System

Abstract

An object of the system according to the embodiment is to identify exaggeration and bias included in the content of a news article and present advice for checking true information.SOLUTION: A system includes a news article analysis unit, an exaggeration detection unit, an advice presentation unit, and an image analysis unit. The news article analysis unit analyzes the content of the news article. The exaggeration detection unit identifies an exaggerated or biased portion from the content of the news article analyzed by the news article analysis unit. The advice presentation unit presents advice for confirming true information with respect to the exaggerated or biased information specified by the exaggeration detection unit. The image analysis unit analyzes an image posted in the news article.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to identify exaggerations or bias in news articles and verify the truth of the information.

[0005] The system according to the embodiment aims to identify exaggerations and biases contained in the content of news articles and provide advice on how to verify the truth of the information. [Means for solving the problem]

[0006] The system according to the embodiment includes a news article analysis unit, an exaggeration detection unit, an advice presentation unit, and an image analysis unit. The news article analysis unit analyzes the content of a news article. The exaggeration detection unit identifies exaggerated or biased parts from the content of the news article analyzed by the news article analysis unit. The advice presentation unit presents advice to confirm the truth of the exaggerated or biased information identified by the exaggeration detection unit. The image analysis unit analyzes images included in the news article. [Effects of the Invention]

[0007] The system according to the embodiment can identify exaggerations and biases contained in the content of news articles and provide advice on how to verify the truth of the information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

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

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

[0028] (Example 1) A news article analysis system according to an embodiment of the present invention analyzes the content of news articles using a generative AI and Gemini, extracts exaggerated or biased sentences and images, and provides advice on how to confirm the truth of the information. This allows the news article analysis system to accurately grasp the content of news articles and eliminate exaggerated or biased information.

[0029] A news article analysis system according to an embodiment includes a news article analysis unit, an exaggeration detection unit, an advice presentation unit, and an image analysis unit. The news article analysis unit analyzes the content of a news article. For example, the generation AI analyzes the text data of a news article to identify exaggerated or biased parts. The generation AI can also accurately identify possible exaggerations or biases by considering the author's past writing habits and background information. The generation AI can also understand the background of exaggerations or biases by referring to the publication date of the news article and related social and political events. The exaggeration detection unit identifies exaggerated or biased parts from the content of the news article analyzed by the news article analysis unit. For example, the generation AI compares the news article with the context and other related articles to evaluate the degree of exaggeration or bias. The generation AI can also analyze reader comments and social media responses to the news article to evaluate the impact of exaggerations or biases. The generation AI can also use an emotion estimation function to identify exaggerated or biased parts of a news article and evaluate the impact of exaggerations or biases based on readers' emotional responses. The advice presentation unit provides advice to verify the truth of exaggerated or biased information identified by the exaggeration detection unit. For example, the generation AI provides a ranking of highly reliable sources, allowing users to select the most reliable source. The generation AI can also refer to related past news articles and data to help users understand the background of the information. Furthermore, the generation AI can use emotion estimation to provide advice to verify the truth of information and recommend the source that gives the user the most comfort. The image analysis unit analyzes images included in news articles. For example, Gemini can refer to the metadata of images included in news articles (such as the date and time of the photo, location, and camera settings) to evaluate the possibility of exaggeration or bias. Gemini can also compare the image's background information and other related images to evaluate the degree of exaggeration or bias. Furthermore, Gemini can use emotion estimation to analyze images included in news articles and evaluate the impact of exaggeration or bias based on readers' emotional responses.As a result, the news article analysis system according to the embodiment can accurately grasp the content of news articles and eliminate exaggerated or biased information. For example, users can make decisions based on reliable information sources and avoid overreacting to exaggerated information. Furthermore, companies and policymakers can make decisions based on true information, which is expected to reduce the stifle of innovation and risk management costs.

[0030] The news article analysis unit takes into account the past writing tendencies and background information of the news article writer, enabling it to identify the possibility of exaggeration or bias with a high degree of accuracy. For example, the generation AI retrieves the past writing tendencies of the news article writer from a database and compares them with the content of the article. For example, it identifies articles written by authors who have used a lot of emotional expressions in the past, and analyzes whether current articles show similar tendencies. The generation AI also takes into account the background information of the news article writer to identify the possibility of exaggeration or bias. For example, it evaluates the content of the article based on the writer's background and the policies of the media outlet to which they belong. In this way, by taking into account the past tendencies of the news article writer, the accuracy of detecting exaggeration and bias is improved.

[0031] The news article analysis unit can understand the background of exaggeration and bias by referring to the publication date of a news article and related social and political events. For example, the generation AI analyzes the publication date of a news article and refers to social and political events that occurred during that period. For example, it detects election-related bias in articles published during election periods. The generation AI also evaluates the content of an article based on the publication date of the news article and related events. For example, it analyzes the impact of events such as demonstrations and international conferences on the article. This makes it possible to understand the background of exaggeration and bias by taking into account the publication date of a news article and related events.

[0032] The news article analysis unit simultaneously analyzes multimodal information, including audio and video data, improving the accuracy of detecting exaggeration and bias. For example, the generative AI in the news article analysis unit analyzes audio and video data in addition to the text data of news articles. For example, it analyzes the tone of voice and facial expressions in news videos to identify the possibility of exaggeration or bias. The generative AI also evaluates the content of articles based on audio and video data. For example, it analyzes the tone and speed of voice, and facial expressions and movements in videos to evaluate the impact of exaggeration or bias. This improves the accuracy of detecting exaggeration and bias by including audio and video data in the analysis.

[0033] The news article analysis unit can simultaneously analyze news articles written in different languages ​​and identify exaggerations and bias from an international perspective. For example, the generation AI can simultaneously analyze news articles written in different languages ​​and identify exaggerations and bias from an international perspective. For example, it can compare articles about the same event in different languages ​​and identify exaggerations. The generation AI can also evaluate the content of articles based on articles in different languages. For example, it can analyze articles in different languages, such as English, Japanese, and Chinese, and evaluate the impact of exaggerations and bias. This makes it possible to identify exaggerations and bias from an international perspective by analyzing articles in different languages.

[0034] The exaggeration detection unit can evaluate the degree of exaggeration or bias by comparing the context of a news article and other related articles. The exaggeration detection unit, for example, the generation AI, analyzes the context of a news article and identifies parts that contain exaggeration or bias. For example, it understands the context of the article and identifies exaggerated expressions. The generation AI also compares it with other related articles to evaluate the degree of exaggeration or bias. For example, it compares articles on the same topic and evaluates the degree of exaggeration. This makes it possible to evaluate the degree of exaggeration or bias by comparing the context of the news article and with other articles.

[0035] The exaggeration detection unit can analyze reader comments and social media reactions to news articles to evaluate the impact of exaggeration and bias. The exaggeration detection unit, for example, the generation AI, analyzes reader comments and social media reactions to news articles to identify parts that contain exaggeration or bias. For example, it analyzes reader comments and identifies exaggerated expressions. The generation AI also evaluates the impact of exaggeration and bias based on social media reactions. For example, it analyzes reactions such as likes, shares, and comments to evaluate the impact of exaggerated expressions. In this way, the impact of exaggeration and bias can be evaluated by analyzing reader comments and social media reactions.

[0036] The exaggeration detection unit can integrate information from different media sources to improve the accuracy of detecting exaggeration and bias. For example, the generative AI integrates information from different media sources to identify exaggerated or biased parts of news articles. For example, it compares articles from different media about the same incident and identifies exaggerated expressions. The generative AI also evaluates the content of articles based on information from different media sources. For example, it integrates information from newspapers, television, online news, etc. and evaluates the impact of exaggeration and bias. In this way, by integrating information from different media sources, the accuracy of detecting exaggeration and bias is improved.

[0037] The exaggeration detection unit can identify patterns of exaggeration and bias by analyzing the past reporting trends of news article writers and media outlets. The exaggeration detection unit, for example, generative AI, analyzes the past reporting trends of news article writers and media outlets to identify parts that contain exaggeration or bias. For example, it identifies articles written by writers who have frequently exaggerated in the past and analyzes whether current articles show a similar trend. The generative AI also evaluates the content of articles based on the past reporting trends of media outlets. For example, it analyzes the reporting style and policy of media outlets to identify patterns of exaggeration and bias. This makes it possible to identify patterns of exaggeration and bias by analyzing the past reporting trends of writers and media outlets.

[0038] The advice presentation unit can provide a ranking of reliable information sources, allowing the user to select the most reliable information source. In the advice presentation unit, for example, the generation AI analyzes the content of news articles and provides a ranking of reliable information sources. For example, the generation AI scores reliable information sources and presents them in a ranking format. The generation AI also clarifies the ranking criteria so that the user can select the most reliable information source. For example, the ranking is created based on reliability scores and user ratings. In this way, by providing a ranking of reliable information sources, the user can select the most reliable information source.

[0039] The advice presentation unit can refer to related past news articles and data to enable the user to understand the background of the information. The advice presentation unit, for example, the generation AI, analyzes the content of a news article and refers to related past news articles and data. For example, it lists past news articles and presents them to the user. The generation AI also uses the data to enable the user to understand the background of the information. For example, it presents statistical data and research results to supplement the content of the article. This allows the user to understand the background of the information by referring to past news articles and data.

[0040] The advice presentation unit can provide information sources in different languages ​​to promote confirmation from an international perspective. For example, the advice presentation unit, the generation AI, analyzes the content of a news article and provides information sources in different languages. For example, it lists articles in different languages ​​about the same incident and presents them to the user. The generation AI also provides advice based on articles in different languages ​​to promote confirmation from an international perspective. For example, it analyzes articles in different languages ​​such as English, Japanese, and Chinese and presents them to the user. In this way, by providing information sources in different languages, it is possible to promote confirmation from an international perspective.

[0041] The advice presentation unit can provide information in a visually easy-to-understand format using visual notes and infographics. For example, the generation AI of the advice presentation unit analyzes the content of a news article and provides information using visual notes and infographics. For example, it visually displays important information. The generation AI also creates visual notes and infographics to make the information easier for the user to understand. For example, it provides information using diagrams, illustrations, and charts. In this way, by using visual notes and infographics, information can be provided in a visually easy-to-understand format.

[0042] The image analysis unit can evaluate the possibility of exaggeration or bias by referring to the metadata of images published in news articles (such as the date and time of the photo, location, and camera settings). The image analysis unit, for example, Gemini, analyzes the metadata of images published in news articles to evaluate the possibility of exaggeration or bias. For example, it analyzes the date and location of the photo to evaluate the credibility of the image. Gemini also evaluates the content of the image based on the camera settings. For example, it identifies exaggerated expressions when the camera settings are unnatural. This makes it possible to evaluate the possibility of exaggeration or bias by referring to the image metadata.

[0043] The image analysis unit can evaluate the degree of exaggeration or bias by comparing the background information of an image with other related images. For example, the image analysis unit, Gemini, analyzes the background information of images published in news articles to evaluate the degree of exaggeration or bias. For example, it analyzes the background information of an image to identify exaggerated expressions. Gemini also compares the image with other related images to evaluate the degree of exaggeration or bias. For example, it compares other images of the same event to evaluate the degree of exaggeration. This makes it possible to evaluate the degree of exaggeration or bias by comparing the image with background information and other images.

[0044] The image analysis unit integrates images from different media sources, improving the accuracy of detecting exaggeration and bias. For example, Gemini analyzes images from different media sources in addition to images published in news articles. For example, it compares images from different media outlets about the same incident to identify exaggerated expressions. Gemini also evaluates the content of images based on images from different media sources. For example, it integrates images from newspapers, television, online news, etc. to evaluate the impact of exaggeration and bias. This improves the accuracy of detecting exaggeration and bias by integrating images from different media sources.

[0045] The image analysis unit can analyze the editing history and traces of manipulation of an image to identify the possibility of exaggeration or bias. For example, Gemini analyzes the editing history and traces of manipulation of images published in news articles to identify the possibility of exaggeration or bias. For example, it analyzes the editing history of an image to identify exaggerated expressions. Gemini also evaluates the content of an image based on the traces of image manipulation. For example, it analyzes traces of image filtering, cropping, and compositing to evaluate the impact of exaggeration or bias. In this way, by analyzing the editing history and traces of manipulation of an image, it is possible to identify the possibility of exaggeration or bias.

[0046] The image analysis unit evaluates the degree of match between the content of an image and the text of an article, and can identify the possibility of exaggeration or bias. For example, Gemini evaluates the degree of match between the content of an image published in a news article and the text of the article, and identifies the possibility of exaggeration or bias. For example, if the content of the image does not match the text of the article, it identifies exaggeration. Gemini also evaluates the impact of exaggeration or bias based on the relevance between the content of the image and the text of the article. For example, it calculates a relevance score between the text and the image, and identifies exaggeration if the degree of match is low. This makes it possible to identify the possibility of exaggeration or bias by evaluating the degree of match between the content of an image and the text of the article.

[0047] The image analysis unit can analyze the visual elements of an image (color, composition, facial expression, etc.) and evaluate the degree of exaggeration or bias. For example, the image analysis unit, Gemini, analyzes the visual elements of images published in news articles (color, composition, facial expression, etc.) and evaluates the degree of exaggeration or bias. For example, if the color or composition is overly emphasized, it identifies exaggerated expressions. Gemini also evaluates the impact of exaggeration or bias based on the facial expressions in the image. For example, if emotional expressions are emphasized, it identifies exaggerated expressions. In this way, the degree of exaggeration or bias can be evaluated by analyzing the visual elements of an image.

[0048] The image analysis unit compares images from different media sources, improving the accuracy of detecting exaggeration and bias. For example, Gemini analyzes images from different media sources in addition to images published in news articles. For example, it compares images from different media outlets about the same incident to identify exaggerated expressions. Gemini also evaluates the content of images based on images from different media sources. For example, it compares images from newspapers, television, online news, etc. to evaluate the impact of exaggeration and bias. This improves the accuracy of detecting exaggeration and bias by comparing images from different media sources.

[0049] The image analysis unit can analyze the editing history and traces of manipulation of an image to identify the possibility of exaggeration or bias. For example, Gemini analyzes the editing history and traces of manipulation of images published in news articles to identify the possibility of exaggeration or bias. For example, it analyzes the editing history of an image to identify exaggerated expressions. Gemini also evaluates the content of an image based on the traces of image manipulation. For example, it analyzes traces of image filtering, cropping, and compositing to evaluate the impact of exaggeration or bias. In this way, by analyzing the editing history and traces of manipulation of an image, it is possible to identify the possibility of exaggeration or bias.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] When analyzing the content of a news article, the news article analysis unit can also generate a reliability score to evaluate the reliability of the article. For example, the generation AI can refer to the past reliability scores of the news article's author to evaluate the reliability of the current article. The generation AI can also evaluate the reliability of the news article's sources and references and calculate the reliability score of the entire article. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources and adjust the reliability score. This allows the news article analysis unit to evaluate the reliability of news articles and provide users with reliable information.

[0052] When analyzing the content of a news article, the news article analysis unit can also generate an influence score to evaluate the article's influence. For example, the generation AI can analyze the number of readers and shares of a news article to evaluate the article's influence. The generation AI can also analyze the frequency with which a news article is cited in other media and calculate an influence score. Furthermore, the generation AI can evaluate the extent to which the content of the news article has influenced social and political discussions and adjust the influence score. This allows the news article analysis unit to evaluate the influence of news articles and provide users with highly influential information.

[0053] When analyzing the content of a news article, the news article analysis unit can also generate a transparency score to evaluate the transparency of the article. For example, the generation AI can analyze whether the author of the news article is clearly stated and whether the source is clearly indicated, and then evaluate the transparency score. The generation AI can also evaluate how detailed the content of the news article is and calculate the transparency score. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources, and adjust the transparency score. In this way, the news article analysis unit can evaluate the transparency of the news article and provide users with highly transparent information.

[0054] When analyzing the content of a news article, the news article analysis unit can also generate a fairness score to evaluate the fairness of the article. For example, the generation AI can analyze whether the content of the news article is biased toward a particular position or opinion and evaluate the fairness score. The generation AI can also evaluate whether the news article provides multiple perspectives and calculate the fairness score. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources and adjust the fairness score. In this way, the news article analysis unit can evaluate the fairness of the news article and provide users with highly fair information.

[0055] When analyzing the content of a news article, the news article analysis unit can also generate a uniqueness score to evaluate the originality of the article. For example, the generation AI can analyze how different the content of the news article is from other news articles and evaluate the uniqueness score. The generation AI can also evaluate whether the news article provides new information or perspectives and calculate the uniqueness score. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources and adjust the uniqueness score. In this way, the news article analysis unit can evaluate the uniqueness of the news article and provide users with highly original information.

[0056] The processing flow of the first embodiment will be briefly explained below.

[0057] Step 1: The news article analysis unit analyzes the content of the news article. For example, the generative AI analyzes the text data of a news article to identify parts that contain exaggeration or bias. It can also take into account the past writing habits and background information of the news article's author to accurately identify possible exaggeration or bias. It can also refer to the publication date of the news article and related social and political events to understand the background to the exaggeration or bias. Step 2: The exaggeration detection unit identifies exaggerated or biased parts of the news article content analyzed by the news article analysis unit. For example, the generative AI evaluates the degree of exaggeration or bias by comparing the news article context and other related articles. It can also analyze reader comments and social media reactions to the news article to evaluate the impact of exaggeration or bias. Furthermore, it can use the emotion estimation function to identify exaggerated or biased parts of the news article and evaluate the impact of exaggeration or bias based on readers' emotional reactions. Step 3: The advice presentation unit provides advice to confirm the truth of the exaggerated or biased information identified by the exaggeration detection unit. For example, the generation AI can provide a ranking of highly reliable sources to allow the user to select the most reliable source. It can also refer to related past news articles and data to help the user understand the background of the information. Furthermore, it can use emotion estimation to provide advice to confirm the truth of the information and recommend the source that gives the user the most comfort. Step 4: The image analysis unit analyzes images featured in news articles. For example, Gemini can refer to the metadata of images featured in news articles (such as the date and time of the photo, location, and camera settings) to assess the possibility of exaggeration or bias. It can also compare the image's background information and other related images to assess the degree of exaggeration or bias. Furthermore, it can use emotion estimation to analyze images featured in news articles and assess the impact of exaggeration or bias based on readers' emotional responses.

[0058] (Example 2) A news article analysis system according to an embodiment of the present invention analyzes the content of news articles using a generative AI and Gemini, extracts exaggerated or biased sentences and images, and provides advice on how to confirm the truth of the information. This allows the news article analysis system to accurately grasp the content of news articles and eliminate exaggerated or biased information.

[0059] A news article analysis system according to an embodiment includes a news article analysis unit, an exaggeration detection unit, an advice presentation unit, and an image analysis unit. The news article analysis unit analyzes the content of a news article. For example, the generation AI analyzes the text data of a news article to identify exaggerated or biased parts. The generation AI can also accurately identify possible exaggerations or biases by considering the author's past writing habits and background information. The generation AI can also understand the background of exaggerations or biases by referring to the publication date of the news article and related social and political events. The exaggeration detection unit identifies exaggerated or biased parts from the content of the news article analyzed by the news article analysis unit. For example, the generation AI compares the news article with the context and other related articles to evaluate the degree of exaggeration or bias. The generation AI can also analyze reader comments and social media responses to the news article to evaluate the impact of exaggerations or biases. The generation AI can also use an emotion estimation function to identify exaggerated or biased parts of a news article and evaluate the impact of exaggerations or biases based on readers' emotional responses. The advice presentation unit provides advice to verify the truth of exaggerated or biased information identified by the exaggeration detection unit. For example, the generation AI provides a ranking of highly reliable sources, allowing users to select the most reliable source. The generation AI can also refer to related past news articles and data to help users understand the background of the information. Furthermore, the generation AI can use emotion estimation to provide advice to verify the truth of information and recommend the source that gives the user the most comfort. The image analysis unit analyzes images included in news articles. For example, Gemini can refer to the metadata of images included in news articles (such as the date and time of the photo, location, and camera settings) to evaluate the possibility of exaggeration or bias. Gemini can also compare the image's background information and other related images to evaluate the degree of exaggeration or bias. Furthermore, Gemini can use emotion estimation to analyze images included in news articles and evaluate the impact of exaggeration or bias based on readers' emotional responses.As a result, the news article analysis system according to the embodiment can accurately grasp the content of news articles and eliminate exaggerated or biased information. For example, users can make decisions based on reliable information sources and avoid overreacting to exaggerated information. Furthermore, companies and policymakers can make decisions based on true information, which is expected to reduce the stifle of innovation and risk management costs.

[0060] The news article analysis unit takes into account the past writing tendencies and background information of the news article writer, enabling it to identify the possibility of exaggeration or bias with a high degree of accuracy. For example, the generation AI retrieves the past writing tendencies of the news article writer from a database and compares them with the content of the article. For example, it identifies articles written by authors who have used a lot of emotional expressions in the past, and analyzes whether current articles show similar tendencies. The generation AI also takes into account the background information of the news article writer to identify the possibility of exaggeration or bias. For example, it evaluates the content of the article based on the writer's background and the policies of the media outlet to which they belong. In this way, by taking into account the past tendencies of the news article writer, the accuracy of detecting exaggeration and bias is improved.

[0061] The news article analysis unit can understand the background of exaggeration and bias by referring to the publication date of a news article and related social and political events. For example, the generation AI analyzes the publication date of a news article and refers to social and political events that occurred during that period. For example, it detects election-related bias in articles published during election periods. The generation AI also evaluates the content of an article based on the publication date of the news article and related events. For example, it analyzes the impact of events such as demonstrations and international conferences on the article. This makes it possible to understand the background of exaggeration and bias by taking into account the publication date of a news article and related events.

[0062] The news article analysis unit uses the emotion estimation function to analyze the content of a news article, predict the reader's emotional response, and evaluate the impact of exaggeration or bias. The news article analysis unit, for example, the generation AI, analyzes the content of a news article and predicts the reader's emotional response using the emotion estimation function. For example, it scores the emotions (joy, anger, sadness, etc.) that the content of the article evokes in the reader. The generation AI also evaluates the impact of exaggeration or bias based on the reader's emotional response. For example, it identifies parts with high emotion scores and evaluates whether those parts are affected by exaggeration or bias. This makes it possible to predict the reader's emotional response and evaluate the impact of exaggeration or bias.

[0063] The news article analysis unit simultaneously analyzes multimodal information, including audio and video data, improving the accuracy of detecting exaggeration and bias. For example, the generative AI in the news article analysis unit analyzes audio and video data in addition to the text data of news articles. For example, it analyzes the tone of voice and facial expressions in news videos to identify the possibility of exaggeration or bias. The generative AI also evaluates the content of articles based on audio and video data. For example, it analyzes the tone and speed of voice, and facial expressions and movements in videos to evaluate the impact of exaggeration or bias. This improves the accuracy of detecting exaggeration and bias by including audio and video data in the analysis.

[0064] The news article analysis unit can simultaneously analyze news articles written in different languages ​​and identify exaggerations and bias from an international perspective. For example, the generation AI can simultaneously analyze news articles written in different languages ​​and identify exaggerations and bias from an international perspective. For example, it can compare articles about the same event in different languages ​​and identify exaggerations. The generation AI can also evaluate the content of articles based on articles in different languages. For example, it can analyze articles in different languages, such as English, Japanese, and Chinese, and evaluate the impact of exaggerations and bias. This makes it possible to identify exaggerations and bias from an international perspective by analyzing articles in different languages.

[0065] The news article analysis unit uses the emotion estimation function to analyze the content of news articles and prioritize displaying articles that evoke the most positive emotions in readers. The news article analysis unit, for example, the generation AI, analyzes the content of news articles and uses the emotion estimation function to prioritize displaying articles that evoke the most positive emotions in readers. For example, articles with high emotion scores are prioritized. The generation AI also determines the order in which articles are displayed based on the reader's emotional response. For example, articles that evoke positive emotions are displayed at the top, and articles that evoke negative emotions are displayed at the bottom. This prioritizes displaying articles that evoke the most positive emotions in readers, thereby improving reader satisfaction.

[0066] The exaggeration detection unit can evaluate the degree of exaggeration or bias by comparing the context of a news article and other related articles. The exaggeration detection unit, for example, the generation AI, analyzes the context of a news article and identifies parts that contain exaggeration or bias. For example, it understands the context of the article and identifies exaggerated expressions. The generation AI also compares it with other related articles to evaluate the degree of exaggeration or bias. For example, it compares articles on the same topic and evaluates the degree of exaggeration. This makes it possible to evaluate the degree of exaggeration or bias by comparing the context of the news article and with other articles.

[0067] The exaggeration detection unit can analyze reader comments and social media reactions to news articles to evaluate the impact of exaggeration and bias. The exaggeration detection unit, for example, the generation AI, analyzes reader comments and social media reactions to news articles to identify parts that contain exaggeration or bias. For example, it analyzes reader comments and identifies exaggerated expressions. The generation AI also evaluates the impact of exaggeration and bias based on social media reactions. For example, it analyzes reactions such as likes, shares, and comments to evaluate the impact of exaggerated expressions. In this way, the impact of exaggeration and bias can be evaluated by analyzing reader comments and social media reactions.

[0068] The exaggeration detection unit uses the emotion estimation function to identify parts of a news article that contain exaggeration or bias, and can evaluate the impact of the exaggeration or bias based on the reader's emotional response. For example, the generative AI analyzes the content of a news article and uses the emotion estimation function to identify parts that contain exaggeration or bias. For example, it identifies parts that contain a lot of emotional expressions. The generative AI also evaluates the impact of exaggeration or bias based on the reader's emotional response. For example, it identifies parts with high emotion scores and evaluates whether those parts are affected by exaggeration or bias. In this way, the emotion estimation function can be used to evaluate the impact of exaggeration or bias based on the reader's emotional response.

[0069] The exaggeration detection unit can integrate information from different media sources to improve the accuracy of detecting exaggeration and bias. For example, the generative AI integrates information from different media sources to identify exaggerated or biased parts of news articles. For example, it compares articles from different media about the same incident and identifies exaggerated expressions. The generative AI also evaluates the content of articles based on information from different media sources. For example, it integrates information from newspapers, television, online news, etc. and evaluates the impact of exaggeration and bias. In this way, by integrating information from different media sources, the accuracy of detecting exaggeration and bias is improved.

[0070] The exaggeration detection unit can identify patterns of exaggeration and bias by analyzing the past reporting trends of news article writers and media outlets. The exaggeration detection unit, for example, generative AI, analyzes the past reporting trends of news article writers and media outlets to identify parts that contain exaggeration or bias. For example, it identifies articles written by writers who have frequently exaggerated in the past and analyzes whether current articles show a similar trend. The generative AI also evaluates the content of articles based on the past reporting trends of media outlets. For example, it analyzes the reporting style and policy of media outlets to identify patterns of exaggeration and bias. This makes it possible to identify patterns of exaggeration and bias by analyzing the past reporting trends of writers and media outlets.

[0071] The exaggeration detection unit uses the emotion estimation function to identify exaggerated or biased parts of a news article, and can prioritize extract the parts to which readers will have the most emotional reaction. For example, the generative AI analyzes the content of a news article and uses the emotion estimation function to identify parts that are exaggerated or biased. For example, it identifies parts with a lot of emotional expression and extracts the parts to which readers will have the most emotional reaction. The generative AI also evaluates the impact of exaggeration or bias based on the reader's emotional reaction. For example, it identifies parts with a high emotion score and evaluates whether those parts are affected by exaggeration or bias. As a result, the emotion estimation function can be used to prioritize extract the parts to which readers will have the most emotional reaction.

[0072] The advice presentation unit can provide a ranking of reliable information sources, allowing the user to select the most reliable information source. In the advice presentation unit, for example, the generation AI analyzes the content of news articles and provides a ranking of reliable information sources. For example, the generation AI scores reliable information sources and presents them in a ranking format. The generation AI also clarifies the ranking criteria so that the user can select the most reliable information source. For example, the ranking is created based on reliability scores and user ratings. In this way, by providing a ranking of reliable information sources, the user can select the most reliable information source.

[0073] The advice presentation unit can refer to related past news articles and data to enable the user to understand the background of the information. The advice presentation unit, for example, the generation AI, analyzes the content of a news article and refers to related past news articles and data. For example, it lists past news articles and presents them to the user. The generation AI also uses the data to enable the user to understand the background of the information. For example, it presents statistical data and research results to supplement the content of the article. This allows the user to understand the background of the information by referring to past news articles and data.

[0074] The advice presentation unit uses the emotion estimation function to present advice for verifying true information and can recommend information sources that give the user the most sense of security. For example, the generation AI analyzes the content of a news article and presents advice for verifying true information using the emotion estimation function. For example, it preferentially recommends information sources with a high emotion score. The generation AI also provides advice based on information sources that give the user the most sense of security. For example, it presents highly reliable information sources to increase the user's sense of security. In this way, by using the emotion estimation function, it is possible to recommend information sources that give the user the most sense of security.

[0075] The advice presentation unit can provide information sources in different languages ​​to promote confirmation from an international perspective. For example, the advice presentation unit, the generation AI, analyzes the content of a news article and provides information sources in different languages. For example, it lists articles in different languages ​​about the same incident and presents them to the user. The generation AI also provides advice based on articles in different languages ​​to promote confirmation from an international perspective. For example, it analyzes articles in different languages ​​such as English, Japanese, and Chinese and presents them to the user. In this way, by providing information sources in different languages, it is possible to promote confirmation from an international perspective.

[0076] The advice presentation unit can provide information in a visually easy-to-understand format using visual notes and infographics. For example, the generation AI of the advice presentation unit analyzes the content of a news article and provides information using visual notes and infographics. For example, it visually displays important information. The generation AI also creates visual notes and infographics to make the information easier for the user to understand. For example, it provides information using diagrams, illustrations, and charts. In this way, by using visual notes and infographics, information can be provided in a visually easy-to-understand format.

[0077] The advice presentation unit uses the emotion estimation function to present advice for confirming true information, and can prioritize displaying information sources that evoke the most positive emotions in the user. For example, the generation AI of the advice presentation unit analyzes the content of a news article and presents advice for confirming true information using the emotion estimation function. For example, it prioritizes displaying information sources with high emotion scores. Furthermore, the generation AI provides advice based on information sources that evoke the most positive emotions in the user. For example, it displays information sources that evoke positive emotions at the top and information sources that evoke negative emotions at the bottom. In this way, by using the emotion estimation function, it is possible to prioritize displaying information sources that evoke the most positive emotions in the user.

[0078] The image analysis unit can evaluate the possibility of exaggeration or bias by referring to the metadata of images published in news articles (such as the date and time of the photo, location, and camera settings). The image analysis unit, for example, Gemini, analyzes the metadata of images published in news articles to evaluate the possibility of exaggeration or bias. For example, it analyzes the date and location of the photo to evaluate the credibility of the image. Gemini also evaluates the content of the image based on the camera settings. For example, it identifies exaggerated expressions when the camera settings are unnatural. This makes it possible to evaluate the possibility of exaggeration or bias by referring to the image metadata.

[0079] The image analysis unit can evaluate the degree of exaggeration or bias by comparing the background information of an image with other related images. For example, the image analysis unit, Gemini, analyzes the background information of images published in news articles to evaluate the degree of exaggeration or bias. For example, it analyzes the background information of an image to identify exaggerated expressions. Gemini also compares the image with other related images to evaluate the degree of exaggeration or bias. For example, it compares other images of the same event to evaluate the degree of exaggeration. This makes it possible to evaluate the degree of exaggeration or bias by comparing the image with background information and other images.

[0080] The image analysis unit uses the emotion estimation function to analyze images published in news articles and can evaluate the influence of exaggeration or bias based on the reader's emotional response. The image analysis unit, for example, Gemini, analyzes images published in news articles and predicts the reader's emotional response using the emotion estimation function. For example, it scores the emotion (joy, anger, sadness, etc.) that the image evokes in the reader. Gemini also evaluates the influence of exaggeration or bias based on the reader's emotional response. For example, it identifies images with high emotion scores and evaluates whether those images are influenced by exaggeration or bias. In this way, the emotion estimation function can evaluate the influence of exaggeration or bias based on the reader's emotional response.

[0081] The image analysis unit integrates images from different media sources, improving the accuracy of detecting exaggeration and bias. For example, Gemini analyzes images from different media sources in addition to images published in news articles. For example, it compares images from different media outlets about the same incident to identify exaggerated expressions. Gemini also evaluates the content of images based on images from different media sources. For example, it integrates images from newspapers, television, online news, etc. to evaluate the impact of exaggeration and bias. This improves the accuracy of detecting exaggeration and bias by integrating images from different media sources.

[0082] The image analysis unit can analyze the editing history and traces of manipulation of an image to identify the possibility of exaggeration or bias. For example, Gemini analyzes the editing history and traces of manipulation of images published in news articles to identify the possibility of exaggeration or bias. For example, it analyzes the editing history of an image to identify exaggerated expressions. Gemini also evaluates the content of an image based on the traces of image manipulation. For example, it analyzes traces of image filtering, cropping, and compositing to evaluate the impact of exaggeration or bias. In this way, by analyzing the editing history and traces of manipulation of an image, it is possible to identify the possibility of exaggeration or bias.

[0083] The image analysis unit uses the emotion estimation function to analyze images published in news articles and can preferentially extract images to which readers have the most emotional reaction. The image analysis unit, for example, Gemini, analyzes images published in news articles and uses the emotion estimation function to extract images to which readers have the most emotional reaction. For example, images with a strong emotional reaction are preferentially extracted. Gemini also determines the display order of images based on the reader's emotional reaction. For example, images with a high emotion score are displayed at the top, and images with a low emotion score are displayed at the bottom. In this way, by using the emotion estimation function, images to which readers have the most emotional reaction can be preferentially extracted.

[0084] The image analysis unit evaluates the degree of match between the content of an image and the text of an article, and can identify the possibility of exaggeration or bias. For example, Gemini evaluates the degree of match between the content of an image published in a news article and the text of the article, and identifies the possibility of exaggeration or bias. For example, if the content of the image does not match the text of the article, it identifies exaggeration. Gemini also evaluates the impact of exaggeration or bias based on the relevance between the content of the image and the text of the article. For example, it calculates a relevance score between the text and the image, and identifies exaggeration if the degree of match is low. This makes it possible to identify the possibility of exaggeration or bias by evaluating the degree of match between the content of an image and the text of the article.

[0085] The image analysis unit can analyze the visual elements of an image (color, composition, facial expression, etc.) and evaluate the degree of exaggeration or bias. For example, the image analysis unit, Gemini, analyzes the visual elements of images published in news articles (color, composition, facial expression, etc.) and evaluates the degree of exaggeration or bias. For example, if the color or composition is overly emphasized, it identifies exaggerated expressions. Gemini also evaluates the impact of exaggeration or bias based on the facial expressions in the image. For example, if emotional expressions are emphasized, it identifies exaggerated expressions. In this way, the degree of exaggeration or bias can be evaluated by analyzing the visual elements of an image.

[0086] The image analysis unit uses the emotion estimation function to identify images in news articles that are exaggerated or biased, and can evaluate the impact of the exaggeration or bias based on readers' emotional responses. The image analysis unit, for example, Gemini, analyzes images published in news articles and uses the emotion estimation function to identify images that are exaggerated or biased. For example, it identifies images that evoke strong emotional responses. Gemini also evaluates the impact of exaggeration or bias based on readers' emotional responses. For example, it identifies images with high emotion scores and evaluates whether those images are influenced by exaggeration or bias. In this way, the emotion estimation function can evaluate the impact of exaggeration or bias based on readers' emotional responses.

[0087] The image analysis unit compares images from different media sources, improving the accuracy of detecting exaggeration and bias. For example, Gemini analyzes images from different media sources in addition to images published in news articles. For example, it compares images from different media outlets about the same incident to identify exaggerated expressions. Gemini also evaluates the content of images based on images from different media sources. For example, it compares images from newspapers, television, online news, etc. to evaluate the impact of exaggeration and bias. This improves the accuracy of detecting exaggeration and bias by comparing images from different media sources.

[0088] The image analysis unit can analyze the editing history and traces of manipulation of an image to identify the possibility of exaggeration or bias. For example, Gemini analyzes the editing history and traces of manipulation of images published in news articles to identify the possibility of exaggeration or bias. For example, it analyzes the editing history of an image to identify exaggerated expressions. Gemini also evaluates the content of an image based on the traces of image manipulation. For example, it analyzes traces of image filtering, cropping, and compositing to evaluate the impact of exaggeration or bias. In this way, by analyzing the editing history and traces of manipulation of an image, it is possible to identify the possibility of exaggeration or bias.

[0089] The image analysis unit uses the emotion estimation function to identify exaggerated or biased images in news articles, and can prioritize extract images to which readers have the greatest emotional response. The image analysis unit, for example, Gemini, analyzes images published in news articles and identifies images to which exaggeration or bias is present using the emotion estimation function. For example, it identifies images that evoke strong emotional responses. Gemini also evaluates the impact of exaggeration or bias based on readers' emotional responses. For example, it identifies images with high emotion scores and evaluates whether those images are influenced by exaggeration or bias. As a result, the emotion estimation function can prioritize extracting images to which readers have the greatest emotional response.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] When analyzing the content of a news article, the news article analysis unit can also generate a reliability score to evaluate the reliability of the article. For example, the generation AI can refer to the past reliability scores of the news article's author to evaluate the reliability of the current article. The generation AI can also evaluate the reliability of the news article's sources and references and calculate the reliability score of the entire article. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources and adjust the reliability score. This allows the news article analysis unit to evaluate the reliability of news articles and provide users with reliable information.

[0092] When analyzing the content of a news article, the news article analysis unit can also generate an influence score to evaluate the article's influence. For example, the generation AI can analyze the number of readers and shares of a news article to evaluate the article's influence. The generation AI can also analyze the frequency with which a news article is cited in other media and calculate an influence score. Furthermore, the generation AI can evaluate the extent to which the content of the news article has influenced social and political discussions and adjust the influence score. This allows the news article analysis unit to evaluate the influence of news articles and provide users with highly influential information.

[0093] When analyzing the content of a news article, the news article analysis unit can also generate a transparency score to evaluate the transparency of the article. For example, the generation AI can analyze whether the author of the news article is clearly stated and whether the source is clearly indicated, and then evaluate the transparency score. The generation AI can also evaluate how detailed the content of the news article is and calculate the transparency score. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources, and adjust the transparency score. In this way, the news article analysis unit can evaluate the transparency of the news article and provide users with highly transparent information.

[0094] When analyzing the content of a news article, the news article analysis unit can also generate a fairness score to evaluate the fairness of the article. For example, the generation AI can analyze whether the content of the news article is biased toward a particular position or opinion and evaluate the fairness score. The generation AI can also evaluate whether the news article provides multiple perspectives and calculate the fairness score. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources and adjust the fairness score. In this way, the news article analysis unit can evaluate the fairness of the news article and provide users with highly fair information.

[0095] When analyzing the content of a news article, the news article analysis unit can also generate a uniqueness score to evaluate the originality of the article. For example, the generation AI can analyze how different the content of the news article is from other news articles and evaluate the uniqueness score. The generation AI can also evaluate whether the news article provides new information or perspectives and calculate the uniqueness score. Furthermore, the generation AI can check whether the content of the news article is consistent with other reliable information sources and adjust the uniqueness score. In this way, the news article analysis unit can evaluate the uniqueness of the news article and provide users with highly original information.

[0096] The news article analysis unit uses the emotion estimation function to analyze the content of a news article and evaluate the credibility of the article based on the reader's emotional response. For example, the generation AI scores the emotions (joy, anger, sadness, etc.) that the content of the news article evokes in the reader and adjusts the credibility score. The generation AI also evaluates the credibility of the article based on the reader's emotional response. For example, it identifies parts with high emotion scores and evaluates whether those parts are consistent with a reliable information source. In this way, the emotion estimation function can be used to evaluate the credibility of a news article based on the reader's emotional response.

[0097] The news article analysis unit uses the emotion estimation function to analyze the content of a news article and evaluate the article's influence based on readers' emotional reactions. For example, the generation AI scores the emotions (joy, anger, sadness, etc.) that the content of a news article evokes in readers and adjusts the influence score. The generation AI also evaluates the article's influence based on readers' emotional reactions. For example, it identifies parts with high emotion scores and evaluates the extent to which those parts have influenced social and political discussions. In this way, the emotion estimation function can be used to evaluate the influence of a news article based on readers' emotional reactions.

[0098] The news article analysis unit uses the emotion estimation function to analyze the content of a news article and evaluate the transparency of the article based on the reader's emotional response. For example, the generation AI scores the emotions (joy, anger, sadness, etc.) that the content of the news article evokes in the reader and adjusts the transparency score. The generation AI also evaluates the transparency of the article based on the reader's emotional response. For example, it identifies parts with high emotion scores and evaluates whether those parts match the citation source and references. In this way, the emotion estimation function can be used to evaluate the transparency of a news article based on the reader's emotional response.

[0099] The news article analysis unit uses the emotion estimation function to analyze the content of a news article and can evaluate the fairness of the article based on the reader's emotional response. For example, the generation AI scores the emotions (joy, anger, sadness, etc.) that the content of the news article evokes in the reader and adjusts the fairness score. The generation AI also evaluates the fairness of the article based on the reader's emotional response. For example, it identifies parts with high emotion scores and evaluates whether those parts offer multiple perspectives. In this way, the emotion estimation function can be used to evaluate the fairness of a news article based on the reader's emotional response.

[0100] The news article analysis unit uses the emotion estimation function to analyze the content of a news article and can evaluate the article's uniqueness based on the reader's emotional response. For example, the generation AI scores the emotions (joy, anger, sadness, etc.) that the content of the news article evokes in the reader and adjusts the uniqueness score. The generation AI also evaluates the article's uniqueness based on the reader's emotional response. For example, it identifies parts with high emotional scores and evaluates how different those parts are from other news articles. In this way, the emotion estimation function can be used to evaluate the uniqueness of a news article based on the reader's emotional response.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The news article analysis unit analyzes the content of the news article. For example, the generative AI analyzes the text data of a news article to identify parts that contain exaggeration or bias. It can also take into account the past writing habits and background information of the news article's author to accurately identify possible exaggeration or bias. It can also refer to the publication date of the news article and related social and political events to understand the background to the exaggeration or bias. Step 2: The exaggeration detection unit identifies exaggerated or biased parts of the news article content analyzed by the news article analysis unit. For example, the generative AI evaluates the degree of exaggeration or bias by comparing the news article context and other related articles. It can also analyze reader comments and social media reactions to the news article to evaluate the impact of exaggeration or bias. Furthermore, it can use the emotion estimation function to identify exaggerated or biased parts of the news article and evaluate the impact of exaggeration or bias based on readers' emotional reactions. Step 3: The advice presentation unit provides advice to confirm the truth of the exaggerated or biased information identified by the exaggeration detection unit. For example, the generation AI can provide a ranking of highly reliable sources to allow the user to select the most reliable source. It can also refer to related past news articles and data to help the user understand the background of the information. Furthermore, it can use emotion estimation to provide advice to confirm the truth of the information and recommend the source that gives the user the most comfort. Step 4: The image analysis unit analyzes images featured in news articles. For example, Gemini can refer to the metadata of images featured in news articles (such as the date and time of the photo, location, and camera settings) to assess the possibility of exaggeration or bias. It can also compare the image's background information and other related images to assess the degree of exaggeration or bias. Furthermore, it can use emotion estimation to analyze images featured in news articles and assess the impact of exaggeration or bias based on readers' emotional responses.

[0103] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

[0108] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0110] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0112] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0113] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0114] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0115] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0116] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0117] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0118] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0123] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0124] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0125] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0126] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0127] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0128] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0129] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0130] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0131] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0132] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0133] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 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.

[0138] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0139] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0140] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0141] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0142] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0143] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0144] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0145] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0146] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0147] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0148] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0149] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0152] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0153] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0154] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0155] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0156] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0157] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0158] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0159] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0160] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0161] 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.

[0162] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0163] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0164] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0165] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0166] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0167] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a news article analysis unit that analyzes the contents of news articles; an exaggeration detection unit that identifies exaggerated or biased parts of the content of the news article analyzed by the news article analysis unit; an advice presentation unit that presents advice to confirm true information with respect to exaggerated or biased information identified by the exaggeration detection unit; An image analysis unit that analyzes images published in news articles. A system characterized by:

2. The news article analysis unit Simultaneous analysis of multimodal information, including audio and video data, improves the accuracy of detecting exaggeration and bias.

2. The system of claim 1.

3. The exaggeration detection unit Assess the level of exaggeration and bias in news articles by comparing them with other related articles and context 2. The system of claim 1.

4. The advice presentation unit Providing a ranking of reliable sources and allowing users to select the most reliable source 2. The system of claim 1.

5. The image analysis unit Look at the metadata of images in news articles (such as date and time of capture, location, and camera settings) to assess potential exaggeration and bias 2. The system of claim 1.

6. The news article analysis unit Analyze news article content using emotion estimation to predict readers' emotional responses and assess the impact of exaggeration and bias 2. The system of claim 1.

7. The exaggeration detection unit Use sentiment estimation to identify exaggerated or biased parts of news articles and assess the impact of exaggeration or bias based on readers' emotional responses.

2. The system of claim 1.

8. The advice presentation unit Using emotion estimation, the system provides advice on verifying truthful information and recommends the source of information that users feel most comfortable with.

2. The system of claim 1.

Images