotion data to the generation AI and cause the generation AI to adjust the display method of the evaluation result based on the emotion.

[0126] The evaluation unit can perform the evaluation while taking into account the geographic distribution of the news articles. For example, the evaluation unit analyzes the geographic distribution of the news articles and evaluates the reliability between highly related regions. The evaluation unit can also evaluate the reliability while taking into account the geographic distribution of the news articles. Furthermore, the evaluation unit can improve the accuracy of the evaluation based on the geographic distribution of the news articles. As a result, the accuracy of the evaluation is improved by taking into account the geographic distribution of the news articles. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI or may be performed without using AI. For example, the evaluation unit can input geographic distribution data of the news articles to the generation AI and cause the generation AI to perform an evaluation based on the geographic distribution.

[0127] The evaluation unit can improve the accuracy of the evaluation by referring to related literature during the evaluation. For example, the evaluation unit can evaluate the reliability of a news article by referring to related literature. The evaluation unit can also evaluate the reliability of a news article based on the related literature. Furthermore, the evaluation unit can improve the accuracy of the evaluation by referring to related literature. As a result, the accuracy of the evaluation is improved by referring to the related literature. A part or all of the above-mentioned processing in the evaluation unit may be performed, for example, using AI, or may be performed without using AI. For example, the evaluation unit can input related literature data to the generation AI and cause the generation AI to perform an evaluation based on the literature.

[0128] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0129] When collecting news articles, the collection unit can preferentially collect highly relevant articles by taking into account the user's past browsing history. For example, the collection unit preferentially collects news articles related to topics that the user has frequently browsed in the past. The collection unit can also collect articles related to news articles that the user has given high ratings in the past. Furthermore, the collection unit can adjust the type of news to be collected in a specific time period based on the user's past browsing history. This allows highly relevant news articles to be efficiently collected by taking into account the user's past browsing history.

[0130] The cross-check unit can generate a reliability score for evaluating the reliability of a news article when cross-checking the news article. For example, the cross-check unit generates a reliability score based on the reliability of the information source of the news article. The cross-check unit can also generate a reliability score based on the degree of agreement of the contents of the news articles. Furthermore, the cross-check unit can also generate a reliability score based on the past performance of the news article. In this way, by generating a reliability score for evaluating the reliability of a news article, a highly reliable news article can be identified.

[0131] When issuing an alert, the alert unit can adjust the content of the alert based on the result of sentiment analysis of the news article. For example, if the news article has positive content, the alert unit issues an alert using positive language. Also, if the news article has negative content, the alert unit can also issue an alert using language that calls attention. Furthermore, if the news article has neutral content, the alert unit can also issue an alert using objective language. In this way, by adjusting the content of the alert based on the result of sentiment analysis of the news article, appropriate information can be provided.

[0132] When cross-checking a news article, the cross-check unit can apply different cross-check algorithms depending on the category of the news article. For example, the cross-check unit applies a specific cross-check algorithm to political news. The cross-check unit can also apply a different cross-check algorithm to economic news. Furthermore, the cross-check unit can also apply a dedicated cross-check algorithm to sports news. This allows for highly accurate cross-checking by applying a cross-check algorithm depending on the category of the news article.

[0133] The determination unit can take into account the social media response of the news article when determining the importance of the news article. For example, if the news article has received many shares and comments on social media, the determination unit determines the importance of the news article to be high. Also, if the news article has received little response on social media, the determination unit can determine the importance of the news article to be low. Furthermore, the determination unit can score the response of the news article on social media and determine the importance based on the score. In this way, by taking into account the response of the news article on social media, it is possible to determine the importance of the news article more accurately.

[0134] The collection unit can estimate the user's emotions when collecting news articles, and adjust the categories of news articles to be collected based on the estimated user's emotions. For example, when the user is feeling stressed, the collection unit preferentially collects positive news articles. In addition, when the user is relaxed, the collection unit can also collect news articles of a wide range of categories. Furthermore, when the user is in a hurry, the collection unit can also preferentially collect important news articles. In this way, by adjusting the categories of news articles according to the user's emotions, it is possible to provide appropriate news articles for the user.

[0135] The cross-check unit can generate a reliability score for evaluating the reliability of a news article when cross-checking the news article. For example, the cross-check unit generates a reliability score based on the reliability of the information source of the news article. The cross-check unit can also generate a reliability score based on the degree of agreement of the contents of the news articles. Furthermore, the cross-check unit can also generate a reliability score based on the past performance of the news article. In this way, by generating a reliability score for evaluating the reliability of a news article, a highly reliable news article can be identified.

[0136] When issuing an alert, the alert unit can adjust the content of the alert based on the result of sentiment analysis of the news article. For example, if the news article has positive content, the alert unit issues an alert using positive language. Also, if the news article has negative content, the alert unit can also issue an alert using language that calls attention. Furthermore, if the news article has neutral content, the alert unit can also issue an alert using objective language. In this way, by adjusting the content of the alert based on the result of sentiment analysis of the news article, appropriate information can be provided.

[0137] When cross-checking a news article, the cross-check unit can apply different cross-check algorithms depending on the category of the news article. For example, the cross-check unit applies a specific cross-check algorithm to political news. The cross-check unit can also apply a different cross-check algorithm to economic news. Furthermore, the cross-check unit can also apply a dedicated cross-check algorithm to sports news. This allows for highly accurate cross-checking by applying a cross-check algorithm depending on the category of the news article.

[0138] The determination unit can take into account the social media response of the news article when determining the importance of the news article. For example, if the news article has received many shares and comments on social media, the determination unit determines the importance of the news article to be high. Also, if the news article has received little response on social media, the determination unit can determine the importance of the news article to be low. Furthermore, the determination unit can score the response of the news article on social media and determine the importance based on the score. In this way, by taking into account the response of the news article on social media, it is possible to determine the importance of the news article more accurately.

[0139] The process flow of the second embodiment will be briefly described below.

[0140] Step 1: The collection unit collects news articles about the same subject from each of a plurality of information sources. The collection unit can collect news articles from information sources such as newspapers, online news sites, blogs, etc. The collection unit can collect news articles using an API or scraping technology. Step 2: The cross-checking unit cross-checks the news articles collected by the collecting unit across multiple sources. The cross-checking unit compares the contents of the news articles using, for example, text matching techniques to detect inconsistencies and contradictions. The cross-checking unit can also verify the contents of the news articles using database matching techniques. Step 3: The alert unit issues an alert to the journalist based on the result of the crosscheck by the crosscheck unit. The alert unit can issue an alert to the journalist using, for example, an email notification or a pop-up notification. The alert unit can also issue an alert to the journalist using a real-time notification or a periodic notification.

[0141] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0142] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0143] Furthermore, the above-described processing by the data processing system 10 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0144] For example, the collection unit is realized by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart device 14, and collects news articles from information sources such as newspapers, online news sites, and blogs. The cross-check unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and cross-checks the collected news articles to detect inconsistencies and contradictions. The alert unit is realized by, for example, the control unit 46A of the smart device 14, and issues an alert to a journalist based on the result of the cross-check. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0145] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0146] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0147] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0148] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0149] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0150] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0151] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0152] Fig. 4 shows an example of main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0153] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0154] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0155] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0156] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0157] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0158] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0159] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0160] For example, the collection unit is realized by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the smart glasses 214, and collects news articles from information sources such as newspapers, online news sites, and blogs. The cross-check unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and cross-checks the collected news articles to detect inconsistencies and contradictions. The alert unit is realized by, for example, the control unit 46A of the smart glasses 214, and issues an alert to a journalist based on the result of the cross-check. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0161] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0162] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0163] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0164] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0165] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0166] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0167] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0168] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0169] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0170] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0171] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0172] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0173] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0174] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0175] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0176] For example, the collection unit is realized by at least one of the headset type terminal 314 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the headset type terminal 314, and collects news articles from information sources such as newspapers, online news sites, and blogs. The cross-check unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and cross-checks the collected news articles to detect inconsistencies and contradictions. The alert unit is realized by, for example, the control unit 46A of the headset type terminal 314, and issues an alert to the journalist based on the result of the cross-check. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0177] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0178] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0179] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0180] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0181] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs the voice according to instructions from the processor 46.

[0182] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0183] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0184] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0185] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0186] The processor 28 reads the specific processing program 56 from the storage 32, and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0187] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0188] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0189] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0190] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires a voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0191] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0192] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0193] For example, the collection unit is realized by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by the control unit 46A of the robot 414, and collects news articles from information sources such as newspapers, online news sites, and blogs. The cross-check unit is realized by, for example, the specific processing unit 290 of the data processing device 12, and cross-checks the collected news articles to detect inconsistencies and contradictions. The alert unit is realized by, for example, the control unit 46A of the robot 414, and issues an alert to the journalist based on the result of the cross-check. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0194] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0195] FIG. 9 is a diagram showing an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0196] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0197] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0198] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0199] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0200] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in Fig. 10. Fig. 10 shows an example in which multiple emotions, "relief," "calm," and "encouraging," have similar emotion values.

[0201] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers, including computer 22.

[0202] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable computer-readable non-transitory storage medium such as a Universal Serial Bus (USB) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0203] In addition, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 upon request from the data processing device 12.

[0204] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0205] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0206] The hardware resource that executes the specific process may be one of these various processors, or may be a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0207] As an example of a configuration using one processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a configuration using a processor that realizes the functions of the entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0208] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0209] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0210] The above description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure, and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, function, action, and effect is an example of the configuration, function, action, and effect of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0211] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0212] (Appendix 1) a collection unit that collects news articles on the same subject from each of a plurality of information sources; a cross-check unit that cross-checks the news articles collected by the collection unit among a plurality of information sources; and an alert unit that issues an alert to a journalist based on a result of the crosscheck by the crosscheck unit. A system characterized by: (Appendix 2) The cross check unit includes: A section for detecting inconsistencies or contradictions between multiple sources of news articles is provided. 2. The system of claim 1, (Appendix 3) The alert unit is Alerts journalists to information containing discrepancies or inconsistencies detected by the detector 3. The system of claim 2, (Appendix 4) The cross check unit includes: Equipped with a section for determining the importance of each element of a news article 2. The system of claim 1, (Appendix 5) The determination unit is Alerts journalists with information including the results of judgments on discrepancies or inconsistencies detected by the detection unit 5. The system of claim 4. (Appendix 6) Each element of the news article is: It is an element of time, place, person, number, quotation, or statement. 2. The system of claim 1, (Appendix 7) A reception unit is provided for receiving selections of news articles from specific sources from journalists. 2. The system of claim 1, (Appendix 8) The collecting unit includes: Collecting news articles relating to the same subject, including the news article selected by the reception unit, from each of the plurality of information sources. 8. The system of claim 7, (Appendix 9) The cross check unit includes: Equipped with an evaluation section that evaluates the reliability of each information source based on the cross-check results 2. The system of claim 1, (Appendix 10) The collecting unit includes: Estimate user emotions and adjust the timing of news article collection based on the estimated user emotions 2. The system of claim 1, (Appendix 11) The collecting unit includes: Analyze past collection history and select the optimal collection method 2. The system of claim 1, (Appendix 12) The collecting unit includes: When collecting news articles, filter them based on specific topics or keywords 2. The system of claim 1, (Appendix 13) The collecting unit includes: Estimate user sentiment and prioritize news articles based on the estimated user sentiment 2. The system of claim 1, (Appendix 14) The collecting unit includes: When collecting news articles, geographic location information is taken into consideration to prioritize the collection of articles with high relevance. 2. The system of claim 1, (Appendix 15) The collecting unit includes: When collecting news articles, analyze social media activity and collect related articles 2. The system of claim 1, (Appendix 16) The cross check unit includes: To estimate a user's emotion and adjust a cross-check criterion based on the estimated user's emotion. 2. The system of claim 1, (Appendix 17) The cross check unit includes: When cross-checking, take into account the correlation between news articles to improve the accuracy of the cross-check. 2. The system of claim 1, (Appendix 18) The cross check unit includes: When cross-checking, the attribute information of the news article submitter is taken into consideration. 2. The system of claim 1, (Appendix 19) The cross check unit includes: Infer user sentiment and adjust the order in which cross-check results are displayed based on the estimated user sentiment. 2. The system of claim 1, (Appendix 20) The cross check unit includes: When cross-checking, the geographical distribution of news articles is taken into account. 2. The system of claim 1, (Appendix 21) The cross check unit includes: When cross-checking, refer to related literature to improve the accuracy of the cross-check. 2. The system of claim 1, (Appendix 22) The alert unit is Infer user emotions and adjust alert wording based on the inferred user emotions 2. The system of claim 1, (Appendix 23) The alert unit is At the time of alerting, adjust the granularity of the alert based on the importance of the news article 2. The system of claim 1, (Appendix 24) The alert unit is When sending an alert, different alert algorithms are applied depending on the news article category. 2. The system of claim 1, (Appendix 25) The alert unit is Infer user emotion and adjust the length of the alert based on the estimated user emotion 2. The system of claim 1, (Appendix 26) The alert unit is When an alert is sent, it prioritizes the alert based on when the news article was submitted 2. The system of claim 1, (Appendix 27) The alert unit is At the time of alerting, adjust the order of alerts based on the relevance of the news article 2. The system of claim 1, (Appendix 28) The detection unit is Estimating a user's emotions and adjusting criteria for detecting discrepancies and inconsistencies based on the estimated user's emotions 3. The system of claim 2, (Appendix 29) The detection unit is During detection, the correlation between news articles is taken into account to improve detection accuracy. 3. The system of claim 2, (Appendix 30) The detection unit is When detecting, the attribute information of the news article submitter is taken into account. 3. The system of claim 2, (Appendix 31) The detection unit is Infer user emotions and adjust the way detection results are displayed based on the estimated user emotions 3. The system of claim 2, (Appendix 32) The detection unit is During detection, the geographic distribution of news articles is taken into account 3. The system of claim 2, (Appendix 33) The detection unit is During detection, refer to related literature to improve detection accuracy 3. The system of claim 2, (Appendix 34) The determination unit is To estimate a user's emotion and adjust a criterion for determining importance based on the estimated user's emotion. 5. The system of claim 4. (Appendix 35) The determination unit is When making judgments, the accuracy of judgments is improved by taking into account the correlation between news articles. 5. The system of claim 4. (Appendix 36) The determination unit is When making a judgment, the attribute information of the news article submitter is taken into consideration. 5. The system of claim 4. (Appendix 37) The determination unit is To estimate a user's emotion and adjust a method of displaying a judgment result based on the estimated user's emotion. 5. The system of claim 4. (Appendix 38) The determination unit is When making a decision, the geographic distribution of news articles is taken into account. 5. The system of claim 4. (Appendix 39) The determination unit is When making a judgment, refer to related literature to improve the accuracy of the judgment. 5. The system of claim 4. (Appendix 40) The reception unit is Estimate the user's emotions and adjust the reception method based on the estimated user's emotions 8. The system of claim 7, (Appendix 41) The reception unit is At the time of reception, the optimal reception method is selected by referring to the user's past selection history. 8. The system of claim 7, (Appendix 42) The reception unit is Estimate the user's emotions and determine the reception priority based on the estimated user's emotions 8. The system of claim 7, (Appendix 43) The reception unit is At the time of reception, the optimal reception method is selected taking into consideration the user's device information. 8. The system of claim 7, (Appendix 44) The evaluation unit is Inferring a user's emotions and adjusting a reliability evaluation criterion based on the estimated user's emotions 10. The system of claim 9, (Appendix 45) The evaluation unit is When evaluating news articles, the accuracy of the evaluation is improved by taking into account their correlation with each other. 10. The system of claim 9, (Appendix 46) The evaluation unit is Inferring user emotion and adjusting the way rating results are displayed based on the estimated user emotion 10. The system of claim 9, (Appendix 47) The evaluation unit is The geographical distribution of news articles is taken into account during the evaluation. 10. The system of claim 9, (Appendix 48) The evaluation unit is During evaluation, refer to related literature to improve the accuracy of the evaluation. 10. The system of claim 9, [Explanation of symbols]

[0213] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects news articles on the same subject from each of a plurality of information sources; a cross-check unit that cross-checks the news articles collected by the collection unit among the plurality of information sources; and an alert unit that issues an alert to a journalist based on a result of the crosscheck by the crosscheck unit. A system characterized by:

2. The cross check unit includes: a detector for detecting inconsistencies or contradictions between the plurality of sources of news articles; 2. The system of claim 1 .

3. The alert unit is An alert is sent to inform the journalist of information including the inconsistencies or contradictions detected by the detection unit.

3. The system of claim 2.

4. The cross check unit includes: A determination unit is provided for determining the importance of each element of the news article.

2. The system of claim 1 .

5. Each element of the news article is: It is an element of time, place, person, number, quotation, or statement.

2. The system of claim 1 .

6. A reception unit is provided for receiving selections of news articles from specific sources from journalists.

2. The system of claim 1 .

7. The collecting unit includes: Collecting news articles relating to the same subject, including the news article selected by the reception unit, from each of the plurality of information sources.

8. The system of claim 7.

Images