system

Abstract

The system according to this embodiment aims to automatically evaluate the reliability of information within a document, enabling users to easily determine its credibility. [Solution] The system according to the embodiment comprises a collection unit, a verification unit, an evaluation unit, a linking unit, and a report generation unit. The collection unit analyzes the document and identifies the portion containing factual information. The verification unit verifies the factual information identified by the collection unit by cross-referencing it with public databases and reliable information sources. The evaluation unit evaluates the reliability of the information verified by the verification unit in percentage terms and highlights questionable portions within the document. The linking unit provides links to data sources that can be referenced for the information evaluated by the evaluation unit. The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and less reliable information visually understandable.

Description

Technical Field

[0006] , , ,

[0005] , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003] <000001`7>

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is time-consuming and costly to manually fact-check the reliability of information on the Internet, and there is a problem that it is difficult for ordinary users to determine the credibility of information. ]

[0005] The system according to the embodiment aims to automatically evaluate the reliability of information in a document so that the user can easily determine the credibility.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a verification unit, an evaluation unit, a linking unit, and a report generation unit. The collection unit analyzes the document and identifies the portion containing factual information. The verification unit verifies the factual information identified by the collection unit by cross-referencing it with public databases and reliable information sources. The evaluation unit evaluates the reliability of the information verified by the verification unit in percentage terms and highlights questionable portions within the document. The linking unit provides links to data sources that can be referenced for the information evaluated by the evaluation unit. The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making the highly reliable and less reliable information visually understandable. [Effects of the Invention]

[0007] The system according to this embodiment can automatically evaluate the reliability of information within a document, allowing users to easily determine its credibility. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8]This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

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

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0014] In the following embodiments, the tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards 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". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the 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. Also, the database 24 and the communication I / F 26 are 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. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. 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, a specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. 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 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

[0027] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The fact-checking AI agent according to an embodiment of the present invention is a system that evaluates the reliability of information on the internet and performs fact-checking quickly and efficiently. This fact-checking AI agent analyzes a document and identifies the portion containing factual information. Next, it cross-references with public databases and reliable information sources to verify the facts. In this process, it uses a knowledge graph to understand the context of the information. Furthermore, it evaluates the reliability of each piece of information in a percentage and highlights questionable portions within the document. Links to the relevant data sources are provided for the relevant information. Finally, it generates a report summarizing the verification results, making highly reliable and less reliable information visually understandable. For example, the fact-checking AI agent analyzes documents such as news articles and blog posts and extracts portions containing factual information. In this process, the generating AI analyzes the content of the document and identifies the facts. Next, the fact-checking AI agent cross-references with public databases and reliable information sources to verify the facts. For example, it checks the accuracy of the information in the document by comparing it with official government databases and reliable news sources. In this process, the generating AI uses a knowledge graph to understand the context of the information and verify the facts. Furthermore, the fact-checking AI agent evaluates the reliability of each piece of information as a percentage and highlights questionable parts of the document. For example, low-reliability information is highlighted in red, and high-reliability information is highlighted in green. Links to the relevant data sources are also provided. In this process, the generating AI evaluates reliability and performs the highlighting and linking. Finally, the fact-checking AI agent generates a report summarizing the verification results, making reliable and unreliable information visually understandable. For example, reliable information is displayed in blue, and unreliable information is displayed in red. In this process, the generating AI generates the report in a visually easy-to-understand format. This mechanism helps prevent the spread of misinformation and promotes the sharing of reliable information. In addition, quantifying the accuracy of information makes it easier for users to judge. Furthermore, by providing references, users can verify the credibility themselves.For example, journalists, content creators, and media companies can use this system to provide accurate and reliable information. This allows the fact-checking AI agent to quickly and efficiently evaluate the reliability of information on the internet and provide users with reliable information.

[0029] The fact-checking AI agent according to this embodiment comprises a collection unit, a verification unit, an evaluation unit, a linking unit, and a report generation unit. The collection unit analyzes a document and identifies the portion containing factual information. The collection unit analyzes a document such as a news article or blog post and extracts the portion containing factual information. The collection unit analyzes the content of the document using a generation AI and identifies factual information. For example, the collection unit can have the generation AI analyze the content of the document and identify factual information based on specific keywords or phrases. The collection unit can also have the generation AI analyze the content of the document and identify the portion containing factual information. The collection unit can also have the generation AI analyze the content of the document and apply an algorithm to identify factual information. The verification unit verifies the factual information identified by the collection unit by cross-referencing it with public databases and reliable information sources. The verification unit verifies the accuracy of the information in the document by comparing it with, for example, official government databases and reliable news sources. The verification unit uses a knowledge graph with the generation AI to understand the context of the information and verify the factual information. For example, the verification unit allows the generating AI to understand the context of the information using a knowledge graph and verify the facts. The verification unit can also apply algorithms to enable the generating AI to understand the context of the information using a knowledge graph and verify the facts. The evaluation unit evaluates the reliability of the information verified by the verification unit in percentages and highlights questionable parts of the document. For example, the evaluation unit highlights information with low reliability in red and information with high reliability in green. The evaluation unit uses the generating AI to evaluate reliability and perform highlighting. For example, the evaluation unit allows the generating AI to evaluate reliability and highlight information with low reliability in red and information with high reliability in green. The evaluation unit can also apply algorithms to enable the generating AI to evaluate reliability and perform highlighting. The linking unit adds links to data sources that can be referenced for the information evaluated by the evaluation unit. For example, the linking unit adds links to data sources that can be referenced for the relevant information. The linking unit uses the generating AI to add links.For example, the linking unit can add links to data sources that the generating AI can reference for the relevant information. The linking unit can also apply algorithms for the generating AI to add links. The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and less reliable information visually understandable. For example, the report generation unit displays highly reliable information in blue and less reliable information in red. The report generation unit generates the report using the generating AI and makes it easy to understand visually. For example, the report generation unit can generate a report in which the generating AI displays highly reliable information in blue and less reliable information in red. The report generation unit can also apply algorithms for the generating AI to generate the report and make it easy to understand visually. As a result, the fact-checking AI agent according to the embodiment can efficiently perform document analysis, verification, evaluation, linking, and report generation, and provide highly reliable information.

[0030] The data collection unit analyzes documents and identifies sections containing factual information. For example, it analyzes documents such as news articles and blog posts and extracts sections containing factual information. The data collection unit uses generative AI to analyze document content and identify factual information. Specifically, the generative AI utilizes natural language processing techniques to understand document content and extracts factual information based on specific keywords and phrases. For example, the generative AI detects keywords such as "published," "confirmed," and "reported" within a document and identifies factual information by analyzing the related context. Furthermore, the generative AI can apply algorithms to more accurately identify sections containing factual information, taking into account the document's structure and context. The data collection unit can also rely on the generative AI to analyze document content and identify sections containing factual information. For example, the generative AI analyzes specific paragraphs or sentences within a document and determines whether they contain factual information. The generative AI can also understand the overall topic and theme of the document and apply algorithms to identify factual information based on that. This allows the data collection unit to efficiently identify factual information within documents and provide a foundation for proceeding to the next verification process.

[0031] The verification department verifies the facts identified by the collection department by cross-referencing them with public databases and reliable information sources. Specifically, the verification department checks the accuracy of the information in the document by comparing it with official government databases and reliable news sources. For example, it refers to government statistical databases, official announcements, and archives of reliable news organizations to confirm whether the collected facts are accurate. The verification department uses generative AI and a knowledge graph to understand the context of the information and verify the facts. The generative AI utilizes the knowledge graph to understand the relationships and background of the information and evaluate the accuracy of the facts. For example, the generative AI uses the knowledge graph to associate information about specific people or events and check whether the information in the document matches existing knowledge. The generative AI can also use the knowledge graph to understand the context of the information and apply algorithms to verify the facts. This allows the verification department to accurately and efficiently verify the collected facts and provide reliable information.

[0032] The evaluation unit assesses the reliability of the information verified by the verification unit as a percentage and highlights questionable parts of the document. Specifically, the evaluation unit highlights information with low reliability in red and information with high reliability in green. The evaluation unit uses generative AI to evaluate reliability and perform highlighting. To evaluate the reliability of verified information, the generative AI refers to past data and statistical information and evaluates the accuracy and reliability of the information as a percentage. For example, the generative AI evaluates the reliability of specific information based on past verification results and reliable information sources and reflects the results in the document. The generative AI can also apply algorithms to evaluate reliability and perform highlighting. This makes it easier for the evaluation unit to visually grasp the reliability of information in the document and enables users to quickly identify questionable information. Furthermore, the evaluation unit can calculate a reliability score for the entire document based on the reliability evaluation results and provide it to the user. This allows the evaluation unit to comprehensively evaluate the reliability of the document and provide information that can serve as a reference for users to judge the accuracy of the information.

[0033] The linking unit adds links to data sources that can be referenced for the information evaluated by the evaluation unit. Specifically, the linking unit adds links to data sources that can be referenced for the relevant information. The linking unit uses a generative AI to add links. The generative AI identifies reliable data sources related to the evaluated information and adds those links to the document. For example, the generative AI searches official databases and reliable news sources related to specific facts and adds those links to the relevant parts of the document. The generative AI can also apply algorithms for adding links and select the most suitable links considering the relevance and reliability of the information. This allows the linking unit to make it easy for users to verify the source of the information and enhance the reliability of the information. Furthermore, the linking unit can update and manage links to always provide the latest information. For example, if the information at the linked destination is updated, the linking unit automatically updates the link to provide the user with the latest information. The linking unit can also periodically evaluate the reliability of links and remove unreliable links. This allows the linking unit to provide users with reliable information and maintain the accuracy of the information.

[0034] The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and unreliable information visually understandable. Specifically, the report generation unit displays highly reliable information in blue and unreliable information in red. The report generation unit uses a generation AI to generate reports in a visually easy-to-understand format. The generation AI generates a report that visually represents the reliability of the information based on the reliability score evaluated by the evaluation unit and the links provided by the linking unit. For example, by displaying highly reliable information in blue and unreliable information in red, the generation AI allows users to grasp the reliability of the information at a glance. The generation AI can also optimize the layout and design of the report and apply algorithms to make the information easy for users to understand. As a result, the report generation unit provides users with verification results in a visually easy-to-understand format, enabling them to quickly judge the reliability of the information. Furthermore, the report generation unit can periodically update the content of the report to reflect the latest verification results. For example, if new information is collected or existing information is updated, the report generation unit automatically updates the report to provide users with the latest information. Furthermore, the report generation unit can improve the content and display method of reports based on user feedback, providing more user-friendly reports. This allows the report generation unit to provide users with reliable information and maintain its accuracy.

[0035] The data collection unit can analyze documents such as news articles and blog posts and identify portions containing factual information. For example, the data collection unit can analyze documents such as news articles and blog posts and extract portions containing factual information. The data collection unit uses generative AI to analyze the content of documents and identify factual information. For example, the data collection unit can use generative AI to analyze documents such as news articles and blog posts and identify factual information based on specific keywords or phrases. The data collection unit can also use generative AI to analyze documents such as news articles and blog posts and identify portions containing factual information. The data collection unit can also apply algorithms to enable generative AI to analyze documents such as news articles and blog posts and identify factual information. This allows for the provision of highly reliable information by identifying factual information from documents such as news articles and blog posts. News articles and blog posts include, but are not limited to, articles from online news sites and personal blogs. Some or all of the processing described above in the data collection unit may be performed using generative AI or without generative AI. For example, the data collection unit can input documents such as news articles and blog posts into a generation AI, which can then perform the task of identifying the facts.

[0036] The verification unit can verify the accuracy of information in a document by comparing it with official government databases and reliable news sources. For example, the verification unit can verify the accuracy of information in a document by comparing it with official government databases and reliable news sources. The verification unit uses generative AI and a knowledge graph to understand the context of the information and verify the facts. For example, the verification unit can use generative AI to verify the accuracy of information in a document by comparing it with official government databases and reliable news sources. The verification unit can also use generative AI to understand the context of the information and verify the facts using a knowledge graph. The verification unit can also apply algorithms to ensure that generative AI verifies the accuracy of information in a document by comparing it with official government databases and reliable news sources. This allows for verification of the accuracy of information in a document by comparing it with official government databases and reliable news sources. Official government databases include, but are not limited to, census databases and legal databases. Reliable news sources include, but are not limited to, major news media and official announcements. Some or all of the above-described processes in the verification unit may be performed using a generative AI, or they may not be performed using a generative AI. For example, the verification unit can input data from official government databases or reliable news sources into a generative AI and have the generative AI perform the verification of the accuracy of the information.

[0037] The evaluation unit can highlight unreliable information in red and highly reliable information in green. For example, the evaluation unit can highlight unreliable information in red and highly reliable information in green. The evaluation unit uses a generative AI to evaluate reliability and perform highlighting. For example, the evaluation unit can have a generative AI evaluate reliability and highlight unreliable information in red and highly reliable information in green. The evaluation unit can also apply an algorithm for the generative AI to evaluate reliability and perform highlighting. This allows users to visually grasp the reliability of information by highlighting it according to its reliability. Unreliable information includes, but is not limited to, information with unclear sources or unverified information. Highly reliable information includes, but is not limited to, official announcements or information from reliable sources. Some or all of the above processing in the evaluation unit may be performed using a generative AI or not. For example, the evaluation unit can input information from a document into a generative AI and have the generative AI perform reliability evaluation and highlighting.

[0038] The linking unit can add links to data sources that can be referenced for the relevant information. For example, the linking unit adds links to data sources that can be referenced for the relevant information. The linking unit uses a generation AI to add links. For example, the linking unit can have a generation AI add links to data sources that can be referenced for the relevant information. The linking unit can also apply an algorithm for the generation AI to add links. This allows users to verify the credibility of the information by adding links to data sources that can be referenced for the relevant information. Reference data sources include, but are not limited to, reliability criteria for linked sites. Some or all of the above processing in the linking unit may be performed using a generation AI or not. For example, the linking unit can input information from a document into a generation AI and have the generation AI perform the task of adding links to data sources that can be referenced.

[0039] The report generation unit can display highly reliable information in blue and less reliable information in red. For example, the report generation unit can display highly reliable information in blue and less reliable information in red. The report generation unit uses a generation AI to generate reports in a visually easy-to-understand format. For example, the report generation unit can generate a report in which the generation AI displays highly reliable information in blue and less reliable information in red. The report generation unit can also apply an algorithm to the generation AI to generate reports and make them visually easy to understand. This allows users to visually grasp the reliability of information by color-coding it according to its reliability. Highly reliable information includes, but is not limited to, official announcements and information from reliable sources. Less reliable information includes, but is not limited to, information with unclear sources and unverified information. Some or all of the above processing in the report generation unit may be performed using the generation AI or not. For example, the report generation unit can input information from a document into the generation AI and have the generation AI perform report generation and color-coding.

[0040] The data collection unit can prioritize identifying factual information based on specific keywords or phrases when analyzing documents. For example, the data collection unit's generating AI can prioritize the analysis of keywords such as "official announcement" or "evidence" to identify reliable information. The data collection unit can also have the generating AI analyze phrases such as "eyewitness accounts" or "reports" to quickly extract factual information. The data collection unit can also have the generating AI analyze keywords such as "investigation results" or "statistical data" to identify reliable information. This allows for the rapid extraction of reliable information by prioritizing the identification of factual information based on specific keywords or phrases. Specific keywords and phrases include, but are not limited to, frequently occurring words and important phrases. Some or all of the above-described processes in the data collection unit may be performed using the generating AI or not. For example, the data collection unit can input specific keywords or phrases from a document into the generating AI and have the generating AI perform the identification of factual information.

[0041] The data collection unit can apply different analysis algorithms depending on the type of document during document analysis. For example, the data collection unit can use a generating AI to apply an analysis algorithm that prioritizes timeliness to news articles. The data collection unit can also use a generating AI to apply an analysis algorithm that considers personal opinions and impressions to blog posts. The data collection unit can also use a generating AI to apply an analysis algorithm that prioritizes specialized terminology and citations to academic papers. By applying different analysis algorithms depending on the type of document, the data collection unit can provide analysis results that are tailored to the characteristics of each document. Document types include, but are not limited to, news articles, academic papers, and blog posts. Some or all of the above-described processes in the data collection unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the data collection unit can input the document type into the generating AI and have the generating AI execute the application of the analysis algorithm.

[0042] The data collection unit can prioritize the analysis of the latest information by considering the document's publication date and time during document analysis. For example, the data collection unit can use a generating AI to prioritize the analysis of the latest news articles and identify the most recent facts. The data collection unit can also use a generating AI to prioritize the analysis of recently updated blog posts and extract the latest opinions and impressions. The data collection unit can also use a generating AI to prioritize the analysis of the latest academic papers and identify the latest research findings. This allows for the rapid identification of the latest facts by prioritizing the analysis of the latest information by considering the document's publication date and time. The document's publication date and time may include, but are not limited to, criteria for prioritizing the latest information. Some or all of the above processing in the data collection unit may be performed using a generating AI or not. For example, the data collection unit can input the document's publication date and time into the generating AI and have the generating AI perform the identification of the latest information.

[0043] The data collection unit can prioritize the analysis of highly reliable documents by considering the author information of the documents during document analysis. For example, the data collection unit can use a generating AI to prioritize the analysis of news articles by prominent journalists. The data collection unit can also use a generating AI to prioritize the analysis of blog posts by experts. The data collection unit can also use a generating AI to prioritize the analysis of academic papers by authoritative researchers. By prioritizing the analysis of highly reliable documents by considering the author information of the documents, the data collection unit can provide highly reliable information. The author information of the documents includes, but is not limited to, author reliability evaluation criteria. Some or all of the above processing in the data collection unit may be performed using a generating AI or not. For example, the data collection unit can input the author information of the documents into a generating AI and have the generating AI identify highly reliable documents.

[0044] The verification unit can improve the accuracy of verification by cross-referencing multiple public databases and information sources during the verification process. For example, the verification unit can use a generating AI to verify information by cross-referencing official government databases with reliable news sources. The verification unit can also use a generating AI to verify information by cross-referencing academic paper databases with expert blogs. The verification unit can also use a generating AI to verify information by cross-referencing official company announcements with third-party reports. This improves the accuracy of verification by cross-referencing multiple public databases and information sources. Examples of multiple public databases and information sources include, but are not limited to, official government databases and reliable news sites. Some or all of the above-described processes in the verification unit may be performed using a generating AI or not. For example, the verification unit can input data from multiple public databases and information sources into a generating AI and have the generating AI perform the cross-referencing.

[0045] The verification unit can apply different verification methods depending on the category of information during verification. For example, the verification unit can use a generating AI to verify political information based on official government announcements and reliable news sources. The verification unit can also use a generating AI to verify economic information based on economic indicators and official company announcements. The verification unit can also use a generating AI to verify scientific information based on academic papers and expert opinions. By applying different verification methods depending on the category of information, the verification unit can provide verification results that are appropriate to the characteristics of the information. Categories of information include, but are not limited to, news, academic papers, and blog posts. Some or all of the above-described processes in the verification unit may be performed using a generating AI or not. For example, the verification unit can input the category of information into the generating AI and have the generating AI perform the application of verification methods.

[0046] The verification unit can determine the priority of verification during the verification process by considering the reliability of the information source. For example, the verification unit may use a generating AI to prioritize the verification of official government announcements and provide reliable information. The verification unit may also use a generating AI to prioritize the verification of well-known news sources and provide reliable information. The verification unit may also use a generating AI to prioritize the verification of expert opinions and provide reliable information. In this way, by determining the priority of verification by considering the reliability of the information source, reliable information can be provided preferentially. The reliability of the information source includes, but is not limited to, past reliability assessments of the source and official announcements. Some or all of the above processing in the verification unit may be performed using a generating AI or not. For example, the verification unit may input reliability data of the information source into a generating AI and have the generating AI perform the determination of verification priorities.

[0047] The verification unit can improve the accuracy of its verification by referring to relevant literature during the verification process. For example, the verification unit can use a generating AI to refer to relevant academic papers and confirm the accuracy of the information. The verification unit can also use a generating AI to refer to relevant reports and confirm the accuracy of the information. The verification unit can also use a generating AI to refer to relevant news articles and confirm the accuracy of the information. In this way, the accuracy of the verification can be improved by referring to relevant literature. Relevant literature includes, but is not limited to, citations and relevant research papers. Some or all of the above processing in the verification unit may be performed using a generating AI or not. For example, the verification unit can input relevant literature data into a generating AI and have the generating AI perform the verification accuracy improvement.

[0048] The evaluation unit can adjust the level of detail in its reliability assessment based on the source and citation count of the information. For example, the evaluation unit will perform a detailed evaluation if the generating AI identifies the source as official. The evaluation unit may also perform a detailed evaluation if the generating AI identifies the source as frequently cited. The evaluation unit may also perform a simplified evaluation if the generating AI identifies the source as unclear. By adjusting the level of detail in the evaluation based on the source and citation count of the information, the evaluation unit can provide highly reliable information. The source and citation count of the information include, but are not limited to, frequently cited literature and highly reliable sources. Some or all of the above processing in the evaluation unit may be performed using the generating AI or not. For example, the evaluation unit can input data on the source and citation count of the information into the generating AI and have the generating AI perform the adjustment of the level of detail in the evaluation.

[0049] The evaluation unit can apply different evaluation algorithms depending on the category of information when evaluating reliability. For example, the evaluation unit can use a generating AI to evaluate political information based on official government announcements and reliable news sources. The evaluation unit can also use a generating AI to evaluate economic information based on economic indicators and official company announcements. The evaluation unit can also use a generating AI to evaluate scientific information based on academic papers and expert opinions. By applying different evaluation algorithms depending on the category of information, the evaluation unit can provide evaluation results that are appropriate to the characteristics of the information. Categories of information include, but are not limited to, news, academic papers, and blog posts. Some or all of the above processing in the evaluation unit may be performed using a generating AI or not. For example, the evaluation unit can input the category of information into the generating AI and have the generating AI perform the application of the evaluation algorithm.

[0050] The evaluation unit can determine the evaluation priority based on the information's release date and time when evaluating reliability. For example, the evaluation unit may have the generating AI prioritize the evaluation of the latest information to provide highly reliable information. The evaluation unit may also have the generating AI prioritize the evaluation of the latest information, delaying the evaluation of older information. The evaluation unit may also adjust the evaluation priority based on the information's release date and time. This allows the evaluation unit to prioritize the provision of the latest information by determining the evaluation priority based on the information's release date and time. The information's release date and time may include, but are not limited to, criteria for prioritizing the latest information. Some or all of the above processing in the evaluation unit may be performed using the generating AI or not. For example, the evaluation unit may input the information's release date and time to the generating AI and have the generating AI determine the evaluation priority.

[0051] The evaluation unit can adjust the order of evaluation based on the relevance of the information when evaluating reliability. For example, the evaluation unit can have the generating AI prioritize the evaluation of highly relevant information to provide reliable information. The evaluation unit can also have the generating AI postpone the evaluation of less relevant information and prioritize important information. The evaluation unit can also have the generating AI adjust the order of evaluation based on the relevance of the information. This allows for the priority provision of important information by adjusting the order of evaluation based on the relevance of the information. The relevance of the information includes, but is not limited to, related topics and common themes. Some or all of the above processing in the evaluation unit may be performed using the generating AI or not. For example, the evaluation unit can input information relevance data into the generating AI and have the generating AI perform the adjustment of the evaluation order.

[0052] The link assignment unit can adjust how links are displayed based on the reliability of the information when assigning links. For example, the link assignment unit can make links to reliable sources more prominent using the generating AI. The link assignment unit can also make links to less reliable sources less prominent using the generating AI. The link assignment unit can also adjust how links are displayed based on the reliability of the information using the generating AI. This allows users to easily identify reliable information by adjusting how links are displayed based on the reliability of the information. Reliability of information includes, but is not limited to, reliable sources and official announcements. Some or all of the above processing in the link assignment unit may be performed using the generating AI or not. For example, the link assignment unit can input information reliability data into the generating AI and have the generating AI perform the adjustment of how links are displayed.

[0053] The link assignment unit can apply different link assignment algorithms depending on the information category when assigning links. For example, the link assignment unit can have the generating AI prioritize linking to official government announcements for political information. The link assignment unit can also have the generating AI prioritize linking to official company announcements for economic information. The link assignment unit can also have the generating AI prioritize linking to academic papers for scientific information. By applying different link assignment algorithms depending on the information category, it is possible to provide links that are appropriate to the characteristics of the information. Information categories include, but are not limited to, news, academic papers, and blog posts. Some or all of the above processing in the link assignment unit may be performed using the generating AI or not. For example, the link assignment unit can input the information category into the generating AI and have the generating AI execute the application of the link assignment algorithm.

[0054] The link assignment unit can determine the priority of links by considering the reliability of the information source when assigning links. For example, the link assignment unit may have a generating AI prioritize links to official government announcements. The link assignment unit may also have a generating AI prioritize links to well-known news sources. The link assignment unit may also have a generating AI prioritize links to expert opinions. By determining the priority of links by considering the reliability of the information source, the system can prioritize the provision of reliable information. The reliability of the information source includes, but is not limited to, past reliability assessments of the source and official announcements. Some or all of the above processing in the link assignment unit may be performed using a generating AI or not. For example, the link assignment unit can input reliability data of the information source into a generating AI and have the generating AI perform the determination of link priority.

[0055] The linking unit can improve the accuracy of links by referring to related literature when assigning links. For example, the linking unit can have the generating AI assign links to relevant academic papers and verify the accuracy of the information. The linking unit can also have the generating AI assign links to relevant reports and verify the accuracy of the information. The linking unit can also have the generating AI assign links to relevant news articles and verify the accuracy of the information. In this way, the accuracy of links can be improved by referring to related literature. Related literature includes, but is not limited to, citations and related research papers. Some or all of the above processing in the linking unit may be performed using the generating AI or not. For example, the linking unit can input related literature data into the generating AI and have the generating AI perform the linking accuracy improvement.

[0056] The report generation unit can adjust the level of detail in a report based on the reliability of the information during report generation. For example, the report generation unit can generate a detailed report for information that the generating AI finds reliable. The report generation unit can also generate a concise report for information that the generating AI finds unreliable. The report generation unit can also adjust the level of detail in a report based on the reliability of the information. This allows users to easily verify reliable information by adjusting the level of detail in the report based on the reliability of the information. Information reliability includes, but is not limited to, reliable sources and official announcements. Some or all of the above processing in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input information reliability data into the generating AI and have the generating AI perform the adjustment of the level of detail in the report.

[0057] The report generation unit can apply different report generation algorithms depending on the category of information when generating a report. For example, the generating AI can generate a report based on official government announcements for political information. The generating AI can also generate a report based on economic indicators and official company announcements for economic information. The generating AI can also generate a report based on academic papers and expert opinions for scientific information. By applying different report generation algorithms depending on the category of information, it is possible to provide reports that are appropriate to the characteristics of the information. Categories of information include, but are not limited to, news, academic papers, and blog posts. Some or all of the above processing in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input the category of information into the generating AI and have the generating AI execute the application of the report generation algorithm.

[0058] The report generation unit can determine the priority of reports based on the information's origin date and time when generating reports. For example, the generating AI can prioritize including the latest information in the report. The report generation unit can also have the generating AI postpone the inclusion of older information in the report. The report generation unit can also have the generating AI adjust the report priority based on the information's origin date and time. This allows for the prioritization of the latest information by determining the report priority based on the information's origin date and time. The information's origin date and time may include, but are not limited to, criteria for prioritizing the latest information. Some or all of the above-described processes in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input the information's origin date and time to the generating AI and have the generating AI determine the report priority.

[0059] The report generation unit can adjust the order of reports based on the relevance of the information during report generation. For example, the report generation unit can prioritize including highly relevant information in the report based on the generation AI. The report generation unit can also postpone including less relevant information in the report based on the generation AI. The report generation unit can also adjust the order of reports based on the relevance of the information based on the generation AI. This allows important information to be provided preferentially by adjusting the order of reports based on the relevance of the information. Relevance of information includes, but is not limited to, related topics and common themes. Some or all of the above processing in the report generation unit may be performed using the generation AI or not. For example, the report generation unit can input information relevance data into the generation AI and have the generation AI perform the adjustment of the report order.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] The data collection unit can prioritize identifying factual information based on specific keywords and phrases during document analysis. For example, the generating AI can prioritize analyzing keywords such as "official announcement" and "evidence" to identify highly reliable information. The generating AI can also analyze phrases such as "eyewitness accounts" and "reports" to quickly extract factual information. The generating AI can also analyze keywords such as "investigation results" and "statistical data" to identify highly reliable information. In this way, highly reliable information can be quickly extracted by prioritizing the identification of factual information based on specific keywords and phrases.

[0062] The data collection unit can apply different analysis algorithms depending on the type of document during analysis. For example, the generating AI can apply an analysis algorithm that prioritizes speed to news articles. It can also apply an analysis algorithm that considers personal opinions and impressions to blog posts. Furthermore, it can apply an analysis algorithm that prioritizes specialized terminology and citations to academic papers. By applying different analysis algorithms depending on the document type, the system can provide analysis results tailored to the characteristics of each document.

[0063] The verification unit can improve the accuracy of verification by cross-referencing multiple public databases and information sources during the verification process. For example, the generating AI can verify information by cross-referencing official government databases with reliable news sources. The generating AI can also verify information by cross-referencing academic paper databases with expert blogs. The generating AI can also verify information by cross-referencing official company announcements with third-party reports. In this way, the accuracy of verification can be improved by cross-referencing multiple public databases and information sources.

[0064] The evaluation unit can adjust the level of detail in its reliability assessment based on the source and citation count of the information. For example, if the generating AI's source is official, it will perform a detailed evaluation. If the generating AI's source is frequently cited, it can also perform a detailed evaluation. If the generating AI's source is unclear, it can perform a simplified evaluation. By adjusting the level of detail in the evaluation based on the source and citation count of the information, it is possible to provide highly reliable information.

[0065] The link assignment unit can adjust how links are displayed based on the reliability of the information when assigning links. For example, the generating AI can make links to reliable sources more prominent. The generating AI can also make links to less reliable sources less prominent. The generating AI can adjust how links are displayed based on the reliability of the information. This allows users to easily identify reliable information by adjusting how links are displayed based on the reliability of the information.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The collection unit analyzes the document and identifies the parts containing factual information. The collection unit analyzes documents such as news articles and blog posts and extracts the parts containing factual information. The collection unit can use generative AI to analyze the content of the document and identify factual information based on specific keywords and phrases. Step 2: The Verification Department verifies the facts identified by the Collection Department by cross-referencing them with public databases and reliable information sources. For example, the Verification Department checks the accuracy of the information in the document by comparing it with official government databases and reliable news sources. The Verification Department uses a knowledge graph with generative AI to understand the context of the information and verify the facts. Step 3: The evaluation unit assesses the reliability of the information verified by the verification unit in percentage terms and highlights questionable parts of the document. For example, the evaluation unit highlights information with low reliability in red and information with high reliability in green. Step 4: The linking unit provides links to data sources that can be referenced for the information evaluated by the evaluation unit. For example, the linking unit provides links to data sources that can be referenced for the relevant information. Step 5: The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and less reliable information visually understandable. For example, the report generation unit displays highly reliable information in blue and less reliable information in red.

[0068] (Example of form 2) The fact-checking AI agent according to an embodiment of the present invention is a system that evaluates the reliability of information on the internet and performs fact-checking quickly and efficiently. This fact-checking AI agent analyzes a document and identifies the portion containing factual information. Next, it cross-references with public databases and reliable information sources to verify the facts. In this process, it uses a knowledge graph to understand the context of the information. Furthermore, it evaluates the reliability of each piece of information in a percentage and highlights questionable portions within the document. Links to the relevant data sources are provided for the relevant information. Finally, it generates a report summarizing the verification results, making highly reliable and less reliable information visually understandable. For example, the fact-checking AI agent analyzes documents such as news articles and blog posts and extracts portions containing factual information. In this process, the generating AI analyzes the content of the document and identifies the facts. Next, the fact-checking AI agent cross-references with public databases and reliable information sources to verify the facts. For example, it checks the accuracy of the information in the document by comparing it with official government databases and reliable news sources. In this process, the generating AI uses a knowledge graph to understand the context of the information and verify the facts. Furthermore, the fact-checking AI agent evaluates the reliability of each piece of information as a percentage and highlights questionable parts of the document. For example, low-reliability information is highlighted in red, and high-reliability information is highlighted in green. Links to the relevant data sources are also provided. In this process, the generating AI evaluates reliability and performs the highlighting and linking. Finally, the fact-checking AI agent generates a report summarizing the verification results, making reliable and unreliable information visually understandable. For example, reliable information is displayed in blue, and unreliable information is displayed in red. In this process, the generating AI generates the report in a visually easy-to-understand format. This mechanism helps prevent the spread of misinformation and promotes the sharing of reliable information. In addition, quantifying the accuracy of information makes it easier for users to judge. Furthermore, by providing references, users can verify the credibility themselves.For example, journalists, content creators, and media companies can use this system to provide accurate and reliable information. This allows the fact-checking AI agent to quickly and efficiently evaluate the reliability of information on the internet and provide users with reliable information.

[0069] The fact-checking AI agent according to this embodiment comprises a collection unit, a verification unit, an evaluation unit, a linking unit, and a report generation unit. The collection unit analyzes a document and identifies the portion containing factual information. The collection unit analyzes a document such as a news article or blog post and extracts the portion containing factual information. The collection unit analyzes the content of the document using a generation AI and identifies factual information. For example, the collection unit can have the generation AI analyze the content of the document and identify factual information based on specific keywords or phrases. The collection unit can also have the generation AI analyze the content of the document and identify the portion containing factual information. The collection unit can also have the generation AI analyze the content of the document and apply an algorithm to identify factual information. The verification unit verifies the factual information identified by the collection unit by cross-referencing it with public databases and reliable information sources. The verification unit verifies the accuracy of the information in the document by comparing it with, for example, official government databases and reliable news sources. The verification unit uses a knowledge graph with the generation AI to understand the context of the information and verify the factual information. For example, the verification unit allows the generating AI to understand the context of the information using a knowledge graph and verify the facts. The verification unit can also apply algorithms to enable the generating AI to understand the context of the information using a knowledge graph and verify the facts. The evaluation unit evaluates the reliability of the information verified by the verification unit in percentages and highlights questionable parts of the document. For example, the evaluation unit highlights information with low reliability in red and information with high reliability in green. The evaluation unit uses the generating AI to evaluate reliability and perform highlighting. For example, the evaluation unit allows the generating AI to evaluate reliability and highlight information with low reliability in red and information with high reliability in green. The evaluation unit can also apply algorithms to enable the generating AI to evaluate reliability and perform highlighting. The linking unit adds links to data sources that can be referenced for the information evaluated by the evaluation unit. For example, the linking unit adds links to data sources that can be referenced for the relevant information. The linking unit uses the generating AI to add links.For example, the linking unit can add links to data sources that the generating AI can reference for the relevant information. The linking unit can also apply algorithms for the generating AI to add links. The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and less reliable information visually understandable. For example, the report generation unit displays highly reliable information in blue and less reliable information in red. The report generation unit generates the report using the generating AI and makes it easy to understand visually. For example, the report generation unit can generate a report in which the generating AI displays highly reliable information in blue and less reliable information in red. The report generation unit can also apply algorithms for the generating AI to generate the report and make it easy to understand visually. As a result, the fact-checking AI agent according to the embodiment can efficiently perform document analysis, verification, evaluation, linking, and report generation, and provide highly reliable information.

[0070] The data collection unit analyzes documents and identifies sections containing factual information. For example, it analyzes documents such as news articles and blog posts and extracts sections containing factual information. The data collection unit uses generative AI to analyze document content and identify factual information. Specifically, the generative AI utilizes natural language processing techniques to understand document content and extracts factual information based on specific keywords and phrases. For example, the generative AI detects keywords such as "published," "confirmed," and "reported" within a document and identifies factual information by analyzing the related context. Furthermore, the generative AI can apply algorithms to more accurately identify sections containing factual information, taking into account the document's structure and context. The data collection unit can also rely on the generative AI to analyze document content and identify sections containing factual information. For example, the generative AI analyzes specific paragraphs or sentences within a document and determines whether they contain factual information. The generative AI can also understand the overall topic and theme of the document and apply algorithms to identify factual information based on that. This allows the data collection unit to efficiently identify factual information within documents and provide a foundation for proceeding to the next verification process.

[0071] The verification department verifies the facts identified by the collection department by cross-referencing them with public databases and reliable information sources. Specifically, the verification department checks the accuracy of the information in the document by comparing it with official government databases and reliable news sources. For example, it refers to government statistical databases, official announcements, and archives of reliable news organizations to confirm whether the collected facts are accurate. The verification department uses generative AI and a knowledge graph to understand the context of the information and verify the facts. The generative AI utilizes the knowledge graph to understand the relationships and background of the information and evaluate the accuracy of the facts. For example, the generative AI uses the knowledge graph to associate information about specific people or events and check whether the information in the document matches existing knowledge. The generative AI can also use the knowledge graph to understand the context of the information and apply algorithms to verify the facts. This allows the verification department to accurately and efficiently verify the collected facts and provide reliable information.

[0072] The evaluation unit assesses the reliability of the information verified by the verification unit as a percentage and highlights questionable parts of the document. Specifically, the evaluation unit highlights information with low reliability in red and information with high reliability in green. The evaluation unit uses generative AI to evaluate reliability and perform highlighting. To evaluate the reliability of verified information, the generative AI refers to past data and statistical information and evaluates the accuracy and reliability of the information as a percentage. For example, the generative AI evaluates the reliability of specific information based on past verification results and reliable information sources and reflects the results in the document. The generative AI can also apply algorithms to evaluate reliability and perform highlighting. This makes it easier for the evaluation unit to visually grasp the reliability of information in the document and enables users to quickly identify questionable information. Furthermore, the evaluation unit can calculate a reliability score for the entire document based on the reliability evaluation results and provide it to the user. This allows the evaluation unit to comprehensively evaluate the reliability of the document and provide information that can serve as a reference for users to judge the accuracy of the information.

[0073] The linking unit adds links to data sources that can be referenced for the information evaluated by the evaluation unit. Specifically, the linking unit adds links to data sources that can be referenced for the relevant information. The linking unit uses a generative AI to add links. The generative AI identifies reliable data sources related to the evaluated information and adds those links to the document. For example, the generative AI searches official databases and reliable news sources related to specific facts and adds those links to the relevant parts of the document. The generative AI can also apply algorithms for adding links and select the most suitable links considering the relevance and reliability of the information. This allows the linking unit to make it easy for users to verify the source of the information and enhance the reliability of the information. Furthermore, the linking unit can update and manage links to always provide the latest information. For example, if the information at the linked destination is updated, the linking unit automatically updates the link to provide the user with the latest information. The linking unit can also periodically evaluate the reliability of links and remove unreliable links. This allows the linking unit to provide users with reliable information and maintain the accuracy of the information.

[0074] The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and unreliable information visually understandable. Specifically, the report generation unit displays highly reliable information in blue and unreliable information in red. The report generation unit uses a generation AI to generate reports in a visually easy-to-understand format. The generation AI generates a report that visually represents the reliability of the information based on the reliability score evaluated by the evaluation unit and the links provided by the linking unit. For example, by displaying highly reliable information in blue and unreliable information in red, the generation AI allows users to grasp the reliability of the information at a glance. The generation AI can also optimize the layout and design of the report and apply algorithms to make the information easy for users to understand. As a result, the report generation unit provides users with verification results in a visually easy-to-understand format, enabling them to quickly judge the reliability of the information. Furthermore, the report generation unit can periodically update the content of the report to reflect the latest verification results. For example, if new information is collected or existing information is updated, the report generation unit automatically updates the report to provide users with the latest information. Furthermore, the report generation unit can improve the content and display method of reports based on user feedback, providing more user-friendly reports. This allows the report generation unit to provide users with reliable information and maintain its accuracy.

[0075] The data collection unit can analyze documents such as news articles and blog posts and identify portions containing factual information. For example, the data collection unit can analyze documents such as news articles and blog posts and extract portions containing factual information. The data collection unit uses generative AI to analyze the content of documents and identify factual information. For example, the data collection unit can use generative AI to analyze documents such as news articles and blog posts and identify factual information based on specific keywords or phrases. The data collection unit can also use generative AI to analyze documents such as news articles and blog posts and identify portions containing factual information. The data collection unit can also apply algorithms to enable generative AI to analyze documents such as news articles and blog posts and identify factual information. This allows for the provision of highly reliable information by identifying factual information from documents such as news articles and blog posts. News articles and blog posts include, but are not limited to, articles from online news sites and personal blogs. Some or all of the processing described above in the data collection unit may be performed using generative AI or without generative AI. For example, the data collection unit can input documents such as news articles and blog posts into a generation AI, which can then perform the task of identifying the facts.

[0076] The verification unit can verify the accuracy of information in a document by comparing it with official government databases and reliable news sources. For example, the verification unit can verify the accuracy of information in a document by comparing it with official government databases and reliable news sources. The verification unit uses generative AI and a knowledge graph to understand the context of the information and verify the facts. For example, the verification unit can use generative AI to verify the accuracy of information in a document by comparing it with official government databases and reliable news sources. The verification unit can also use generative AI to understand the context of the information and verify the facts using a knowledge graph. The verification unit can also apply algorithms to ensure that generative AI verifies the accuracy of information in a document by comparing it with official government databases and reliable news sources. This allows for verification of the accuracy of information in a document by comparing it with official government databases and reliable news sources. Official government databases include, but are not limited to, census databases and legal databases. Reliable news sources include, but are not limited to, major news media and official announcements. Some or all of the above-described processes in the verification unit may be performed using a generative AI, or they may not be performed using a generative AI. For example, the verification unit can input data from official government databases or reliable news sources into a generative AI and have the generative AI perform the verification of the accuracy of the information.

[0077] The evaluation unit can highlight unreliable information in red and highly reliable information in green. For example, the evaluation unit can highlight unreliable information in red and highly reliable information in green. The evaluation unit uses a generative AI to evaluate reliability and perform highlighting. For example, the evaluation unit can have a generative AI evaluate reliability and highlight unreliable information in red and highly reliable information in green. The evaluation unit can also apply an algorithm for the generative AI to evaluate reliability and perform highlighting. This allows users to visually grasp the reliability of information by highlighting it according to its reliability. Unreliable information includes, but is not limited to, information with unclear sources or unverified information. Highly reliable information includes, but is not limited to, official announcements or information from reliable sources. Some or all of the above processing in the evaluation unit may be performed using a generative AI or not. For example, the evaluation unit can input information from a document into a generative AI and have the generative AI perform reliability evaluation and highlighting.

[0078] The linking unit can add links to data sources that can be referenced for the relevant information. For example, the linking unit adds links to data sources that can be referenced for the relevant information. The linking unit uses a generation AI to add links. For example, the linking unit can have a generation AI add links to data sources that can be referenced for the relevant information. The linking unit can also apply an algorithm for the generation AI to add links. This allows users to verify the credibility of the information by adding links to data sources that can be referenced for the relevant information. Reference data sources include, but are not limited to, reliability criteria for linked sites. Some or all of the above processing in the linking unit may be performed using a generation AI or not. For example, the linking unit can input information from a document into a generation AI and have the generation AI perform the task of adding links to data sources that can be referenced.

[0079] The report generation unit can display highly reliable information in blue and less reliable information in red. For example, the report generation unit can display highly reliable information in blue and less reliable information in red. The report generation unit uses a generation AI to generate reports in a visually easy-to-understand format. For example, the report generation unit can generate a report in which the generation AI displays highly reliable information in blue and less reliable information in red. The report generation unit can also apply an algorithm to the generation AI to generate reports and make them visually easy to understand. This allows users to visually grasp the reliability of information by color-coding it according to its reliability. Highly reliable information includes, but is not limited to, official announcements and information from reliable sources. Less reliable information includes, but is not limited to, information with unclear sources and unverified information. Some or all of the above processing in the report generation unit may be performed using the generation AI or not. For example, the report generation unit can input information from a document into the generation AI and have the generation AI perform report generation and color-coding.

[0080] The data collection unit can estimate the user's emotions and adjust the document analysis method based on the estimated emotions. For example, if the user is stressed, the data collection unit can use a generative AI to apply a concise analysis method and extract only the important facts. If the user is relaxed, the data collection unit can use a generative AI to apply a detailed analysis method and gain a deeper understanding of the overall context of the document. If the user is in a hurry, the data collection unit can use a generative AI to perform a rapid analysis and prioritize the identification of key facts. This allows for the provision of analysis results tailored to the user by adjusting the document analysis method according to the user's emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using or without the generative AI. For example, the data collection unit can input user emotion data into the generative AI and have the generative AI adjust the document analysis method.

[0081] The data collection unit can prioritize identifying factual information based on specific keywords or phrases when analyzing documents. For example, the data collection unit's generating AI can prioritize the analysis of keywords such as "official announcement" or "evidence" to identify reliable information. The data collection unit can also have the generating AI analyze phrases such as "eyewitness accounts" or "reports" to quickly extract factual information. The data collection unit can also have the generating AI analyze keywords such as "investigation results" or "statistical data" to identify reliable information. This allows for the rapid extraction of reliable information by prioritizing the identification of factual information based on specific keywords or phrases. Specific keywords and phrases include, but are not limited to, frequently occurring words and important phrases. Some or all of the above-described processes in the data collection unit may be performed using the generating AI or not. For example, the data collection unit can input specific keywords or phrases from a document into the generating AI and have the generating AI perform the identification of factual information.

[0082] The data collection unit can apply different analysis algorithms depending on the type of document during document analysis. For example, the data collection unit can use a generating AI to apply an analysis algorithm that prioritizes timeliness to news articles. The data collection unit can also use a generating AI to apply an analysis algorithm that considers personal opinions and impressions to blog posts. The data collection unit can also use a generating AI to apply an analysis algorithm that prioritizes specialized terminology and citations to academic papers. By applying different analysis algorithms depending on the type of document, the data collection unit can provide analysis results that are tailored to the characteristics of each document. Document types include, but are not limited to, news articles, academic papers, and blog posts. Some or all of the above-described processes in the data collection unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the data collection unit can input the document type into the generating AI and have the generating AI execute the application of the analysis algorithm.

[0083] The data collection unit can estimate the user's emotions and determine the priority of documents to analyze based on the estimated emotions. For example, if the user is feeling anxious, the data collection unit can have the generative AI prioritize the analysis of highly reliable documents. If the user is excited, the data collection unit can also have the generative AI prioritize the analysis of documents containing the latest information. If the user is relaxed, the data collection unit can also have the generative AI prioritize the analysis of documents containing detailed information. This allows for the priority of providing the user with information relevant to their emotions by determining the priority of documents to analyze according to their emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using the generative AI or not. For example, the data collection unit can input user emotion data into the generative AI and have the generative AI determine the priority of documents.

[0084] The data collection unit can prioritize the analysis of the latest information by considering the document's publication date and time during document analysis. For example, the data collection unit can use a generating AI to prioritize the analysis of the latest news articles and identify the most recent facts. The data collection unit can also use a generating AI to prioritize the analysis of recently updated blog posts and extract the latest opinions and impressions. The data collection unit can also use a generating AI to prioritize the analysis of the latest academic papers and identify the latest research findings. This allows for the rapid identification of the latest facts by prioritizing the analysis of the latest information by considering the document's publication date and time. The document's publication date and time may include, but are not limited to, criteria for prioritizing the latest information. Some or all of the above processing in the data collection unit may be performed using a generating AI or not. For example, the data collection unit can input the document's publication date and time into the generating AI and have the generating AI perform the identification of the latest information.

[0085] The data collection unit can prioritize the analysis of highly reliable documents by considering the author information of the documents during document analysis. For example, the data collection unit can use a generating AI to prioritize the analysis of news articles by prominent journalists. The data collection unit can also use a generating AI to prioritize the analysis of blog posts by experts. The data collection unit can also use a generating AI to prioritize the analysis of academic papers by authoritative researchers. By prioritizing the analysis of highly reliable documents by considering the author information of the documents, the data collection unit can provide highly reliable information. The author information of the documents includes, but is not limited to, author reliability evaluation criteria. Some or all of the above processing in the data collection unit may be performed using a generating AI or not. For example, the data collection unit can input the author information of the documents into a generating AI and have the generating AI identify highly reliable documents.

[0086] The verification unit can estimate the user's emotions and adjust the verification criteria based on the estimated emotions. For example, if the user is feeling anxious, the verification unit can use a generative AI to apply strict verification criteria and provide reliable information. If the user is relaxed, the verification unit can use a generative AI to apply flexible verification criteria and provide a wide range of information. If the user is in a hurry, the verification unit can use a generative AI to apply rapid verification criteria and prioritize verifying key facts. This allows the verification unit to provide verification results that are appropriate for the user by adjusting the verification criteria according to the user's emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the verification unit may be performed using or without the generative AI. For example, the verification unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the verification criteria.

[0087] The verification unit can improve the accuracy of verification by cross-referencing multiple public databases and information sources during the verification process. For example, the verification unit can use a generating AI to verify information by cross-referencing official government databases with reliable news sources. The verification unit can also use a generating AI to verify information by cross-referencing academic paper databases with expert blogs. The verification unit can also use a generating AI to verify information by cross-referencing official company announcements with third-party reports. This improves the accuracy of verification by cross-referencing multiple public databases and information sources. Examples of multiple public databases and information sources include, but are not limited to, official government databases and reliable news sites. Some or all of the above-described processes in the verification unit may be performed using a generating AI or not. For example, the verification unit can input data from multiple public databases and information sources into a generating AI and have the generating AI perform the cross-referencing.

[0088] The verification unit can apply different verification methods depending on the category of information during verification. For example, the verification unit can use a generating AI to verify political information based on official government announcements and reliable news sources. The verification unit can also use a generating AI to verify economic information based on economic indicators and official company announcements. The verification unit can also use a generating AI to verify scientific information based on academic papers and expert opinions. By applying different verification methods depending on the category of information, the verification unit can provide verification results that are appropriate to the characteristics of the information. Categories of information include, but are not limited to, news, academic papers, and blog posts. Some or all of the above-described processes in the verification unit may be performed using a generating AI or not. For example, the verification unit can input the category of information into the generating AI and have the generating AI perform the application of verification methods.

[0089] The verification unit can estimate the user's emotions and adjust how the verification results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the verification unit can use a generative AI to provide detailed verification results and highlight reliable information. If the user is relaxed, the verification unit can also use a generative AI to provide concise verification results and display a wide range of information. If the user is in a hurry, the verification unit can use a generative AI to quickly display key verification results and highlight important information. This allows the system to provide verification results that are appropriate for the user by adjusting how the results are displayed according to their emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the verification unit may be performed using or without a generative AI. For example, the verification unit can input user emotion data into a generative AI and have the generative AI adjust how the verification results are displayed.

[0090] The verification unit can determine the priority of verification during the verification process by considering the reliability of the information source. For example, the verification unit may use a generating AI to prioritize the verification of official government announcements and provide reliable information. The verification unit may also use a generating AI to prioritize the verification of well-known news sources and provide reliable information. The verification unit may also use a generating AI to prioritize the verification of expert opinions and provide reliable information. In this way, by determining the priority of verification by considering the reliability of the information source, reliable information can be provided preferentially. The reliability of the information source includes, but is not limited to, past reliability assessments of the source and official announcements. Some or all of the above processing in the verification unit may be performed using a generating AI or not. For example, the verification unit may input reliability data of the information source into a generating AI and have the generating AI perform the determination of verification priorities.

[0091] The verification unit can improve the accuracy of its verification by referring to relevant literature during the verification process. For example, the verification unit can use a generating AI to refer to relevant academic papers and confirm the accuracy of the information. The verification unit can also use a generating AI to refer to relevant reports and confirm the accuracy of the information. The verification unit can also use a generating AI to refer to relevant news articles and confirm the accuracy of the information. In this way, the accuracy of the verification can be improved by referring to relevant literature. Relevant literature includes, but is not limited to, citations and relevant research papers. Some or all of the above processing in the verification unit may be performed using a generating AI or not. For example, the verification unit can input relevant literature data into a generating AI and have the generating AI perform the verification accuracy improvement.

[0092] The evaluation unit can estimate the user's emotions and adjust the reliability evaluation method based on the estimated user emotions. For example, if the user is feeling anxious, the evaluation unit can use a generative AI to apply strict evaluation criteria and provide reliable information. If the user is relaxed, the evaluation unit can also use a generative AI to apply flexible evaluation criteria and provide a wide range of information. If the user is in a hurry, the evaluation unit can use a generative AI to apply rapid evaluation criteria and prioritize the evaluation of key facts. This allows the evaluation unit to provide evaluation results that are appropriate for the user by adjusting the reliability evaluation method according to the user's emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using or without the generative AI. For example, the evaluation unit can input user emotion data into the generative AI and have the generative AI perform the adjustment of the reliability evaluation method.

[0093] The evaluation unit can adjust the level of detail in its reliability assessment based on the source and citation count of the information. For example, the evaluation unit will perform a detailed evaluation if the generating AI identifies the source as official. The evaluation unit may also perform a detailed evaluation if the generating AI identifies the source as frequently cited. The evaluation unit may also perform a simplified evaluation if the generating AI identifies the source as unclear. By adjusting the level of detail in the evaluation based on the source and citation count of the information, the evaluation unit can provide highly reliable information. The source and citation count of the information include, but are not limited to, frequently cited literature and highly reliable sources. Some or all of the above processing in the evaluation unit may be performed using the generating AI or not. For example, the evaluation unit can input data on the source and citation count of the information into the generating AI and have the generating AI perform the adjustment of the level of detail in the evaluation.

[0094] The evaluation unit can apply different evaluation algorithms depending on the category of information when evaluating reliability. For example, the evaluation unit can use a generating AI to evaluate political information based on official government announcements and reliable news sources. The evaluation unit can also use a generating AI to evaluate economic information based on economic indicators and official company announcements. The evaluation unit can also use a generating AI to evaluate scientific information based on academic papers and expert opinions. By applying different evaluation algorithms depending on the category of information, the evaluation unit can provide evaluation results that are appropriate to the characteristics of the information. Categories of information include, but are not limited to, news, academic papers, and blog posts. Some or all of the above processing in the evaluation unit may be performed using a generating AI or not. For example, the evaluation unit can input the category of information into the generating AI and have the generating AI perform the application of the evaluation algorithm.

[0095] The evaluation unit can estimate the user's emotions and adjust how the reliability evaluation results are displayed based on the estimated user emotions. For example, if the user is feeling anxious, the evaluation unit can use a generative AI to provide detailed evaluation results and highlight reliable information. If the user is relaxed, the evaluation unit can also use a generative AI to provide concise evaluation results and display a wide range of information. If the user is in a hurry, the evaluation unit can use a generative AI to quickly display key evaluation results and highlight important information. This allows the evaluation unit to provide evaluation results that are appropriate for the user by adjusting how the reliability evaluation results are displayed according to the user's emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the evaluation unit may be performed using or without a generative AI. For example, the evaluation unit can input user emotion data into a generative AI and have the generative AI adjust how the evaluation results are displayed.

[0096] The evaluation unit can determine the evaluation priority based on the information's release date and time when evaluating reliability. For example, the evaluation unit may have the generating AI prioritize the evaluation of the latest information to provide highly reliable information. The evaluation unit may also have the generating AI prioritize the evaluation of the latest information, delaying the evaluation of older information. The evaluation unit may also adjust the evaluation priority based on the information's release date and time. This allows the evaluation unit to prioritize the provision of the latest information by determining the evaluation priority based on the information's release date and time. The information's release date and time may include, but are not limited to, criteria for prioritizing the latest information. Some or all of the above processing in the evaluation unit may be performed using the generating AI or not. For example, the evaluation unit may input the information's release date and time to the generating AI and have the generating AI determine the evaluation priority.

[0097] The evaluation unit can adjust the order of evaluation based on the relevance of the information when evaluating reliability. For example, the evaluation unit can have the generating AI prioritize the evaluation of highly relevant information to provide reliable information. The evaluation unit can also have the generating AI postpone the evaluation of less relevant information and prioritize important information. The evaluation unit can also have the generating AI adjust the order of evaluation based on the relevance of the information. This allows for the priority provision of important information by adjusting the order of evaluation based on the relevance of the information. The relevance of the information includes, but is not limited to, related topics and common themes. Some or all of the above processing in the evaluation unit may be performed using the generating AI or not. For example, the evaluation unit can input information relevance data into the generating AI and have the generating AI perform the adjustment of the evaluation order.

[0098] The link assignment unit can estimate the user's emotions and adjust the link assignment method based on the estimated emotions. For example, if the user is feeling anxious, the link assignment unit can have the generating AI prioritize links to reliable sources. If the user is relaxed, the link assignment unit can have the generating AI provide links to a wide range of sources. If the user is in a hurry, the link assignment unit can have the generating AI quickly provide links to primary sources. This allows the system to provide links that are appropriate for the user by adjusting the link assignment method according to the user's emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the processing described above in the link assignment unit may be performed using the generating AI or not. For example, the link assignment unit can input user emotion data into the generating AI and have the generating AI adjust the link assignment method.

[0099] The link assignment unit can adjust how links are displayed based on the reliability of the information when assigning links. For example, the link assignment unit can make links to reliable sources more prominent using the generating AI. The link assignment unit can also make links to less reliable sources less prominent using the generating AI. The link assignment unit can also adjust how links are displayed based on the reliability of the information using the generating AI. This allows users to easily identify reliable information by adjusting how links are displayed based on the reliability of the information. Reliability of information includes, but is not limited to, reliable sources and official announcements. Some or all of the above processing in the link assignment unit may be performed using the generating AI or not. For example, the link assignment unit can input information reliability data into the generating AI and have the generating AI perform the adjustment of how links are displayed.

[0100] The link assignment unit can apply different link assignment algorithms depending on the information category when assigning links. For example, the link assignment unit can have the generating AI prioritize linking to official government announcements for political information. The link assignment unit can also have the generating AI prioritize linking to official company announcements for economic information. The link assignment unit can also have the generating AI prioritize linking to academic papers for scientific information. By applying different link assignment algorithms depending on the information category, it is possible to provide links that are appropriate to the characteristics of the information. Information categories include, but are not limited to, news, academic papers, and blog posts. Some or all of the above processing in the link assignment unit may be performed using the generating AI or not. For example, the link assignment unit can input the information category into the generating AI and have the generating AI execute the application of the link assignment algorithm.

[0101] The link assignment unit can estimate the user's emotions and adjust the display order of links based on the estimated emotions. For example, if the user is feeling anxious, the link assignment unit's generating AI can display links to reliable sources first. If the user is relaxed, the link assignment unit's generating AI can randomly display links to a wide range of sources. If the user is in a hurry, the link assignment unit's generating AI can display links to primary sources first. This allows the system to provide users with links that are appropriate to them by adjusting the display order of links according to their emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the link assignment unit may be performed using the generating AI or not. For example, the link assignment unit can input user emotion data into the generating AI and have the generating AI adjust the display order of links.

[0102] The link assignment unit can determine the priority of links by considering the reliability of the information source when assigning links. For example, the link assignment unit may have a generating AI prioritize links to official government announcements. The link assignment unit may also have a generating AI prioritize links to well-known news sources. The link assignment unit may also have a generating AI prioritize links to expert opinions. By determining the priority of links by considering the reliability of the information source, the system can prioritize the provision of reliable information. The reliability of the information source includes, but is not limited to, past reliability assessments of the source and official announcements. Some or all of the above processing in the link assignment unit may be performed using a generating AI or not. For example, the link assignment unit can input reliability data of the information source into a generating AI and have the generating AI perform the determination of link priority.

[0103] The linking unit can improve the accuracy of links by referring to related literature when assigning links. For example, the linking unit can have the generating AI assign links to relevant academic papers and verify the accuracy of the information. The linking unit can also have the generating AI assign links to relevant reports and verify the accuracy of the information. The linking unit can also have the generating AI assign links to relevant news articles and verify the accuracy of the information. In this way, the accuracy of links can be improved by referring to related literature. Related literature includes, but is not limited to, citations and related research papers. Some or all of the above processing in the linking unit may be performed using the generating AI or not. For example, the linking unit can input related literature data into the generating AI and have the generating AI perform the linking accuracy improvement.

[0104] The report generation unit can estimate the user's emotions and adjust how the report is displayed based on the estimated emotions. For example, if the user is feeling anxious, the generating AI can provide a detailed report and highlight reliable information. If the user is relaxed, the generating AI can also provide a concise report and display a wide range of information. If the user is in a hurry, the generating AI can quickly display the main report and highlight important information. This allows the report to be tailored to the user by adjusting how it is displayed according to their emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input user emotion data into the generating AI and have the generating AI adjust how the report is displayed.

[0105] The report generation unit can adjust the level of detail in a report based on the reliability of the information during report generation. For example, the report generation unit can generate a detailed report for information that the generating AI finds reliable. The report generation unit can also generate a concise report for information that the generating AI finds unreliable. The report generation unit can also adjust the level of detail in a report based on the reliability of the information. This allows users to easily verify reliable information by adjusting the level of detail in the report based on the reliability of the information. Information reliability includes, but is not limited to, reliable sources and official announcements. Some or all of the above processing in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input information reliability data into the generating AI and have the generating AI perform the adjustment of the level of detail in the report.

[0106] The report generation unit can apply different report generation algorithms depending on the category of information when generating a report. For example, the generating AI can generate a report based on official government announcements for political information. The generating AI can also generate a report based on economic indicators and official company announcements for economic information. The generating AI can also generate a report based on academic papers and expert opinions for scientific information. By applying different report generation algorithms depending on the category of information, it is possible to provide reports that are appropriate to the characteristics of the information. Categories of information include, but are not limited to, news, academic papers, and blog posts. Some or all of the above processing in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input the category of information into the generating AI and have the generating AI execute the application of the report generation algorithm.

[0107] The report generation unit can estimate the user's emotions and adjust the display order of the report based on the estimated emotions. For example, if the user is feeling anxious, the generating AI can display reliable information first. If the user is relaxed, the generating AI can also display a wide range of information randomly. If the user is in a hurry, the generating AI can also display key information first. This allows the report to be tailored to the user by adjusting the display order of the report according to the user's emotions. The user's emotions are realized using an emotion estimation function, such as an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input user emotion data into the generating AI and have the generating AI adjust the display order of the report.

[0108] The report generation unit can determine the priority of reports based on the information's origin date and time when generating reports. For example, the generating AI can prioritize including the latest information in the report. The report generation unit can also have the generating AI postpone the inclusion of older information in the report. The report generation unit can also have the generating AI adjust the report priority based on the information's origin date and time. This allows for the prioritization of the latest information by determining the report priority based on the information's origin date and time. The information's origin date and time may include, but are not limited to, criteria for prioritizing the latest information. Some or all of the above-described processes in the report generation unit may be performed using the generating AI or not. For example, the report generation unit can input the information's origin date and time to the generating AI and have the generating AI determine the report priority.

[0109] The report generation unit can adjust the order of reports based on the relevance of the information during report generation. For example, the report generation unit can prioritize including highly relevant information in the report based on the generation AI. The report generation unit can also postpone including less relevant information in the report based on the generation AI. The report generation unit can also adjust the order of reports based on the relevance of the information based on the generation AI. This allows important information to be provided preferentially by adjusting the order of reports based on the relevance of the information. Relevance of information includes, but is not limited to, related topics and common themes. Some or all of the above processing in the report generation unit may be performed using the generation AI or not. For example, the report generation unit can input information relevance data into the generation AI and have the generation AI perform the adjustment of the report order.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The data collection unit can estimate the user's emotions and adjust the document analysis method based on the estimated emotions. For example, if the user is stressed, the generative AI can apply a concise analysis method and extract only the important facts. If the user is relaxed, the generative AI can apply a detailed analysis method and gain a deeper understanding of the overall context of the document. If the user is in a hurry, the generative AI can perform a rapid analysis and prioritize the identification of key facts. In this way, by adjusting the document analysis method according to the user's emotions, it is possible to provide analysis results that are appropriate for the user.

[0112] The verification unit can estimate the user's emotions and adjust the verification criteria based on those emotions. For example, if the user is feeling anxious, the generative AI can apply strict verification criteria to provide reliable information. If the user is relaxed, the generative AI can apply flexible verification criteria to provide a wide range of information. If the user is in a hurry, the generative AI can apply rapid verification criteria to prioritize verifying key facts. This allows the system to provide verification results that are appropriate for the user by adjusting the verification criteria according to their emotions.

[0113] The evaluation unit can estimate the user's emotions and adjust the reliability evaluation method based on the estimated user emotions. For example, if the user is feeling anxious, the generating AI can apply strict evaluation criteria to provide reliable information. If the user is relaxed, the generating AI can apply flexible evaluation criteria to provide a wide range of information. If the user is in a hurry, the generating AI can apply rapid evaluation criteria and prioritize evaluating key facts. In this way, by adjusting the reliability evaluation method according to the user's emotions, it is possible to provide evaluation results that are appropriate for the user.

[0114] The link generation unit can estimate the user's emotions and adjust the link generation method based on the estimated emotions. For example, if the user is feeling anxious, the generating AI will prioritize providing links to reliable sources. If the user is relaxed, the generating AI can also provide links to a wide range of sources. If the user is in a hurry, the generating AI can quickly provide links to major sources. In this way, by adjusting the link generation method according to the user's emotions, it is possible to provide links that are appropriate for the user.

[0115] The report generation unit can estimate the user's emotions and adjust how the report is displayed based on those emotions. For example, if the user is feeling anxious, the generating AI can provide a detailed report and highlight reliable information. If the user is relaxed, the generating AI can provide a concise report and display a wide range of information. If the user is in a hurry, the generating AI can quickly display the main report and highlight important information. In this way, by adjusting how the report is displayed according to the user's emotions, a report tailored to the user can be provided.

[0116] The data collection unit can prioritize identifying factual information based on specific keywords and phrases during document analysis. For example, the generating AI can prioritize analyzing keywords such as "official announcement" and "evidence" to identify highly reliable information. The generating AI can also analyze phrases such as "eyewitness accounts" and "reports" to quickly extract factual information. The generating AI can also analyze keywords such as "investigation results" and "statistical data" to identify highly reliable information. In this way, highly reliable information can be quickly extracted by prioritizing the identification of factual information based on specific keywords and phrases.

[0117] The data collection unit can apply different analysis algorithms depending on the type of document during analysis. For example, the generating AI can apply an analysis algorithm that prioritizes speed to news articles. It can also apply an analysis algorithm that considers personal opinions and impressions to blog posts. Furthermore, it can apply an analysis algorithm that prioritizes specialized terminology and citations to academic papers. By applying different analysis algorithms depending on the document type, the system can provide analysis results tailored to the characteristics of each document.

[0118] The verification unit can improve the accuracy of verification by cross-referencing multiple public databases and information sources during the verification process. For example, the generating AI can verify information by cross-referencing official government databases with reliable news sources. The generating AI can also verify information by cross-referencing academic paper databases with expert blogs. The generating AI can also verify information by cross-referencing official company announcements with third-party reports. In this way, the accuracy of verification can be improved by cross-referencing multiple public databases and information sources.

[0119] The evaluation unit can adjust the level of detail in its reliability assessment based on the source and citation count of the information. For example, if the generating AI's source is official, it will perform a detailed evaluation. If the generating AI's source is frequently cited, it can also perform a detailed evaluation. If the generating AI's source is unclear, it can perform a simplified evaluation. By adjusting the level of detail in the evaluation based on the source and citation count of the information, it is possible to provide highly reliable information.

[0120] The link assignment unit can adjust how links are displayed based on the reliability of the information when assigning links. For example, the generating AI can make links to reliable sources more prominent. The generating AI can also make links to less reliable sources less prominent. The generating AI can adjust how links are displayed based on the reliability of the information. This allows users to easily identify reliable information by adjusting how links are displayed based on the reliability of the information.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The collection unit analyzes the document and identifies the parts containing factual information. The collection unit analyzes documents such as news articles and blog posts and extracts the parts containing factual information. The collection unit can use generative AI to analyze the content of the document and identify factual information based on specific keywords and phrases. Step 2: The Verification Department verifies the facts identified by the Collection Department by cross-referencing them with public databases and reliable information sources. For example, the Verification Department checks the accuracy of the information in the document by comparing it with official government databases and reliable news sources. The Verification Department uses a knowledge graph with generative AI to understand the context of the information and verify the facts. Step 3: The evaluation unit assesses the reliability of the information verified by the verification unit in percentage terms and highlights questionable parts of the document. For example, the evaluation unit highlights information with low reliability in red and information with high reliability in green. Step 4: The linking unit provides links to data sources that can be referenced for the information evaluated by the evaluation unit. For example, the linking unit provides links to data sources that can be referenced for the relevant information. Step 5: The report generation unit generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, making highly reliable and less reliable information visually understandable. For example, the report generation unit displays highly reliable information in blue and less reliable information in red.

[0123] 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 audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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 audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the collection unit, verification unit, evaluation unit, linking unit, and report generation unit, is implemented in at least one of the smart device 14 and the data processing device 12. For example, the collection unit is implemented by the computer 36 of the smart device 14, which analyzes the document and identifies the parts containing factual information. The verification unit is implemented by the identification processing unit 290 of the data processing device 12, which cross-references with public databases and reliable information sources to verify the factual information. The evaluation unit is implemented by the control unit 46A of the smart device 14, which evaluates the reliability of each piece of information in percentages and highlights questionable parts of the document. The linking unit is implemented by the identification processing unit 290 of the data processing device 12, which provides links to data sources that can be referenced for the evaluated information. The report generation unit is implemented by the control unit 46A of the smart device 14, which generates a report summarizing the verification results, making highly reliable and low-reliability information visually understandable. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, 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 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] 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 audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a 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. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed 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 necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the collection unit, verification unit, evaluation unit, linking unit, and report generation unit, is implemented in at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is implemented by the computer 36 of the smart glasses 214, which analyzes the document and identifies the parts containing factual information. The verification unit is implemented by the identification processing unit 290 of the data processing device 12, which cross-references with public databases and reliable information sources to verify the facts. The evaluation unit is implemented by the control unit 46A of the smart glasses 214, which evaluates the reliability of each piece of information in percentages and highlights questionable parts of the document. The linking unit is implemented by the identification processing unit 290 of the data processing device 12, which provides links to data sources that can be referenced for the evaluated information. The report generation unit is implemented by the control unit 46A of the smart glasses 214, which generates a report summarizing the verification results and presents highly reliable and low-reliability information in a visually understandable format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, 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 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a 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. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the collection unit, verification unit, evaluation unit, linking unit, and report generation unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the headset terminal 314, which analyzes the document and identifies the parts containing factual information. The verification unit is implemented by the identification processing unit 290 of the data processing unit 12, which cross-references with public databases and reliable information sources to verify the facts. The evaluation unit is implemented by the control unit 46A of the headset terminal 314, which evaluates the reliability of each piece of information in percentages and highlights questionable parts of the document. The linking unit is implemented by the identification processing unit 290 of the data processing unit 12, which provides links to data sources that can be referenced for the evaluated information. The report generation unit is implemented by the control unit 46A of the headset terminal 314, which generates a report summarizing the verification results and presents highly reliable and low-reliability information in a visually understandable format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the 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 user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also 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 processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a 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. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] 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 performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed 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 necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the collection unit, verification unit, evaluation unit, linking unit, and report generation unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit is implemented by the computer 36 of the robot 414, which analyzes the document and identifies the parts containing factual information. The verification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which cross-references with public databases and reliable information sources to verify the factual information. The evaluation unit is implemented by, for example, the control unit 46A of the robot 414, which evaluates the reliability of each piece of information in percentages and highlights questionable parts in the document. The linking unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12, which provides links to data sources that can be referenced for the evaluated information. The report generation unit is implemented by, for example, the control unit 46A of the robot 414, which generates a report summarizing the verification results and presents highly reliable and low-reliability information in a visually understandable format. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in 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 the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it 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 emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] Alternatively, 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 in response to a request from the data processing device 12.

[0186] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) A collection unit that analyzes the document and identifies the parts containing factual information, The verification unit cross-references the facts identified by the collection unit with public databases and reliable information sources to verify them, An evaluation unit that evaluates the reliability of the information verified by the verification unit in percentage terms and highlights questionable parts of the document, A linking unit that provides a link to a data source that can be referenced for the information evaluated by the evaluation unit, The system includes a report generation unit that generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, and that presents highly reliable and low-reliability information in a visually understandable format. A system characterized by the following features. (Note 2) The aforementioned collection unit is Analyze documents such as news articles and blog posts to identify sections containing factual information. The system described in Appendix 1, characterized by the features described herein. (Note 3) The verification unit, We verify the accuracy of the information in the document by cross-referencing it with official government databases and reliable news sources. The system described in Appendix 1, characterized by the features described herein. (Note 4) The evaluation unit, Low-reliability information is highlighted in red, and high-reliability information is highlighted in green. The system described in Appendix 1, characterized by the features described herein. (Note 5) The linking unit is, Provide links to the relevant data sources. The system described in Appendix 1, characterized by the features described herein. (Note 6) The report generation unit, Highly reliable information is displayed in blue, and less reliable information is displayed in red. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is It estimates the user's emotions and adjusts the document analysis method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is When analyzing a document, prioritize identifying factual information based on specific keywords or phrases. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is When analyzing documents, different analysis algorithms are applied depending on the type of document. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and determines the priority of documents to analyze based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is When analyzing documents, the system prioritizes analyzing the most recent information, taking into account the document's publication date and time. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is When analyzing documents, the system prioritizes analyzing highly reliable documents by considering the author information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The verification unit, We estimate the user's emotions and adjust the validation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The verification unit, During verification, we cross-reference multiple public databases and information sources to improve the accuracy of the verification. The system described in Appendix 1, characterized by the features described herein. (Note 15) The verification unit, During verification, different verification methods are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The verification unit, It estimates the user's emotions and adjusts how the verification results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The verification unit, During verification, the reliability of the information source is taken into consideration when determining the priority of verification. The system described in Appendix 1, characterized by the features described herein. (Note 18) The verification unit, During verification, we refer to relevant literature to improve the accuracy of the verification. The system described in Appendix 1, characterized by the features described herein. (Note 19) The evaluation unit, We estimate user sentiment and adjust the reliability evaluation method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 20) The evaluation unit, When evaluating reliability, adjust the level of detail based on the source of the information and the number of citations. The system described in Appendix 1, characterized by the features described herein. (Note 21) The evaluation unit, When evaluating reliability, different evaluation algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 22) The evaluation unit, The system estimates user sentiment and adjusts how reliability evaluation results are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 23) The evaluation unit, When evaluating reliability, the evaluation priority is determined based on the date and time the information was published. The system described in Appendix 1, characterized by the features described herein. (Note 24) The evaluation unit, When evaluating reliability, adjust the order of evaluation based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. (Note 25) The linking unit is, It estimates the user's emotions and adjusts the linking method based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The linking unit is, When a link is added, the way the link is displayed is adjusted based on the reliability of the information. The system described in Appendix 1, characterized by the features described herein. (Note 27) The linking unit is, When assigning links, different link assignment algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 28) The linking unit is, It estimates the user's sentiment and adjusts the display order of links based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 29) The linking unit is, When creating links, the priority of the links is determined by considering the reliability of the information source. The system described in Appendix 1, characterized by the features described herein. (Note 30) The linking unit is, When creating links, we improve the accuracy of the links by referring to related literature. The system described in Appendix 1, characterized by the features described herein. (Note 31) The report generation unit, It estimates user sentiment and adjusts how reports are displayed based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The report generation unit, When generating a report, adjust the level of detail in the report based on the reliability of the information. The system described in Appendix 1, characterized by the features described herein. (Note 33) The report generation unit, When generating reports, different report generation algorithms are applied depending on the category of information. The system described in Appendix 1, characterized by the features described herein. (Note 34) The report generation unit, It estimates user sentiment and adjusts the display order of reports based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The report generation unit, When generating reports, the report priority is determined based on the date and time the information was sent. The system described in Appendix 1, characterized by the features described herein. (Note 36) The report generation unit, When generating reports, adjust the order of the reports based on the relevance of the information. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. A collection unit that analyzes the document and identifies the parts containing factual information, The verification unit cross-references the facts identified by the collection unit with public databases and reliable information sources to verify them, An evaluation unit that evaluates the reliability of the information verified by the verification unit in percentage terms and highlights questionable parts of the document, A linking unit that provides a link to a data source that can be referenced for the information evaluated by the evaluation unit, The system includes a report generation unit that generates a report summarizing the verification results based on the information obtained by the evaluation unit and the linking unit, and that presents highly reliable and low-reliability information in a visually understandable format. A system characterized by the following features.

2. The aforementioned collection unit is Analyze documents such as news articles and blog posts to identify sections containing factual information. The system according to feature 1.

3. The verification unit, We verify the accuracy of the information in the document by cross-referencing it with official government databases and reliable news sources. The system according to feature 1.

4. The evaluation unit described above, Low-reliability information is highlighted in red, and high-reliability information is highlighted in green. The system according to feature 1.

5. The linking unit is, Provide links to the relevant data sources. The system according to feature 1.

6. The report generation unit, Highly reliable information is displayed in blue, and less reliable information is displayed in red. The system according to feature 1.

7. The aforementioned collection unit is It estimates the user's emotions and adjusts the document analysis method based on the estimated user emotions. The system according to feature 1.

8. The aforementioned collection unit is When analyzing a document, prioritize identifying factual information based on specific keywords or phrases. The system according to feature 1.

Images