system

Abstract

The system according to this embodiment aims to evaluate the reliability of news articles and websites, detect misinformation, and provide appropriate information. [Solution] The system according to the embodiment comprises an analysis unit, an evaluation unit, a detection unit, and a provision unit. The analysis unit analyzes the content of news articles and websites. The evaluation unit evaluates the reliability of the content analyzed by the analysis unit. The detection unit detects misinformation based on the results evaluated by the evaluation unit. The provision unit provides appropriate information based on the misinformation detected by the detection unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the reliability of news articles and websites has not been sufficiently evaluated to detect misinformation, and there is room for improvement.

[0005] The system according to the embodiment aims to evaluate the reliability of news articles and websites, detect misinformation, and provide appropriate information.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an analysis unit, an evaluation unit, a detection unit, and a provision unit. The analysis unit analyzes the content of news articles and websites. The evaluation unit evaluates the reliability of the content analyzed by the analysis unit. The detection unit detects misinformation based on the results evaluated by the evaluation unit. The provision unit provides appropriate information based on the misinformation detected by the detection unit. [Effects of the Invention]

[0007] The system according to this embodiment can evaluate the reliability of news articles and websites, detect misinformation, and provide appropriate information. [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 signed storage is one or more non-volatile storage devices that store various programs and various parameters. 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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of 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 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the 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) An educational support system according to an embodiment of the present invention is a system that uses generative AI to rate the reliability of news articles and websites, enabling children to access reliable information with peace of mind. The educational support system analyzes the content of news articles and websites using natural language processing technology and evaluates the reliability of the analyzed content in cooperation with a fact-checking API. Based on the evaluation results, it automatically detects misinformation and unreliable content and provides children with appropriate information. For example, the educational support system analyzes the content of news articles and websites using natural language processing technology. In this process, it analyzes the content of the article in detail and extracts important information and keywords. For example, it identifies facts and claims mentioned in the article and collects basic data to evaluate whether they are reliable. Next, the educational support system evaluates the reliability of the analyzed content in cooperation with a fact-checking API. The fact-checking API compares the content of the article with existing reliable databases to determine whether it is accurate. For example, it checks whether the statistical data and citations mentioned in the article are accurate. This allows for an objective evaluation of the reliability of the article. Next, the educational support system automatically detects misinformation and unreliable content based on the evaluation results. For example, if an error is detected by a fact-checking API, the article will be deemed unreliable. In this way, misinformation and unreliable content can be automatically filtered out. Finally, the educational support system provides children with appropriate information. Only articles and websites rated as highly reliable are displayed to children, providing a safe learning environment. For example, reliable information can be provided through educational portal sites and applications. This allows children to access trustworthy information with peace of mind without being misled by misinformation. Furthermore, in educational settings, it becomes possible to conduct lessons and learning based on reliable information. For example, by providing reliable information as teaching materials and references, the quality of education can be improved. In this way, the educational support system ensures that children can access trustworthy information with peace of mind.

[0029] The educational support system according to this embodiment comprises an analysis unit, an evaluation unit, a detection unit, and a provision unit. The analysis unit analyzes the content of news articles and websites. The analysis unit analyzes the content of news articles and websites using, for example, natural language processing technology. For example, the analysis unit uses morphological analysis to analyze the content of the article in detail. The analysis unit can also analyze the grammatical structure of the article using grammatical analysis. The analysis unit can also analyze the meaning of the article using semantic analysis. For example, the analysis unit uses morphological analysis to extract important information and keywords from the article. Grammatical analysis is used to analyze the grammatical structure of the article and understand the structure of sentences. Semantic analysis is used to analyze the meaning of the article and understand the content of the article. The evaluation unit evaluates the reliability of the content analyzed by the analysis unit. The evaluation unit evaluates the reliability of the analyzed content in cooperation with, for example, a fact-checking API. For example, the evaluation unit uses a fact-checking API to verify whether the statistical data and citations mentioned in the article are accurate. The evaluation unit can also use a fact-checking API to evaluate whether the content of the article is reliable. Furthermore, the evaluation unit can objectively assess the reliability of an article using a fact-checking API. For example, the evaluation unit can use the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The fact-checking API compares the article's content with existing reliable databases to determine its accuracy. This allows the evaluation unit to objectively assess the reliability of the article. The detection unit detects misinformation based on the results evaluated by the evaluation unit. For example, the detection unit automatically detects misinformation based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit determines that the article is unreliable. The detection unit can also automatically filter out misinformation and unreliable content based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit determines that the article is unreliable. This allows the detection unit to automatically filter out misinformation and unreliable content. The provision unit provides appropriate information based on the misinformation detected by the detection unit.The information provider can, for example, display only articles and websites that have been evaluated as highly reliable to children. For example, the information provider can provide reliable information through educational portal sites and applications. The information provider can also display only articles and websites that have been evaluated as highly reliable to children. The information provider can also display only articles and websites that have been evaluated as highly reliable to children. For example, the information provider can provide reliable information through educational portal sites and applications. This allows the educational support system according to the embodiment to allow children to access reliable information with peace of mind. Some or all of the processing described above in the information provider can be performed using AI, for example, or without AI. For example, the information provider can input articles and websites that have been evaluated as highly reliable into a generating AI and have the generating AI perform the task of providing appropriate information.

[0030] The analysis unit analyzes the content of news articles and websites. For example, it uses natural language processing techniques to analyze the content of news articles and websites. Specifically, it uses morphological analysis to analyze the content of articles in detail. Morphological analysis is a technique that breaks down text into words and morphemes, clarifying their meaning and role. This allows for the extraction of important information and keywords within the article. Furthermore, it can also analyze the grammatical structure of the article using grammatical analysis. Grammatical analysis is a technique that understands the structure of a text and clarifies the relationships between subjects, predicates, objects, etc. This allows for an accurate grasp of the overall meaning of the text. It can also analyze the meaning of the article using semantic analysis. Semantic analysis is a technique that understands the content of a text and grasps the underlying intentions and context. For example, by using morphological analysis to extract important information and keywords within the article, analyzing the grammatical structure using grammatical analysis, and analyzing the meaning of the article using semantic analysis, the content of the article can be understood in detail. This allows the analysis unit to analyze the content of news articles and websites in detail and provide information necessary for evaluating reliability and detecting misinformation.

[0031] The evaluation unit assesses the reliability of the content analyzed by the analysis unit. For example, the evaluation unit evaluates the reliability of the analyzed content in conjunction with a fact-checking API. Specifically, it uses the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The fact-checking API compares the information with existing reliable databases to determine the accuracy of the article's content. For example, the evaluation unit uses the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The evaluation unit can also use the fact-checking API to assess the reliability of the article's content. Furthermore, the evaluation unit can use the fact-checking API to objectively evaluate the reliability of the article. For example, the evaluation unit uses the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The fact-checking API compares the information with existing reliable databases to determine the accuracy of the article's content. This allows the evaluation unit to objectively evaluate the reliability of the article. Furthermore, the evaluation unit can comprehensively evaluate the reliability of the article based on the information provided by the analysis unit. For example, the reliability of an article can be evaluated by considering factors such as the source of the article, the author's credibility, and their past performance. This allows the evaluation unit to accurately assess the reliability of the content analyzed by the analysis unit, contributing to the detection of misinformation and the provision of appropriate information.

[0032] The detection unit detects misinformation based on the results evaluated by the evaluation unit. For example, the detection unit automatically detects misinformation based on the results evaluated by the evaluation unit. Specifically, if an error is detected by the fact-checking API, the article is judged to be unreliable. The detection unit can also automatically filter out misinformation and unreliable content based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the article is judged to be unreliable. This allows the detection unit to automatically filter out misinformation and unreliable content. Furthermore, the detection unit can learn patterns and characteristics of misinformation based on the information provided by the evaluation unit, thereby improving the accuracy of future misinformation detection. For example, it can extract characteristics of misinformation based on data of misinformation detected in the past and utilize them to detect new misinformation. The detection unit can also improve the accuracy of misinformation detection using AI. For example, it can learn patterns and characteristics of misinformation using machine learning algorithms and utilize them to detect new misinformation. This allows the detection unit to improve the accuracy of misinformation detection and build a foundation for providing highly reliable information.

[0033] The information provider provides appropriate information based on the misinformation detected by the detection unit. For example, the information provider displays only articles and websites that have been evaluated as highly reliable to children. Specifically, it provides reliable information through educational portal sites and applications. For example, the information provider can input articles and websites that have been evaluated as highly reliable into a generating AI and have the generating AI provide appropriate information. Based on the input information, the generating AI provides information in a format suitable for children. For example, the generating AI can summarize the content of articles concisely or provide information in a visually easy-to-understand format. This allows the information provider to ensure that children can access reliable information with peace of mind. In addition, the information provider can collect user feedback and continuously improve the quality of the information it provides. For example, based on user feedback, it can review the content and format of the information provided and provide more understandable and reliable information. Furthermore, the information provider can reliably transmit information using multiple communication methods. For example, it can provide information not only through educational portal sites and applications, but also through email and social media. This allows the information provider to ensure that children can access reliable information with peace of mind.

[0034] The analysis unit can analyze the content of news articles and websites using natural language processing techniques. For example, the analysis unit can use morphological analysis to analyze the content of an article in detail. For example, the analysis unit can use morphological analysis to extract important information and keywords from the article. The analysis unit can also use grammatical analysis to analyze the grammatical structure of an article. For example, the analysis unit can use grammatical analysis to analyze the grammatical structure of an article and understand the structure of sentences. The analysis unit can also use semantic analysis to analyze the meaning of an article. For example, the analysis unit can use semantic analysis to analyze the meaning of an article and understand its content. In this way, the content of news articles and websites can be analyzed in detail using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the content of a news article or website into a generating AI and have the generating AI perform analysis using natural language processing techniques.

[0035] The evaluation unit can assess the reliability of the analyzed content in conjunction with a fact-checking API. For example, the evaluation unit can use the fact-checking API to verify whether the statistical data and citations mentioned in the article are accurate. For example, the evaluation unit can use the fact-checking API to assess whether the content of the article is reliable. The evaluation unit can also use the fact-checking API to objectively evaluate the reliability of the article. For example, the evaluation unit can use the fact-checking API to verify whether the statistical data and citations mentioned in the article are accurate. The fact-checking API compares the content of the article with existing reliable databases to determine whether it is accurate. This allows the evaluation unit to objectively evaluate the reliability of the article. This allows the evaluation unit to objectively evaluate the reliability of the analyzed content in conjunction with a fact-checking API. Fact-checking APIs include, but are not limited to, PolitiFact and FactCheck.org. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input the fact-checking API into a generating AI and have the generating AI perform the reliability evaluation.

[0036] The detection unit can detect misinformation based on the results evaluated by the evaluation unit. For example, the detection unit can automatically detect misinformation based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit will determine that the article is unreliable. The detection unit can also automatically filter out misinformation and unreliable content based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit will determine that the article is unreliable. This allows the detection unit to automatically filter out misinformation and unreliable content. This allows the detection unit to automatically detect misinformation based on the evaluation results. Misinformation includes, but is not limited to, false information and misleading information. Some or all of the above processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can input the results evaluated by the evaluation unit into a generating AI and have the generating AI perform misinformation detection.

[0037] The information provider can display only articles and websites that have been deemed highly reliable to children. The information provider can provide reliable information, for example, through educational portal sites and applications. For example, the information provider can display only articles and websites that have been deemed highly reliable to children. The information provider can also display only articles and websites that have been deemed highly reliable to children. The information provider can also display only articles and websites that have been deemed highly reliable to children. For example, the information provider can provide reliable information through educational portal sites and applications. This provides a safe learning environment for children by providing only highly reliable information. Highly reliable information includes, but is not limited to, fact-checked information and information based on reliable sources. Some or all of the processing described above in the information provider may be performed using AI, for example, or not using AI. For example, the information provider can input articles and websites deemed highly reliable into a generating AI and have the generating AI provide appropriate information.

[0038] The analysis unit can prioritize the analysis of news articles and website content based on specific themes or topics. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. The analysis unit can also prioritize the analysis of health-related articles to provide reliable health information. For example, the analysis unit can prioritize the analysis of health-related articles to provide reliable health information. The analysis unit can also prioritize the analysis of environmental issues to provide up-to-date environmental information. For example, the analysis unit can prioritize the analysis of environmental issues to provide up-to-date environmental information. In this way, by prioritizing the analysis based on specific themes or topics, information suitable for children can be provided. Specific themes or topics include, but are not limited to, politics, economics, and science. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input news articles or website content into the generation AI and have the generation AI perform analysis based on specific themes or topics.

[0039] The analysis unit can improve the accuracy of its analysis by considering the past credibility of the article's author. For example, the analysis unit can refer to the credibility score of the author's past articles and prioritize the analysis of articles by authors with high credibility. The analysis unit can also consider the author's past history of disseminating misinformation and carefully analyze articles by authors with low credibility. The analysis unit can also consider the author's field of expertise and evaluate their credibility in that field to improve the accuracy of its analysis. This allows for improved accuracy of the analysis by considering the article's author's past credibility. The article's author's past credibility includes, but is not limited to, past achievements and evaluations. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past reliability data of the article's author into the generating AI and have the generating AI perform a reliability evaluation.

[0040] The analysis unit can customize the analysis algorithm based on the language and region of the article during analysis. For example, the analysis unit applies appropriate natural language processing techniques depending on the language of the article. The analysis unit can also analyze while considering region-specific information based on the region of the article. The analysis unit can also analyze by referring to an appropriate database based on the language and region of the article. This allows for improved accuracy of the analysis by customizing the analysis algorithm based on the language and region of the article. Examples of article languages ​​and regions include, but are not limited to, Japanese, English, Asian regions, and European regions. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the language and region data of the article into a generating AI and have the generating AI perform the customization of the analysis algorithm.

[0041] The analysis unit can improve the accuracy of its analysis by considering the article's metadata (publication date, author, source, etc.) during the analysis. For example, the analysis unit can consider the article's publication date and prioritize analyzing the most recent information. The analysis unit can also evaluate the reliability of the article's author and prioritize analyzing articles by reliable authors. The analysis unit can also check the article's source and prioritize analyzing articles with reliable sources. By considering the article's metadata, the accuracy of the analysis can be improved. Article metadata includes, but is not limited to, the publication date, author, and source. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the article's metadata into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0042] The evaluation unit can improve the reliability of its evaluations by referencing multiple databases when collaborating with the fact-checking API. For example, the evaluation unit can refer to multiple reliable databases and cross-check the evaluation results. The evaluation unit can also integrate information from different databases and perform a comprehensive evaluation. The evaluation unit can also consider the update frequency of the databases and perform evaluations based on the latest information. For example, the evaluation unit considers the update frequency of the databases and performs evaluations based on the latest information. This improves the reliability of the evaluations by referencing multiple databases. Multiple databases include, but are not limited to, academic databases and news databases. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input information from multiple databases into a generating AI and have the generating AI perform the task of improving the reliability of the evaluations.

[0043] The evaluation unit can individually assess the reliability of the sources cited in an article and calculate an overall reliability score. For example, the evaluation unit can assess the past reliability of the sources cited in an article and calculate a reliability score. The evaluation unit can also consider the specialized field of the sources and assess their reliability in that field. For example, the evaluation unit can consider the specialized field of the sources and assess their reliability in that field. The evaluation unit can also consider the frequency of information provision by the sources and adjust the reliability score. For example, the evaluation unit can consider the frequency of information provision by the sources and adjust the reliability score. In this way, an overall reliability score can be calculated by individually assessing the reliability of the sources cited in an article. Source reliability includes, but is not limited to, the reliability of the source and the number of citations. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input the reliability data of the sources cited in an article into a generating AI and have the generating AI calculate the reliability score.

[0044] The evaluation unit can apply different evaluation criteria to articles based on their category (politics, economics, science, etc.) during the evaluation process. For example, the evaluation unit may evaluate political articles by referring to highly reliable databases. For example, the evaluation unit may evaluate economic articles based on the latest economic data. For example, the evaluation unit may evaluate science articles by referring to specialized databases. This allows for more appropriate evaluations by applying different evaluation criteria based on the article category. Article categories include, but are not limited to, politics, economics, and science. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input article category data into a generating AI and have the generating AI apply the evaluation criteria.

[0045] The evaluation unit can perform evaluations based on the latest information, taking into account the article's update history. For example, the evaluation unit can check the article's update history and perform evaluations based on the latest information. The evaluation unit can also evaluate fluctuations in reliability based on the update history. For example, the evaluation unit can evaluate fluctuations in reliability based on the update history. The evaluation unit can also consider the update history and check whether the latest information is reflected. For example, the evaluation unit considers the update history and checks whether the latest information is reflected. This makes it possible to perform evaluations based on the latest information by considering the article's update history. The article's update history includes, but is not limited to, the update date and time and the update content. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input the article's update history data into a generating AI and have the generating AI perform the evaluation.

[0046] The detection unit can improve the accuracy of misinformation detection by comparing the content of the article with the results of a fact-checking API during detection. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. The detection unit can also evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. For example, the detection unit can evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. The detection unit can also perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. For example, the detection unit can perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. This improves the accuracy of misinformation detection by comparing the content of the article with the results of the fact-checking API. Fact-checking APIs include, but are not limited to, PolitiFact and FactCheck.org. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input the content of the article and the results of the fact-checking API into the generating AI, and have the generating AI perform the detection of misinformation.

[0047] The detection unit can detect misinformation by considering the context and tone of the article during detection. For example, the detection unit can analyze the context of the article and evaluate the likelihood of misinformation. The detection unit can also analyze the tone of the article to improve the accuracy of misinformation detection. The detection unit can also integrate the context and tone to perform comprehensive misinformation detection. This allows for improved accuracy in detecting misinformation by considering the context and tone of the article. The context and tone of the article include, but are not limited to, sentiment analysis and contextual analysis. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can input data on the context and tone of the article into a generating AI and have the generating AI perform misinformation detection.

[0048] The detection unit can apply different detection algorithms to the article format (text, images, videos, etc.) during detection. For example, the detection unit can use natural language processing techniques to detect misinformation in text articles. The detection unit can also use image analysis techniques to detect misinformation in image articles. The detection unit can also use video analysis techniques to detect misinformation in video articles. By applying an appropriate detection algorithm based on the article format, the accuracy of misinformation detection can be improved. The article format includes, but is not limited to, text, images, and videos. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input article format data into a generating AI and have the generating AI perform the application of the detection algorithm.

[0049] The detection unit can improve the accuracy of misinformation detection by considering the article's related links and references during detection. For example, the detection unit can analyze the article's related links and evaluate the likelihood of misinformation. The detection unit can also check references and detect unreliable information. The detection unit can also integrate related links and references to perform comprehensive misinformation detection. By considering the article's related links and references, the accuracy of misinformation detection can be improved. Related links and references include, but are not limited to, link reliability and citation count. Some or all of the above processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can input data on the article's related links and references into a generating AI and have the generating AI perform misinformation detection.

[0050] The information provider can provide the most relevant information by referring to the user's past browsing history at the time of provision. For example, the information provider can analyze the user's past browsing history and provide relevant information. The information provider can also prioritize displaying reliable information that the user has previously viewed. The information provider can also predict and provide information that the user might be interested in based on their browsing history. This allows the information provider to provide more relevant information by referring to the user's past browsing history. The user's past browsing history includes, but is not limited to, the date and time of browsing and the content of browsing. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's past browsing history data into a generating AI and have the generating AI perform the task of providing the most relevant information.

[0051] The information provider can adjust the difficulty level of the information based on the user's age and grade level when providing it. For example, the provider can provide information that is easy to understand according to the user's age. The provider can also provide information of an appropriate difficulty level based on the user's grade level. The provider can also add explanations of technical terms according to the user's age and grade level. By adjusting the difficulty level of the information according to the user's age and grade level, it becomes possible to provide more appropriate information. The user's age and grade level include, but are not limited to, age groups and grade-specific information. Some or all of the above processing in the information provider may be performed using, for example, AI, or not using AI. For example, the provider can input user age and grade level data into a generating AI and have the generating AI perform the information difficulty level adjustment.

[0052] The service provider can select the optimal display method at the time of delivery, taking into account the user's device information (PC, smartphone, tablet, etc.). For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. The service provider can also provide a display method optimized for a larger screen if the user is using a tablet. For example, if the user is using a PC, the service provider can display detailed information. For example, if the user is using a PC, the service provider can display detailed information. This makes it possible to provide more appropriate information by selecting the optimal display method based on the user's device information. User device information includes, but is not limited to, PCs, smartphones, and tablets. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's device information into a generating AI and have the generating AI select the optimal display method.

[0053] The service provider can provide additional relevant information based on the user's interests at the time of delivery. For example, the service provider can analyze the user's past browsing history and provide additional relevant information. The service provider can also provide information on topics that the user might be interested in. The service provider can also suggest relevant news articles and websites based on the user's interests. This enables more appropriate information delivery by providing additional relevant information based on the user's interests. User interests include, but are not limited to, survey results and past browsing history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input user interest data into a generating AI and have the generating AI provide the additional relevant information.

[0054] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0055] The analysis unit can prioritize the analysis of news articles and website content based on specific themes or topics. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. The analysis unit can also prioritize the analysis of health-related articles to provide reliable health information. For example, the analysis unit can prioritize the analysis of health-related articles to provide reliable health information. The analysis unit can also prioritize the analysis of environmental issues to provide up-to-date environmental information. For example, the analysis unit can prioritize the analysis of environmental issues to provide up-to-date environmental information. In this way, by prioritizing the analysis based on specific themes or topics, information suitable for children can be provided. Specific themes or topics include, but are not limited to, politics, economics, and science. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input news articles or website content into the generation AI and have the generation AI perform analysis based on specific themes or topics.

[0056] The analysis unit can improve the accuracy of its analysis by considering the past credibility of the article's author. For example, the analysis unit can refer to the credibility score of the author's past articles and prioritize the analysis of articles by authors with high credibility. The analysis unit can also consider the author's past history of disseminating misinformation and carefully analyze articles by authors with low credibility. The analysis unit can also consider the author's field of expertise and evaluate their credibility in that field to improve the accuracy of its analysis. This allows for improved accuracy of the analysis by considering the article's author's past credibility. The article's author's past credibility includes, but is not limited to, past achievements and evaluations. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past reliability data of the article's author into the generating AI and have the generating AI perform a reliability evaluation.

[0057] The evaluation unit can improve the reliability of its evaluations by referencing multiple databases when collaborating with the fact-checking API. For example, the evaluation unit can refer to multiple reliable databases and cross-check the evaluation results. The evaluation unit can also integrate information from different databases and perform a comprehensive evaluation. The evaluation unit can also consider the update frequency of the databases and perform evaluations based on the latest information. For example, the evaluation unit considers the update frequency of the databases and performs evaluations based on the latest information. This improves the reliability of the evaluations by referencing multiple databases. Multiple databases include, but are not limited to, academic databases and news databases. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input information from multiple databases into a generating AI and have the generating AI perform the task of improving the reliability of the evaluations.

[0058] The detection unit can improve the accuracy of misinformation detection by comparing the content of the article with the results of a fact-checking API during detection. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. The detection unit can also evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. For example, the detection unit can evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. The detection unit can also perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. For example, the detection unit can perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. This improves the accuracy of misinformation detection by comparing the content of the article with the results of the fact-checking API. Fact-checking APIs include, but are not limited to, PolitiFact and FactCheck.org. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input the content of the article and the results of the fact-checking API into the generating AI, and have the generating AI perform the detection of misinformation.

[0059] The information provider can provide the most relevant information by referring to the user's past browsing history at the time of provision. For example, the information provider can analyze the user's past browsing history and provide relevant information. The information provider can also prioritize displaying reliable information that the user has previously viewed. The information provider can also predict and provide information that the user might be interested in based on their browsing history. This allows the information provider to provide more relevant information by referring to the user's past browsing history. The user's past browsing history includes, but is not limited to, the date and time of browsing and the content of browsing. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's past browsing history data into a generating AI and have the generating AI perform the task of providing the most relevant information.

[0060] The information provider can adjust the difficulty level of the information based on the user's age and grade level when providing it. For example, the provider can provide information that is easy to understand according to the user's age. The provider can also provide information of an appropriate difficulty level based on the user's grade level. The provider can also add explanations of technical terms according to the user's age and grade level. By adjusting the difficulty level of the information according to the user's age and grade level, it becomes possible to provide more appropriate information. The user's age and grade level include, but are not limited to, age groups and grade-specific information. Some or all of the above processing in the information provider may be performed using, for example, AI, or not using AI. For example, the provider can input user age and grade level data into a generating AI and have the generating AI perform the information difficulty level adjustment.

[0061] The following briefly describes the processing flow for example form 1.

[0062] Step 1: The analysis unit analyzes the content of news articles and websites. The analysis unit uses natural language processing technology to perform morphological analysis, grammatical analysis, and semantic analysis to extract important information and keywords from the article and understand its grammatical structure and meaning. Step 2: The evaluation unit assesses the reliability of the content analyzed by the analysis unit. The evaluation unit works in conjunction with the fact-checking API to verify the accuracy of the statistical data and citations mentioned in the article, and objectively evaluates the reliability of the article. Step 3: The detection unit detects misinformation based on the results evaluated by the evaluation unit. If an error is detected by the fact-checking API, the detection unit determines that the article is unreliable and automatically filters out misinformation and unreliable content. Step 4: The provider unit provides appropriate information based on the misinformation detected by the detection unit. The provider unit displays only articles and websites that have been rated as highly reliable and provides reliable information through educational portal sites and applications.

[0063] (Example of form 2) An educational support system according to an embodiment of the present invention is a system that uses generative AI to rate the reliability of news articles and websites, enabling children to access reliable information with peace of mind. The educational support system analyzes the content of news articles and websites using natural language processing technology and evaluates the reliability of the analyzed content in cooperation with a fact-checking API. Based on the evaluation results, it automatically detects misinformation and unreliable content and provides children with appropriate information. For example, the educational support system analyzes the content of news articles and websites using natural language processing technology. In this process, it analyzes the content of the article in detail and extracts important information and keywords. For example, it identifies facts and claims mentioned in the article and collects basic data to evaluate whether they are reliable. Next, the educational support system evaluates the reliability of the analyzed content in cooperation with a fact-checking API. The fact-checking API compares the content of the article with existing reliable databases to determine whether it is accurate. For example, it checks whether the statistical data and citations mentioned in the article are accurate. This allows for an objective evaluation of the reliability of the article. Next, the educational support system automatically detects misinformation and unreliable content based on the evaluation results. For example, if an error is detected by a fact-checking API, the article will be deemed unreliable. In this way, misinformation and unreliable content can be automatically filtered out. Finally, the educational support system provides children with appropriate information. Only articles and websites rated as highly reliable are displayed to children, providing a safe learning environment. For example, reliable information can be provided through educational portal sites and applications. This allows children to access trustworthy information with peace of mind without being misled by misinformation. Furthermore, in educational settings, it becomes possible to conduct lessons and learning based on reliable information. For example, by providing reliable information as teaching materials and references, the quality of education can be improved. In this way, the educational support system ensures that children can access trustworthy information with peace of mind.

[0064] The educational support system according to this embodiment comprises an analysis unit, an evaluation unit, a detection unit, and a provision unit. The analysis unit analyzes the content of news articles and websites. The analysis unit analyzes the content of news articles and websites using, for example, natural language processing technology. For example, the analysis unit uses morphological analysis to analyze the content of the article in detail. The analysis unit can also analyze the grammatical structure of the article using grammatical analysis. The analysis unit can also analyze the meaning of the article using semantic analysis. For example, the analysis unit uses morphological analysis to extract important information and keywords from the article. Grammatical analysis is used to analyze the grammatical structure of the article and understand the structure of sentences. Semantic analysis is used to analyze the meaning of the article and understand the content of the article. The evaluation unit evaluates the reliability of the content analyzed by the analysis unit. The evaluation unit evaluates the reliability of the analyzed content in cooperation with, for example, a fact-checking API. For example, the evaluation unit uses a fact-checking API to verify whether the statistical data and citations mentioned in the article are accurate. The evaluation unit can also use a fact-checking API to evaluate whether the content of the article is reliable. Furthermore, the evaluation unit can objectively assess the reliability of an article using a fact-checking API. For example, the evaluation unit can use the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The fact-checking API compares the article's content with existing reliable databases to determine its accuracy. This allows the evaluation unit to objectively assess the reliability of the article. The detection unit detects misinformation based on the results evaluated by the evaluation unit. For example, the detection unit automatically detects misinformation based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit determines that the article is unreliable. The detection unit can also automatically filter out misinformation and unreliable content based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit determines that the article is unreliable. This allows the detection unit to automatically filter out misinformation and unreliable content. The provision unit provides appropriate information based on the misinformation detected by the detection unit.The information provider can, for example, display only articles and websites that have been evaluated as highly reliable to children. For example, the information provider can provide reliable information through educational portal sites and applications. The information provider can also display only articles and websites that have been evaluated as highly reliable to children. The information provider can also display only articles and websites that have been evaluated as highly reliable to children. For example, the information provider can provide reliable information through educational portal sites and applications. This allows the educational support system according to the embodiment to allow children to access reliable information with peace of mind. Some or all of the processing described above in the information provider can be performed using AI, for example, or without AI. For example, the information provider can input articles and websites that have been evaluated as highly reliable into a generating AI and have the generating AI perform the task of providing appropriate information.

[0065] The analysis unit analyzes the content of news articles and websites. For example, it uses natural language processing techniques to analyze the content of news articles and websites. Specifically, it uses morphological analysis to analyze the content of articles in detail. Morphological analysis is a technique that breaks down text into words and morphemes, clarifying their meaning and role. This allows for the extraction of important information and keywords within the article. Furthermore, it can also analyze the grammatical structure of the article using grammatical analysis. Grammatical analysis is a technique that understands the structure of a text and clarifies the relationships between subjects, predicates, objects, etc. This allows for an accurate grasp of the overall meaning of the text. It can also analyze the meaning of the article using semantic analysis. Semantic analysis is a technique that understands the content of a text and grasps the underlying intentions and context. For example, by using morphological analysis to extract important information and keywords within the article, analyzing the grammatical structure using grammatical analysis, and analyzing the meaning of the article using semantic analysis, the content of the article can be understood in detail. This allows the analysis unit to analyze the content of news articles and websites in detail and provide information necessary for evaluating reliability and detecting misinformation.

[0066] The evaluation unit assesses the reliability of the content analyzed by the analysis unit. For example, the evaluation unit evaluates the reliability of the analyzed content in conjunction with a fact-checking API. Specifically, it uses the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The fact-checking API compares the information with existing reliable databases to determine the accuracy of the article's content. For example, the evaluation unit uses the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The evaluation unit can also use the fact-checking API to assess the reliability of the article's content. Furthermore, the evaluation unit can use the fact-checking API to objectively evaluate the reliability of the article. For example, the evaluation unit uses the fact-checking API to verify the accuracy of statistical data and citations mentioned in the article. The fact-checking API compares the information with existing reliable databases to determine the accuracy of the article's content. This allows the evaluation unit to objectively evaluate the reliability of the article. Furthermore, the evaluation unit can comprehensively evaluate the reliability of the article based on the information provided by the analysis unit. For example, the reliability of an article can be evaluated by considering factors such as the source of the article, the author's credibility, and their past performance. This allows the evaluation unit to accurately assess the reliability of the content analyzed by the analysis unit, contributing to the detection of misinformation and the provision of appropriate information.

[0067] The detection unit detects misinformation based on the results evaluated by the evaluation unit. For example, the detection unit automatically detects misinformation based on the results evaluated by the evaluation unit. Specifically, if an error is detected by the fact-checking API, the article is judged to be unreliable. The detection unit can also automatically filter out misinformation and unreliable content based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the article is judged to be unreliable. This allows the detection unit to automatically filter out misinformation and unreliable content. Furthermore, the detection unit can learn patterns and characteristics of misinformation based on the information provided by the evaluation unit, thereby improving the accuracy of future misinformation detection. For example, it can extract characteristics of misinformation based on data of misinformation detected in the past and utilize them to detect new misinformation. The detection unit can also improve the accuracy of misinformation detection using AI. For example, it can learn patterns and characteristics of misinformation using machine learning algorithms and utilize them to detect new misinformation. This allows the detection unit to improve the accuracy of misinformation detection and build a foundation for providing highly reliable information.

[0068] The information provider provides appropriate information based on the misinformation detected by the detection unit. For example, the information provider displays only articles and websites that have been evaluated as highly reliable to children. Specifically, it provides reliable information through educational portal sites and applications. For example, the information provider can input articles and websites that have been evaluated as highly reliable into a generating AI and have the generating AI provide appropriate information. Based on the input information, the generating AI provides information in a format suitable for children. For example, the generating AI can summarize the content of articles concisely or provide information in a visually easy-to-understand format. This allows the information provider to ensure that children can access reliable information with peace of mind. In addition, the information provider can collect user feedback and continuously improve the quality of the information it provides. For example, based on user feedback, it can review the content and format of the information provided and provide more understandable and reliable information. Furthermore, the information provider can reliably transmit information using multiple communication methods. For example, it can provide information not only through educational portal sites and applications, but also through email and social media. This allows the information provider to ensure that children can access reliable information with peace of mind.

[0069] The analysis unit can analyze the content of news articles and websites using natural language processing techniques. For example, the analysis unit can use morphological analysis to analyze the content of an article in detail. For example, the analysis unit can use morphological analysis to extract important information and keywords from the article. The analysis unit can also use grammatical analysis to analyze the grammatical structure of an article. For example, the analysis unit can use grammatical analysis to analyze the grammatical structure of an article and understand the structure of sentences. The analysis unit can also use semantic analysis to analyze the meaning of an article. For example, the analysis unit can use semantic analysis to analyze the meaning of an article and understand its content. In this way, the content of news articles and websites can be analyzed in detail using natural language processing techniques. Natural language processing techniques include, but are not limited to, morphological analysis, grammatical analysis, and semantic analysis. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the content of a news article or website into a generating AI and have the generating AI perform analysis using natural language processing techniques.

[0070] The evaluation unit can assess the reliability of the analyzed content in conjunction with a fact-checking API. For example, the evaluation unit can use the fact-checking API to verify whether the statistical data and citations mentioned in the article are accurate. For example, the evaluation unit can use the fact-checking API to assess whether the content of the article is reliable. The evaluation unit can also use the fact-checking API to objectively evaluate the reliability of the article. For example, the evaluation unit can use the fact-checking API to verify whether the statistical data and citations mentioned in the article are accurate. The fact-checking API compares the content of the article with existing reliable databases to determine whether it is accurate. This allows the evaluation unit to objectively evaluate the reliability of the article. This allows the evaluation unit to objectively evaluate the reliability of the analyzed content in conjunction with a fact-checking API. Fact-checking APIs include, but are not limited to, PolitiFact and FactCheck.org. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input the fact-checking API into a generating AI and have the generating AI perform the reliability evaluation.

[0071] The detection unit can detect misinformation based on the results evaluated by the evaluation unit. For example, the detection unit can automatically detect misinformation based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit will determine that the article is unreliable. The detection unit can also automatically filter out misinformation and unreliable content based on the results evaluated by the evaluation unit. For example, if an error is detected by the fact-checking API, the detection unit will determine that the article is unreliable. This allows the detection unit to automatically filter out misinformation and unreliable content. This allows the detection unit to automatically detect misinformation based on the evaluation results. Misinformation includes, but is not limited to, false information and misleading information. Some or all of the above processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can input the results evaluated by the evaluation unit into a generating AI and have the generating AI perform misinformation detection.

[0072] The information provider can display only articles and websites that have been deemed highly reliable to children. The information provider can provide reliable information, for example, through educational portal sites and applications. For example, the information provider can display only articles and websites that have been deemed highly reliable to children. The information provider can also display only articles and websites that have been deemed highly reliable to children. The information provider can also display only articles and websites that have been deemed highly reliable to children. For example, the information provider can provide reliable information through educational portal sites and applications. This provides a safe learning environment for children by providing only highly reliable information. Highly reliable information includes, but is not limited to, fact-checked information and information based on reliable sources. Some or all of the processing described above in the information provider may be performed using AI, for example, or not using AI. For example, the information provider can input articles and websites deemed highly reliable into a generating AI and have the generating AI provide appropriate information.

[0073] The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated emotions. For example, if the user is excited, the analysis unit can perform a detailed analysis and provide more information. For example, if the user is excited, the analysis unit can perform a detailed analysis and provide more information. The analysis unit can also perform a concise analysis and provide only the essentials if the user is tired. For example, if the user is tired, the analysis unit can perform a concise analysis and provide only the essentials. The analysis unit can also prioritize analyzing reliable information and provide reassurance if the user is feeling anxious. For example, if the analysis unit prioritizes analyzing reliable information and provides reassurance if the user is feeling anxious. In this way, by adjusting the depth of the analysis according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0074] The analysis unit can prioritize the analysis of news articles and website content based on specific themes or topics. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. The analysis unit can also prioritize the analysis of health-related articles to provide reliable health information. For example, the analysis unit can prioritize the analysis of health-related articles to provide reliable health information. The analysis unit can also prioritize the analysis of environmental issues to provide up-to-date environmental information. For example, the analysis unit can prioritize the analysis of environmental issues to provide up-to-date environmental information. In this way, by prioritizing the analysis based on specific themes or topics, information suitable for children can be provided. Specific themes or topics include, but are not limited to, politics, economics, and science. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input news articles or website content into the generation AI and have the generation AI perform analysis based on specific themes or topics.

[0075] The analysis unit can improve the accuracy of its analysis by considering the past credibility of the article's author. For example, the analysis unit can refer to the credibility score of the author's past articles and prioritize the analysis of articles by authors with high credibility. The analysis unit can also consider the author's past history of disseminating misinformation and carefully analyze articles by authors with low credibility. The analysis unit can also consider the author's field of expertise and evaluate their credibility in that field to improve the accuracy of its analysis. This allows for improved accuracy of the analysis by considering the article's author's past credibility. The article's author's past credibility includes, but is not limited to, past achievements and evaluations. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past reliability data of the article's author into the generating AI and have the generating AI perform a reliability evaluation.

[0076] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is relaxed, the analysis unit can display detailed analysis results. For example, if the user is relaxed, the analysis unit can display detailed analysis results. The analysis unit can also display only the essential points concisely if the user is in a hurry. For example, if the user is anxious, the analysis unit can highlight and display reliable information. For example, if the user is anxious, the analysis unit can highlight and display reliable information. In this way, by adjusting the display method of the analysis results according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without using AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0077] The analysis unit can customize the analysis algorithm based on the language and region of the article during analysis. For example, the analysis unit applies appropriate natural language processing techniques depending on the language of the article. The analysis unit can also analyze while considering region-specific information based on the region of the article. The analysis unit can also analyze by referring to an appropriate database based on the language and region of the article. This allows for improved accuracy of the analysis by customizing the analysis algorithm based on the language and region of the article. Examples of article languages ​​and regions include, but are not limited to, Japanese, English, Asian regions, and European regions. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the language and region data of the article into a generating AI and have the generating AI perform the customization of the analysis algorithm.

[0078] The analysis unit can improve the accuracy of its analysis by considering the article's metadata (publication date, author, source, etc.) during the analysis. For example, the analysis unit can consider the article's publication date and prioritize analyzing the most recent information. The analysis unit can also evaluate the reliability of the article's author and prioritize analyzing articles by reliable authors. The analysis unit can also check the article's source and prioritize analyzing articles with reliable sources. By considering the article's metadata, the accuracy of the analysis can be improved. Article metadata includes, but is not limited to, the publication date, author, and source. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the article's metadata into a generating AI and have the generating AI perform the analysis accuracy improvement.

[0079] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is feeling anxious, the evaluation unit will prioritize evaluating reliable information. The evaluation unit can also apply detailed evaluation criteria if the user is relaxed. The evaluation unit can also apply concise evaluation criteria if the user is in a hurry. By adjusting the evaluation criteria according to the user's emotions, a more appropriate evaluation becomes possible. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 AI, for example, or without AI. For example, the evaluation unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0080] The evaluation unit can improve the reliability of its evaluations by referencing multiple databases when collaborating with the fact-checking API. For example, the evaluation unit can refer to multiple reliable databases and cross-check the evaluation results. The evaluation unit can also integrate information from different databases and perform a comprehensive evaluation. The evaluation unit can also consider the update frequency of the databases and perform evaluations based on the latest information. For example, the evaluation unit considers the update frequency of the databases and performs evaluations based on the latest information. This improves the reliability of the evaluations by referencing multiple databases. Multiple databases include, but are not limited to, academic databases and news databases. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input information from multiple databases into a generating AI and have the generating AI perform the task of improving the reliability of the evaluations.

[0081] The evaluation unit can individually assess the reliability of the sources cited in an article and calculate an overall reliability score. For example, the evaluation unit can assess the past reliability of the sources cited in an article and calculate a reliability score. The evaluation unit can also consider the specialized field of the sources and assess their reliability in that field. For example, the evaluation unit can consider the specialized field of the sources and assess their reliability in that field. The evaluation unit can also consider the frequency of information provision by the sources and adjust the reliability score. For example, the evaluation unit can consider the frequency of information provision by the sources and adjust the reliability score. In this way, an overall reliability score can be calculated by individually assessing the reliability of the sources cited in an article. Source reliability includes, but is not limited to, the reliability of the source and the number of citations. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input the reliability data of the sources cited in an article into a generating AI and have the generating AI calculate the reliability score.

[0082] The evaluation unit can estimate the user's emotions and adjust the display method of the evaluation results based on the estimated user emotions. For example, if the user is feeling anxious, the evaluation unit can highlight and display reliable information. For example, if the user is feeling anxious, the evaluation unit can highlight and display reliable information. The evaluation unit can also display detailed evaluation results if the user is relaxed. For example, if the user is relaxed, the evaluation unit can display detailed evaluation results. The evaluation unit can also display only the essential points concisely if the user is in a hurry. For example, if the user is in a hurry, the evaluation unit can display only the essential points concisely. In this way, by adjusting the display method of the evaluation results according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the evaluation unit may be performed using AI, for example, or without AI. For example, the evaluation unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0083] The evaluation unit can apply different evaluation criteria to articles based on their category (politics, economics, science, etc.) during the evaluation process. For example, the evaluation unit may evaluate political articles by referring to highly reliable databases. For example, the evaluation unit may evaluate economic articles based on the latest economic data. For example, the evaluation unit may evaluate science articles by referring to specialized databases. This allows for more appropriate evaluations by applying different evaluation criteria based on the article category. Article categories include, but are not limited to, politics, economics, and science. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input article category data into a generating AI and have the generating AI apply the evaluation criteria.

[0084] The evaluation unit can perform evaluations based on the latest information, taking into account the article's update history. For example, the evaluation unit can check the article's update history and perform evaluations based on the latest information. The evaluation unit can also evaluate fluctuations in reliability based on the update history. For example, the evaluation unit can evaluate fluctuations in reliability based on the update history. The evaluation unit can also consider the update history and check whether the latest information is reflected. For example, the evaluation unit considers the update history and checks whether the latest information is reflected. This makes it possible to perform evaluations based on the latest information by considering the article's update history. The article's update history includes, but is not limited to, the update date and time and the update content. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input the article's update history data into a generating AI and have the generating AI perform the evaluation.

[0085] The detection unit can estimate the user's emotions and adjust the misinformation detection criteria based on the estimated user emotions. For example, if the user is feeling anxious, the detection unit can apply strict detection criteria. The detection unit can also apply flexible detection criteria if the user is relaxed. The detection unit can also apply criteria to quickly detect misinformation if the user is in a hurry. By adjusting the misinformation detection criteria according to the user's emotions, more appropriate misinformation detection becomes possible. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0086] The detection unit can improve the accuracy of misinformation detection by comparing the content of the article with the results of a fact-checking API during detection. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. The detection unit can also evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. For example, the detection unit can evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. The detection unit can also perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. For example, the detection unit can perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. This improves the accuracy of misinformation detection by comparing the content of the article with the results of the fact-checking API. Fact-checking APIs include, but are not limited to, PolitiFact and FactCheck.org. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input the content of the article and the results of the fact-checking API into the generating AI, and have the generating AI perform the detection of misinformation.

[0087] The detection unit can detect misinformation by considering the context and tone of the article during detection. For example, the detection unit can analyze the context of the article and evaluate the likelihood of misinformation. The detection unit can also analyze the tone of the article to improve the accuracy of misinformation detection. The detection unit can also integrate the context and tone to perform comprehensive misinformation detection. This allows for improved accuracy in detecting misinformation by considering the context and tone of the article. The context and tone of the article include, but are not limited to, sentiment analysis and contextual analysis. Some or all of the above-described processes in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can input data on the context and tone of the article into a generating AI and have the generating AI perform misinformation detection.

[0088] The detection unit can estimate the user's emotions and adjust how misinformation is displayed based on the estimated emotions. For example, if the user is feeling anxious, the detection unit can highlight the misinformation. For example, if the user is feeling anxious, the detection unit can highlight the misinformation. The detection unit can also display a detailed explanation of the misinformation if the user is relaxed. For example, if the user is relaxed, the detection unit can display a detailed explanation of the misinformation. The detection unit can also display the misinformation concisely if the user is in a hurry. For example, if the user is in a hurry, the detection unit can display the misinformation concisely. By adjusting how misinformation is displayed according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0089] The detection unit can apply different detection algorithms to the article format (text, images, videos, etc.) during detection. For example, the detection unit can use natural language processing techniques to detect misinformation in text articles. The detection unit can also use image analysis techniques to detect misinformation in image articles. The detection unit can also use video analysis techniques to detect misinformation in video articles. By applying an appropriate detection algorithm based on the article format, the accuracy of misinformation detection can be improved. The article format includes, but is not limited to, text, images, and videos. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input article format data into a generating AI and have the generating AI perform the application of the detection algorithm.

[0090] The detection unit can improve the accuracy of misinformation detection by considering the article's related links and references during detection. For example, the detection unit can analyze the article's related links and evaluate the likelihood of misinformation. The detection unit can also check references and detect unreliable information. The detection unit can also integrate related links and references to perform comprehensive misinformation detection. By considering the article's related links and references, the accuracy of misinformation detection can be improved. Related links and references include, but are not limited to, link reliability and citation count. Some or all of the above processing in the detection unit may be performed using, for example, AI, or without AI. For example, the detection unit can input data on the article's related links and references into a generating AI and have the generating AI perform misinformation detection.

[0091] The information provider can estimate the user's emotions and adjust how the information is displayed based on the estimated emotions. For example, if the user is feeling anxious, the information provider can highlight and display reliable information. For example, if the user is feeling anxious, the information provider can highlight and display reliable information. The information provider can also display detailed information if the user is relaxed. For example, if the user is relaxed, the information provider can display detailed information. The information provider can also display only the essential points concisely if the user is in a hurry. For example, if the user is in a hurry, the information provider can display only the essential points concisely. By adjusting how the information is displayed according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 information provider may be performed using AI, for example, or without AI. For example, the service provider can input user emotion data into a generating AI and have the AI ​​perform emotion estimation.

[0092] The information provider can provide the most relevant information by referring to the user's past browsing history at the time of provision. For example, the information provider can analyze the user's past browsing history and provide relevant information. The information provider can also prioritize displaying reliable information that the user has previously viewed. The information provider can also predict and provide information that the user might be interested in based on their browsing history. This allows the information provider to provide more relevant information by referring to the user's past browsing history. The user's past browsing history includes, but is not limited to, the date and time of browsing and the content of browsing. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's past browsing history data into a generating AI and have the generating AI perform the task of providing the most relevant information.

[0093] The information provider can adjust the difficulty level of the information based on the user's age and grade level when providing it. For example, the provider can provide information that is easy to understand according to the user's age. The provider can also provide information of an appropriate difficulty level based on the user's grade level. The provider can also add explanations of technical terms according to the user's age and grade level. By adjusting the difficulty level of the information according to the user's age and grade level, it becomes possible to provide more appropriate information. The user's age and grade level include, but are not limited to, age groups and grade-specific information. Some or all of the above processing in the information provider may be performed using, for example, AI, or not using AI. For example, the provider can input user age and grade level data into a generating AI and have the generating AI perform the information difficulty level adjustment.

[0094] The information provider can estimate the user's emotions and determine the priority of the information to be provided based on the estimated emotions. For example, if the user is feeling anxious, the information provider can prioritize providing reliable information. For example, if the user is feeling anxious, the information provider can prioritize providing reliable information. The information provider can also prioritize providing detailed information if the user is relaxed. For example, if the user is relaxed, the information provider can prioritize providing detailed information. The information provider can also prioritize providing only the essentials if the user is in a hurry. For example, if the user is in a hurry, the information provider can prioritize providing only the essentials. This allows for more appropriate information to be provided by determining the priority of the information to be provided according to the user's emotions. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 information provider may be performed using AI, for example, or without AI. For example, the service provider can input user emotion data into a generating AI and have the AI ​​perform emotion estimation.

[0095] The service provider can select the optimal display method at the time of delivery, taking into account the user's device information (PC, smartphone, tablet, etc.). For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. For example, if the user is using a smartphone, the service provider can provide a display method that matches the screen size. The service provider can also provide a display method optimized for a larger screen if the user is using a tablet. For example, if the user is using a PC, the service provider can display detailed information. For example, if the user is using a PC, the service provider can display detailed information. This makes it possible to provide more appropriate information by selecting the optimal display method based on the user's device information. User device information includes, but is not limited to, PCs, smartphones, and tablets. Some or all of the above processing in the service provider may be performed using, for example, AI, or not using AI. For example, the service provider can input the user's device information into a generating AI and have the generating AI select the optimal display method.

[0096] The service provider can provide additional relevant information based on the user's interests at the time of delivery. For example, the service provider can analyze the user's past browsing history and provide additional relevant information. The service provider can also provide information on topics that the user might be interested in. The service provider can also suggest relevant news articles and websites based on the user's interests. This enables more appropriate information delivery by providing additional relevant information based on the user's interests. User interests include, but are not limited to, survey results and past browsing history. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input user interest data into a generating AI and have the generating AI provide the additional relevant information.

[0097] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0098] The analysis unit can prioritize the analysis of news articles and website content based on specific themes or topics. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. For example, the analysis unit can prioritize the analysis of education-related articles to provide information suitable for children. The analysis unit can also prioritize the analysis of health-related articles to provide reliable health information. For example, the analysis unit can prioritize the analysis of health-related articles to provide reliable health information. The analysis unit can also prioritize the analysis of environmental issues to provide up-to-date environmental information. For example, the analysis unit can prioritize the analysis of environmental issues to provide up-to-date environmental information. In this way, by prioritizing the analysis based on specific themes or topics, information suitable for children can be provided. Specific themes or topics include, but are not limited to, politics, economics, and science. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input news articles or website content into the generation AI and have the generation AI perform analysis based on specific themes or topics.

[0099] The analysis unit can improve the accuracy of its analysis by considering the past credibility of the article's author. For example, the analysis unit can refer to the credibility score of the author's past articles and prioritize the analysis of articles by authors with high credibility. The analysis unit can also consider the author's past history of disseminating misinformation and carefully analyze articles by authors with low credibility. The analysis unit can also consider the author's field of expertise and evaluate their credibility in that field to improve the accuracy of its analysis. This allows for improved accuracy of the analysis by considering the article's author's past credibility. The article's author's past credibility includes, but is not limited to, past achievements and evaluations. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input past reliability data of the article's author into the generating AI and have the generating AI perform a reliability evaluation.

[0100] The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated emotions. For example, if the user is excited, the analysis unit can perform a detailed analysis and provide more information. For example, if the user is excited, the analysis unit can perform a detailed analysis and provide more information. The analysis unit can also perform a concise analysis and provide only the essentials if the user is tired. For example, if the user is tired, the analysis unit can perform a concise analysis and provide only the essentials. The analysis unit can also prioritize analyzing reliable information and provide reassurance if the user is feeling anxious. For example, if the analysis unit prioritizes analyzing reliable information and provides reassurance if the user is feeling anxious. In this way, by adjusting the depth of the analysis according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0101] The evaluation unit can improve the reliability of its evaluations by referencing multiple databases when collaborating with the fact-checking API. For example, the evaluation unit can refer to multiple reliable databases and cross-check the evaluation results. The evaluation unit can also integrate information from different databases and perform a comprehensive evaluation. The evaluation unit can also consider the update frequency of the databases and perform evaluations based on the latest information. For example, the evaluation unit considers the update frequency of the databases and performs evaluations based on the latest information. This improves the reliability of the evaluations by referencing multiple databases. Multiple databases include, but are not limited to, academic databases and news databases. Some or all of the above processing in the evaluation unit may be performed using, for example, AI, or not using AI. For example, the evaluation unit can input information from multiple databases into a generating AI and have the generating AI perform the task of improving the reliability of the evaluations.

[0102] The evaluation unit can estimate the user's emotions and adjust the evaluation criteria based on the estimated emotions. For example, if the user is feeling anxious, the evaluation unit will prioritize evaluating reliable information. The evaluation unit can also apply detailed evaluation criteria if the user is relaxed. The evaluation unit can also apply concise evaluation criteria if the user is in a hurry. By adjusting the evaluation criteria according to the user's emotions, a more appropriate evaluation becomes possible. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 AI, for example, or without AI. For example, the evaluation unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0103] The detection unit can improve the accuracy of misinformation detection by comparing the content of the article with the results of a fact-checking API during detection. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. For example, the detection unit can detect misinformation by comparing the content of the article with a fact-checking API. The detection unit can also evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. For example, the detection unit can evaluate the reliability of the article based on the results of the fact-checking API and detect misinformation. The detection unit can also perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. For example, the detection unit can perform comprehensive misinformation detection by integrating the content of the article with the results of the fact-checking API. This improves the accuracy of misinformation detection by comparing the content of the article with the results of the fact-checking API. Fact-checking APIs include, but are not limited to, PolitiFact and FactCheck.org. Some or all of the above processing in the detection unit may be performed using, for example, AI, or not using AI. For example, the detection unit can input the content of the article and the results of the fact-checking API into the generating AI, and have the generating AI perform the detection of misinformation.

[0104] The detection unit can estimate the user's emotions and adjust the misinformation detection criteria based on the estimated user emotions. For example, if the user is feeling anxious, the detection unit can apply strict detection criteria. The detection unit can also apply flexible detection criteria if the user is relaxed. The detection unit can also apply criteria to quickly detect misinformation if the user is in a hurry. By adjusting the misinformation detection criteria according to the user's emotions, more appropriate misinformation detection becomes possible. The estimation of the user's emotions is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. 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 detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input user emotion data into a generating AI and have the generating AI perform emotion estimation.

[0105] The information provider can estimate the user's emotions and adjust how the information is displayed based on the estimated emotions. For example, if the user is feeling anxious, the information provider can highlight and display reliable information. For example, if the user is feeling anxious, the information provider can highlight and display reliable information. The information provider can also display detailed information if the user is relaxed. For example, if the user is relaxed, the information provider can display detailed information. The information provider can also display only the essential points concisely if the user is in a hurry. For example, if the user is in a hurry, the information provider can display only the essential points concisely. By adjusting how the information is displayed according to the user's emotions, more appropriate information can be provided. The estimation of the user's emotions is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative 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 information provider may be performed using AI, for example, or without AI. For example, the service provider can input user emotion data into a generating AI and have the AI ​​perform emotion estimation.

[0106] The information provider can provide the most relevant information by referring to the user's past browsing history at the time of provision. For example, the information provider can analyze the user's past browsing history and provide relevant information. The information provider can also prioritize displaying reliable information that the user has previously viewed. The information provider can also predict and provide information that the user might be interested in based on their browsing history. This allows the information provider to provide more relevant information by referring to the user's past browsing history. The user's past browsing history includes, but is not limited to, the date and time of browsing and the content of browsing. Some or all of the above processing in the information provider may be performed using AI, for example, or without AI. For example, the information provider can input the user's past browsing history data into a generating AI and have the generating AI perform the task of providing the most relevant information.

[0107] The information provider can adjust the difficulty level of the information based on the user's age and grade level when providing it. For example, the provider can provide information that is easy to understand according to the user's age. The provider can also provide information of an appropriate difficulty level based on the user's grade level. The provider can also add explanations of technical terms according to the user's age and grade level. By adjusting the difficulty level of the information according to the user's age and grade level, it becomes possible to provide more appropriate information. The user's age and grade level include, but are not limited to, age groups and grade-specific information. Some or all of the above processing in the information provider may be performed using, for example, AI, or not using AI. For example, the provider can input user age and grade level data into a generating AI and have the generating AI perform the information difficulty level adjustment.

[0108] The following briefly describes the processing flow for example form 2.

[0109] Step 1: The analysis unit analyzes the content of news articles and websites. The analysis unit uses natural language processing technology to perform morphological analysis, grammatical analysis, and semantic analysis to extract important information and keywords from the article and understand its grammatical structure and meaning. Step 2: The evaluation unit assesses the reliability of the content analyzed by the analysis unit. The evaluation unit works in conjunction with the fact-checking API to verify the accuracy of the statistical data and citations mentioned in the article, and objectively evaluates the reliability of the article. Step 3: The detection unit detects misinformation based on the results evaluated by the evaluation unit. If an error is detected by the fact-checking API, the detection unit determines that the article is unreliable and automatically filters out misinformation and unreliable content. Step 4: The provider unit provides appropriate information based on the misinformation detected by the detection unit. The provider unit displays only articles and websites that have been rated as highly reliable and provides reliable information through educational portal sites and applications.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] Each of the multiple elements described above, including the analysis unit, evaluation unit, detection unit, and provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart device 14 and analyzes the content of news articles and websites using natural language processing technology. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the reliability of the analyzed content in cooperation with a fact-checking API. The detection unit is implemented by the control unit 46A of the smart device 14 and automatically detects misinformation based on the evaluation results. The provision unit is implemented by the identification processing unit 290 of the data processing unit 12 and displays only articles and websites that have been evaluated as highly reliable to children. The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0114] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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).

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.).

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the analysis unit, evaluation unit, detection unit, and provision unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the smart glasses 214 and analyzes the content of news articles and websites using natural language processing technology. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the reliability of the analyzed content in cooperation with a fact-checking API. The detection unit is implemented by the control unit 46A of the smart glasses 214 and automatically detects misinformation based on the evaluation results. The provision unit is implemented by the identification processing unit 290 of the data processing unit 12 and displays only articles and websites that have been evaluated as highly reliable to children. The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0130] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the analysis unit, evaluation unit, detection unit, and provision unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the headset terminal 314 and analyzes the content of news articles and websites using natural language processing technology. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the reliability of the analyzed content in cooperation with a fact-checking API. The detection unit is implemented by the control unit 46A of the headset terminal 314 and automatically detects misinformation based on the evaluation results. The provision unit is implemented by the identification processing unit 290 of the data processing unit 12 and displays only articles and websites that have been evaluated as highly reliable to children. The analysis unit can estimate the user's emotions and adjust the depth of analysis based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0146] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] Each of the multiple elements described above, including the analysis unit, evaluation unit, detection unit, and provision unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the analysis unit is implemented by the processor 46 of the robot 414 and analyzes the content of news articles and websites using natural language processing technology. The evaluation unit is implemented by the identification processing unit 290 of the data processing unit 12 and evaluates the reliability of the analyzed content in cooperation with a fact-checking API. The detection unit is implemented by the control unit 46A of the robot 414 and automatically detects misinformation based on the evaluation results. The provision unit is implemented by the identification processing unit 290 of the data processing unit 12 and displays only articles and websites that have been evaluated as highly reliable to children. The analysis unit can estimate the user's emotions and adjust the depth of the analysis based on the estimated emotions. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be modified in various ways.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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."

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] (Note 1) The analysis department analyzes the content of news articles and websites, An evaluation unit that evaluates the reliability of the content analyzed by the analysis unit, A detection unit that detects misinformation based on the results evaluated by the evaluation unit, The system includes a providing unit that provides appropriate information based on the erroneous information detected by the detection unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Analyze news articles and website content using natural language processing technology. The system described in Appendix 1, characterized by the features described herein. (Note 3) The evaluation unit, Evaluate the reliability of the analyzed content in conjunction with the fact-checking API. The system described in Appendix 1, characterized by the features described herein. (Note 4) The detection unit is Detect misinformation based on the results evaluated by the evaluation unit. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned supply unit is, Only articles and websites that have been rated as highly reliable will be displayed to children. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned analysis unit, It estimates the user's emotions and adjusts the depth of the analysis based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned analysis unit, When analyzing news articles and website content, prioritize the analysis based on specific themes or topics. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by considering the past credibility of the article's author. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned analysis unit, During analysis, the analysis algorithm is customized based on the language and region of the article. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned analysis unit, During analysis, consider the article's metadata to improve the accuracy of the analysis. The system described in Appendix 1, characterized by the features described herein. (Note 12) The evaluation unit, It estimates the user's emotions and adjusts the evaluation criteria based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The evaluation unit, When integrating with fact-checking APIs, referencing multiple databases improves the reliability of the evaluation. The system described in Appendix 1, characterized by the features described herein. (Note 14) The evaluation unit, During the evaluation process, the reliability of the sources cited in the article is assessed individually, and an overall reliability score is calculated. The system described in Appendix 1, characterized by the features described herein. (Note 15) The evaluation unit, The system estimates the user's emotions and adjusts how the evaluation results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The evaluation unit, When evaluating, different evaluation criteria are applied based on the article's category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The evaluation unit, When evaluating an article, the article's update history will be taken into consideration, and the evaluation will be based on the latest information. The system described in Appendix 1, characterized by the features described herein. (Note 18) The detection unit is The system estimates the user's emotions and adjusts the misinformation detection criteria based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The detection unit is When misinformation is detected, the content of the article is compared with the results of the fact-checking API to improve the accuracy of misinformation detection. The system described in Appendix 1, characterized by the features described herein. (Note 20) The detection unit is During detection, the context and tone of the article are taken into consideration when detecting misinformation. The system described in Appendix 1, characterized by the features described herein. (Note 21) The detection unit is It estimates the user's emotions and adjusts how misinformation is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The detection unit is When detecting an article, a different detection algorithm is applied based on the article's format. The system described in Appendix 1, characterized by the features described herein. (Note 23) The detection unit is When detecting misinformation, the accuracy of the detection process is improved by considering related links and references in the article. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned supply unit is, It estimates the user's emotions and adjusts how information is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned supply unit is, When providing information, we refer to the user's past browsing history to provide the most relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned supply unit is, When providing the content, the difficulty level of the information will be adjusted based on the user's age and grade level. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned supply unit is, It estimates the user's emotions and prioritizes the information provided based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned supply unit is, When providing the service, the optimal display method is selected considering the user's device information. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned supply unit is, When providing the service, we will provide additional relevant information based on the user's interests. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0182] 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. The analysis department analyzes the content of news articles and websites, An evaluation unit that evaluates the reliability of the content analyzed by the analysis unit, A detection unit that detects misinformation based on the results evaluated by the evaluation unit, The system includes a providing unit that provides appropriate information based on the erroneous information detected by the detection unit. A system characterized by the following features.

2. The aforementioned analysis unit, Analyze news articles and website content using natural language processing technology. The system according to feature 1.

3. The evaluation unit, Evaluate the reliability of the analyzed content in conjunction with the fact-checking API. The system according to feature 1.

4. The detection unit is False information is detected based on the results evaluated by the evaluation unit. The system according to feature 1.

5. The aforementioned supply unit is, Only articles and websites that have been rated as highly reliable will be displayed to children. The system according to feature 1.

6. The aforementioned analysis unit, It estimates the user's emotions and adjusts the depth of the analysis based on the estimated user emotions. The system according to feature 1.

7. The aforementioned analysis unit, When analyzing news articles and website content, prioritize the analysis based on specific themes or topics. The system according to feature 1.

8. The aforementioned analysis unit, During analysis, the accuracy of the analysis is improved by considering the past credibility of the article's author. The system according to feature 1.

9. The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system according to feature 1.

10. The aforementioned analysis unit, During analysis, the analysis algorithm is customized based on the language and region of the article. The system according to feature 1.

Images