System

Abstract

An object of the system according to the embodiment is to evaluate the reliability of news or information and detect a fake news or a counterfeit video / image.SOLUTION: A system according to an embodiment includes a fake news detection unit, a counterfeit video / image detection unit, and a social media monitoring unit. The fake news detection unit evaluates the reliability of news or information using the generated AI and detects a fake news. A forged video / image detection part analyzes the feature of the video or the image by using the generated AI, and detects the traces of unnatural deformation or editing. The social media monitoring unit monitors information on social media using the generated AI, and issues a warning for suspicious information.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 technologies are not sufficient in assessing the reliability of news and information, and in detecting fake news and fabricated videos and images, so there is room for improvement.

[0005] The system according to the embodiment aims to evaluate the reliability of news and information and detect fake news and forged videos and images. [Means for solving the problem]

[0006] The system according to the embodiment comprises a fake news detection unit, a fake video / image detection unit, and a social media monitoring unit. The fake news detection unit uses a generation AI to evaluate the reliability of news and information and detect fake news. The fake video / image detection unit uses a generation AI to analyze the characteristics of videos and images and detect unnatural deformations or traces of editing. The social media monitoring unit uses a generation AI to monitor information on social media and issue warnings for suspicious information. [Effects of the Invention]

[0007] The system according to the embodiment can evaluate the reliability of news and information and detect fake news and forged videos and images. [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 non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a 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) The Truth Guard system according to an embodiment of the present invention uses generative AI to evaluate the reliability of news and information, detect fake news, analyze the characteristics of videos and images, detect unnatural deformations and traces of editing, monitor information on social media, and issue warnings for suspicious information. As a result, the Truth Guard system can realize a highly reliable information environment.

[0029] The Truth Guard system according to the embodiment includes a fake news detection unit, a fake video / image detection unit, and a social media monitoring unit. The fake news detection unit uses a generation AI to evaluate the reliability of news and information and detect fake news. For example, the generation AI checks the sources and citations of news articles and detects information from unreliable sources as fake news. The generation AI can also analyze the content of news articles and prioritize detecting articles containing emotionally extreme content. The generation AI can also refer to the past credibility history of the news article's author and prioritize detecting articles written by unreliable authors. For example, the generation AI analyzes the text data of news articles and evaluates the credibility of the source and citation. The generation AI calculates the emotional score of the article using a sentiment analysis algorithm and detects articles containing extreme content. The generation AI retrieves the author's past credibility history from a database and prioritizes detecting articles written by unreliable authors. The fake video / image detection unit uses a generation AI to analyze the characteristics of video and images and detect unnatural deformations and traces of editing. For example, generative AI can analyze the color tone and light reflection of video and images to identify unnatural deformations or edited areas. Generative AI can also analyze the metadata of video and images to detect inconsistencies in the date and time of capture or location. Generative AI can also learn the characteristics of different cameras and devices to determine whether a video was taken with a specific device. For example, generative AI can analyze video and images at the pixel level to detect signs of editing or manipulation. Generative AI can use metadata analysis algorithms to detect inconsistencies in the date and time of capture or location. Generative AI can learn the characteristics of cameras and devices to determine whether a video was taken with a specific device. The social media monitoring unit uses generative AI to monitor information on social media and issue warnings for suspicious information. For example, generative AI can analyze the content of social media posts and the poster's history and display warnings for suspicious information. Generative AI can also perform sentiment analysis of social media posts to prioritize monitoring of emotionally charged posts.Furthermore, when analyzing social media posts, the generation AI can use an emotion estimation function to detect suspicious information based on the user's emotional reactions. For example, the generation AI analyzes social media posts to detect unreliable information. The generation AI uses an emotion analysis algorithm to calculate an emotion score for the posted content and prioritize monitoring of extreme posts. The generation AI uses the emotion estimation function to analyze the user's emotional reactions and detect suspicious information. As a result, the Truth Guard system according to the embodiment can realize a highly reliable information environment. For example, by evaluating the reliability of news articles, the spread of fake news can be prevented. Furthermore, by detecting fake videos and images, the spread of visual fake information can be prevented. Furthermore, by monitoring social media, the spread of suspicious information can be detected early and a warning can be issued. This allows users to obtain reliable information and contributes to a healthier information environment.

[0030] The fake news detection unit checks the sources and citations of news articles and can detect information from unreliable sources as fake news. For example, the fake news detection unit inputs the text data of a news article into the generation AI and checks the sources and citations. For example, the generation AI evaluates the reliability of the sources and citations of a news article and detects information from unreliable sources as fake news. The generation AI can also evaluate the accuracy of the sources and citations of a news article and detect false information. The generation AI can also evaluate the consistency of the sources and citations of a news article and detect contradictory information. This allows for effective detection of fake news from unreliable sources.

[0031] The forged video / image detection unit analyzes the color tone and light reflection of the video or image to identify areas where unnatural deformation or editing has occurred. The forged video / image detection unit, for example, performs pixel-level analysis of the video or image to analyze the color tone and light reflection. For example, the generation AI analyzes the color tone and light reflection of the video or image to identify areas where unnatural deformation or editing has occurred. The generation AI can also analyze changes in the color tone and light reflection of the video or image to detect traces of editing or processing. The generation AI can also analyze inconsistencies in the color tone and light reflection of the video or image to detect traces of forgery. This allows for effective detection of video or images that have been unnaturally deformed or edited.

[0032] The social media monitoring unit can analyze the content of social media posts and the poster's history, and display warnings for suspicious information. For example, the social media monitoring unit inputs the content of social media posts into the generation AI, which then analyzes the content of the posts and the poster's history. For example, the generation AI analyzes the content of social media posts and detects unreliable information. The generation AI can also analyze the history of social media posters and prioritize monitoring information from posters who have previously spread false information. The generation AI can also analyze the consistency of social media posts and detect contradictory information. This makes it possible to effectively monitor suspicious information on social media and display warnings.

[0033] When evaluating the credibility of news articles, the fake news detection unit can refer to the past credibility history of the article's author and prioritize detecting articles written by authors with low credibility. For example, the fake news detection unit registers the past credibility history of news article authors in a database, and the generation AI evaluates credibility by referring to that data. For example, the generation AI can prioritize detecting articles written by authors who have a history of writing fake news in the past. The generation AI can also analyze the author's past credibility scores to detect articles written by authors with low credibility. The generation AI can also analyze the evaluations of the author's past articles to detect articles written by authors with low credibility. This allows for effective detection of articles written by authors with low credibility.

[0034] When evaluating the credibility of news articles, the fake news detection unit can automatically translate news articles in different languages ​​and evaluate their credibility from an international perspective. For example, the fake news detection unit automatically translates news articles into different languages, and the generation AI evaluates their credibility based on the translated data. For example, the generation AI translates news articles into multiple languages, such as English, French, and Chinese, and evaluates their credibility from an international perspective. The generation AI can also compare news articles in different languages ​​and detect unreliable information. The generation AI can also analyze the consistency of news articles in different languages ​​and detect contradictory information. This allows the credibility of news articles to be evaluated from an international perspective.

[0035] The fake news detection unit can also analyze multimedia content, including images and videos, when assessing the reliability of news articles, to detect visual fake news. For example, the fake news detection unit uses generative AI to analyze images and videos included in news articles to detect visual fake news. For example, the generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. The generative AI can also analyze the characteristics of images and videos to detect traces of forgery. The generative AI can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake news.

[0036] The forged video / image detection unit can analyze the metadata of videos and images and detect inconsistencies in the shooting date / time and location. For example, the forged video / image detection unit inputs the metadata of videos and images into the generation AI and detects inconsistencies in the shooting date / time and location. For example, the generation AI displays a warning if the date, time, or location listed in the metadata is unnatural. The generation AI can also analyze the metadata and identify inconsistencies in the shooting date / time and location. The generation AI can also analyze the consistency of the metadata and detect contradictory information. This allows for effective detection of inconsistencies in the shooting date / time and location.

[0037] The counterfeit video and image detection unit can analyze video and images by learning the characteristics of different cameras and devices and determining whether they were taken with a specific device. For example, the counterfeit video and image detection unit trains a generation AI to learn the characteristics of different cameras and devices and determine whether video and images were taken with a specific device. For example, the generation AI can make this determination based on the camera's serial number and lens characteristics. The generation AI can also analyze the characteristics of the camera or device to determine whether they were taken with a specific device. The generation AI can also analyze the consistency of the characteristics of the camera or device to detect signs of counterfeiting. This effectively determines whether they were taken with a specific device.

[0038] The fake video / image detection unit can simultaneously analyze audio data when analyzing video or images, and detect inconsistencies between audio and video. For example, when analyzing video or images, the generation AI can simultaneously analyze audio data and detect inconsistencies between audio and video. For example, the generation AI can display a warning if the timing of audio and video does not match. The generation AI can also analyze the content of audio and video to identify inconsistencies. The generation AI can also analyze the consistency between audio and video to detect contradictory information. This allows for effective detection of inconsistencies between audio and video.

[0039] When analyzing videos and images, the forged video / image detection unit can compare multiple videos and images taken from different perspectives to detect unnatural editing or manipulation. For example, when analyzing videos and images, the generation AI compares multiple videos and images taken from different perspectives to detect unnatural editing or manipulation. For example, the generation AI compares videos of the same scene taken from different angles to identify traces of editing. The generation AI can also analyze the characteristics of videos and images from different perspectives to detect traces of forgery. The generation AI can also analyze the consistency of videos and images from different perspectives to detect contradictory information. This allows for effective detection of unnatural editing or manipulation by comparing videos and images from different perspectives.

[0040] When analyzing the content of social media posts, the social media monitoring unit can refer to the poster's past reliability history and prioritize monitoring information about posters with low reliability. For example, the social media monitoring unit registers the past reliability history of social media posters in a database, and the generation AI refers to that data to evaluate reliability. For example, the generation AI prioritizes monitoring information about posters who have a history of posting fake news in the past. The generation AI can also analyze the poster's past reliability score and detect information about posters with low reliability. The generation AI can also analyze the evaluation of the poster's past post content and detect information about posters with low reliability. This allows for effective monitoring of information about posters with low reliability.

[0041] When analyzing social media posts, the social media monitoring unit can automatically translate posts in different languages ​​to monitor from an international perspective. For example, the social media monitoring unit automatically translates social media posts into different languages, and the generation AI analyzes them based on the translated data. For example, the generation AI can translate social media posts into multiple languages, such as English, French, and Chinese, to monitor from an international perspective. The generation AI can also compare posts in different languages ​​to detect unreliable information. The generation AI can also analyze the consistency of posts in different languages ​​to detect contradictory information. This enables effective monitoring of social media posts from an international perspective.

[0042] When analyzing social media posts, the social media monitoring unit can also analyze multimedia content, including images and videos, to detect visual fake information. For example, the social media monitoring unit uses generative AI to analyze images and videos included in social media posts to detect visual fake information. For example, generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. Generative AI can also analyze the characteristics of images and videos to detect traces of forgery. Generative AI can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake information.

[0043] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0044] The Truth Guard system also includes a user credibility evaluation unit. This unit can analyze a user's past behavioral history and posted content to calculate a credibility score. For example, if a user has a history of spreading false information in the past, the system can set the user's credibility score low. It can also analyze the consistency of a user's posted content and lower the credibility score if the user posts contradictory information. Furthermore, the system can perform a comprehensive credibility evaluation by taking into account the credibility of the user's followers and the accounts they follow. This allows the system to prioritize monitoring information from low-reliability users and display warnings.

[0045] The Truth Guard system also includes a news article topic classification unit. The news article topic classification unit can analyze the content of news articles and classify them into specific topics. For example, it can classify them into categories such as politics, economics, sports, and entertainment. It can also perform a credibility assessment for each topic and prioritize the detection of unreliable information in a specific topic. Furthermore, the topic classification unit can calculate a credibility score for each topic and warn of information related to unreliable topics. This can prevent the spread of fake news in a specific topic.

[0046] The Truth Guard system can also automatically translate news articles in different languages ​​to evaluate their credibility from an international perspective. For example, it can translate a news article into multiple languages, such as English, French, and Chinese, to evaluate its credibility from an international perspective. It can also compare news articles in different languages ​​to detect unreliable information. It can also analyze the consistency of news articles in different languages ​​to detect contradictory information. This allows it to evaluate the credibility of news articles from an international perspective.

[0047] The Truth Guard system can also analyze multimedia content, including images and videos, when assessing the credibility of news articles to detect visual fake news. For example, the images and videos included in news articles can be analyzed using generative AI to detect visual fake news. Generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. It can also analyze the characteristics of images and videos to detect signs of forgery. It can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake news.

[0048] The Truth Guard system can also automatically translate posts in different languages ​​when analyzing social media posts, allowing for monitoring from an international perspective. For example, social media posts can be automatically translated into different languages, and the generation AI can analyze them based on the translated data. The generation AI can translate social media posts into multiple languages, such as English, French, and Chinese, allowing for monitoring from an international perspective. It can also compare posts in different languages ​​to detect unreliable information. It can also analyze the consistency of posts in different languages ​​to detect contradictory information. This allows for effective monitoring of social media posts from an international perspective.

[0049] The Truth Guard system can also analyze multimedia content, including images and videos, in its analysis of social media posts to detect visual fake information. For example, it uses generative AI to analyze images and videos included in social media posts to detect visual fake information. Generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. It can also analyze the characteristics of images and videos to detect signs of forgery. It can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake information.

[0050] The Truth Guard system can also analyze social media posts by referencing the poster's past credibility history and prioritize monitoring information from posters with low credibility. For example, the past credibility history of social media posters can be registered in a database, and the generation AI can refer to that data to evaluate their credibility. The generation AI can prioritize monitoring information from posters who have a history of posting fake news in the past. It can also analyze the poster's past credibility score to detect information from posters with low credibility. It can also analyze the evaluation of the poster's past posts to detect information from posters with low credibility. This allows for effective monitoring of information from posters with low credibility.

[0051] The processing flow of the first embodiment will be briefly explained below.

[0052] Step 1: The fake news detection unit uses generation AI to evaluate the reliability of news and information and detect fake news. The generation AI checks the sources and citations of news articles and detects information from unreliable sources as fake news. The generation AI also analyzes the content of news articles and can prioritize detecting articles containing emotionally extreme content. Furthermore, the generation AI refers to the past reliability history of the news article's author and prioritizes detecting articles written by authors with low reliability. Step 2: The fake video and image detection unit uses generative AI to analyze the characteristics of the video and image and detect signs of unnatural deformation or editing. Generative AI analyzes the color tone and light reflection of the video and image to identify areas where unnatural deformation or editing has occurred. Generative AI can also analyze the metadata of the video and image to detect inconsistencies in the shooting date and time or location. Furthermore, generative AI can learn the characteristics of different cameras and devices and determine whether a photo was taken with a specific device. Step 3: The social media monitoring unit uses generation AI to monitor information on social media and issue warnings for suspicious information. The generation AI analyzes the content of social media posts and the poster's history, and displays warnings for suspicious information. The generation AI can also perform sentiment analysis of the content of social media posts and prioritize monitoring of emotionally extreme posts. Furthermore, the generation AI can use its emotion estimation function to detect suspicious information based on the user's emotional reactions.

[0053] (Example 2) The Truth Guard system according to an embodiment of the present invention uses generative AI to evaluate the reliability of news and information, detect fake news, analyze the characteristics of videos and images, detect unnatural deformations and traces of editing, monitor information on social media, and issue warnings for suspicious information. As a result, the Truth Guard system can realize a highly reliable information environment.

[0054] The Truth Guard system according to the embodiment includes a fake news detection unit, a fake video / image detection unit, and a social media monitoring unit. The fake news detection unit uses a generation AI to evaluate the reliability of news and information and detect fake news. For example, the generation AI checks the sources and citations of news articles and detects information from unreliable sources as fake news. The generation AI can also analyze the content of news articles and prioritize detecting articles containing emotionally extreme content. The generation AI can also refer to the past credibility history of the news article's author and prioritize detecting articles written by unreliable authors. For example, the generation AI analyzes the text data of news articles and evaluates the credibility of the source and citation. The generation AI calculates the emotional score of the article using a sentiment analysis algorithm and detects articles containing extreme content. The generation AI retrieves the author's past credibility history from a database and prioritizes detecting articles written by unreliable authors. The fake video / image detection unit uses a generation AI to analyze the characteristics of video and images and detect unnatural deformations and traces of editing. For example, generative AI can analyze the color tone and light reflection of video and images to identify unnatural deformations or edited areas. Generative AI can also analyze the metadata of video and images to detect inconsistencies in the date and time of capture or location. Generative AI can also learn the characteristics of different cameras and devices to determine whether a video was taken with a specific device. For example, generative AI can analyze video and images at the pixel level to detect signs of editing or manipulation. Generative AI can use metadata analysis algorithms to detect inconsistencies in the date and time of capture or location. Generative AI can learn the characteristics of cameras and devices to determine whether a video was taken with a specific device. The social media monitoring unit uses generative AI to monitor information on social media and issue warnings for suspicious information. For example, generative AI can analyze the content of social media posts and the poster's history and display warnings for suspicious information. Generative AI can also perform sentiment analysis of social media posts to prioritize monitoring of emotionally charged posts.Furthermore, when analyzing social media posts, the generation AI can use an emotion estimation function to detect suspicious information based on the user's emotional reactions. For example, the generation AI analyzes social media posts to detect unreliable information. The generation AI uses an emotion analysis algorithm to calculate an emotion score for the posted content and prioritize monitoring of extreme posts. The generation AI uses the emotion estimation function to analyze the user's emotional reactions and detect suspicious information. As a result, the Truth Guard system according to the embodiment can realize a highly reliable information environment. For example, by evaluating the reliability of news articles, the spread of fake news can be prevented. Furthermore, by detecting fake videos and images, the spread of visual fake information can be prevented. Furthermore, by monitoring social media, the spread of suspicious information can be detected early and a warning can be issued. This allows users to obtain reliable information and contributes to a healthier information environment.

[0055] The fake news detection unit checks the sources and citations of news articles and can detect information from unreliable sources as fake news. For example, the fake news detection unit inputs the text data of a news article into the generation AI and checks the sources and citations. For example, the generation AI evaluates the reliability of the sources and citations of a news article and detects information from unreliable sources as fake news. The generation AI can also evaluate the accuracy of the sources and citations of a news article and detect false information. The generation AI can also evaluate the consistency of the sources and citations of a news article and detect contradictory information. This allows for effective detection of fake news from unreliable sources.

[0056] The forged video / image detection unit analyzes the color tone and light reflection of the video or image to identify areas where unnatural deformation or editing has occurred. The forged video / image detection unit, for example, performs pixel-level analysis of the video or image to analyze the color tone and light reflection. For example, the generation AI analyzes the color tone and light reflection of the video or image to identify areas where unnatural deformation or editing has occurred. The generation AI can also analyze changes in the color tone and light reflection of the video or image to detect traces of editing or processing. The generation AI can also analyze inconsistencies in the color tone and light reflection of the video or image to detect traces of forgery. This allows for effective detection of video or images that have been unnaturally deformed or edited.

[0057] The social media monitoring unit can analyze the content of social media posts and the poster's history, and display warnings for suspicious information. For example, the social media monitoring unit inputs the content of social media posts into the generation AI, which then analyzes the content of the posts and the poster's history. For example, the generation AI analyzes the content of social media posts and detects unreliable information. The generation AI can also analyze the history of social media posters and prioritize monitoring information from posters who have previously spread false information. The generation AI can also analyze the consistency of social media posts and detect contradictory information. This makes it possible to effectively monitor suspicious information on social media and display warnings.

[0058] The fake news detection unit performs sentiment analysis of news articles and can prioritize detecting articles containing emotionally extreme content. For example, the fake news detection unit inputs the text data of news articles into the generation AI and performs sentiment analysis. For example, the generation AI calculates the sentiment score of the news article and prioritizes detecting articles containing emotionally extreme content. The generation AI can also analyze the emotional expressions in news articles and detect articles containing extreme content. The generation AI can also analyze the emotional tone of news articles and detect articles containing emotionally provocative content. This allows for effective detection of fake news containing emotionally extreme content.

[0059] When evaluating the credibility of news articles, the fake news detection unit can refer to the past credibility history of the article's author and prioritize detecting articles written by authors with low credibility. For example, the fake news detection unit registers the past credibility history of news article authors in a database, and the generation AI evaluates credibility by referring to that data. For example, the generation AI can prioritize detecting articles written by authors who have a history of writing fake news in the past. The generation AI can also analyze the author's past credibility scores to detect articles written by authors with low credibility. The generation AI can also analyze the evaluations of the author's past articles to detect articles written by authors with low credibility. This allows for effective detection of articles written by authors with low credibility.

[0060] The fake news detection unit cross-references the content of a news article with related social media reactions and can detect fake news based on users' emotional reactions using an emotion estimation function. For example, the fake news detection unit cross-references the content of a news article with related social media reactions using a generation AI and analyzes users' emotional reactions using an emotion estimation function. For example, the generation AI compares the content of a news article with social media reactions and prioritizes detecting articles with high emotion scores and many reactions. The generation AI can also analyze the content of a news article and the emotional reactions on social media to detect fake news that is likely to resonate emotionally. The generation AI can also analyze the content of a news article and the emotional tone of social media to detect articles that contain emotionally provocative content. This allows for effective detection of fake news based on users' emotional reactions.

[0061] When evaluating the credibility of news articles, the fake news detection unit can automatically translate news articles in different languages ​​and evaluate their credibility from an international perspective. For example, the fake news detection unit automatically translates news articles into different languages, and the generation AI evaluates their credibility based on the translated data. For example, the generation AI translates news articles into multiple languages, such as English, French, and Chinese, and evaluates their credibility from an international perspective. The generation AI can also compare news articles in different languages ​​and detect unreliable information. The generation AI can also analyze the consistency of news articles in different languages ​​and detect contradictory information. This allows the credibility of news articles to be evaluated from an international perspective.

[0062] The fake news detection unit can also analyze multimedia content, including images and videos, when assessing the reliability of news articles, to detect visual fake news. For example, the fake news detection unit uses generative AI to analyze images and videos included in news articles to detect visual fake news. For example, the generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. The generative AI can also analyze the characteristics of images and videos to detect traces of forgery. The generative AI can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake news.

[0063] When assessing the credibility of a news article, the fake news detection unit uses the emotion estimation function to monitor users' emotional reactions in real time, and can prioritize the detection of fake news that is likely to resonate emotionally. For example, when assessing the credibility of a news article, the fake news detection unit uses the emotion estimation function to monitor users' emotional reactions in real time. For example, the generation AI analyzes the content of the news article and prioritizes the detection of articles with high emotion scores. The generation AI can also analyze the emotional tone of the news article to detect fake news that is likely to resonate emotionally. The generation AI can also analyze the emotional expressions in the news article to detect articles that contain emotionally inciting content. This allows for the effective detection of fake news that is likely to resonate emotionally.

[0064] The forged video / image detection unit can analyze the metadata of videos and images and detect inconsistencies in the shooting date / time and location. For example, the forged video / image detection unit inputs the metadata of videos and images into the generation AI and detects inconsistencies in the shooting date / time and location. For example, the generation AI displays a warning if the date, time, or location listed in the metadata is unnatural. The generation AI can also analyze the metadata and identify inconsistencies in the shooting date / time and location. The generation AI can also analyze the consistency of the metadata and detect contradictory information. This allows for effective detection of inconsistencies in the shooting date / time and location.

[0065] The counterfeit video and image detection unit can analyze video and images by learning the characteristics of different cameras and devices and determining whether they were taken with a specific device. For example, the counterfeit video and image detection unit trains a generation AI to learn the characteristics of different cameras and devices and determine whether video and images were taken with a specific device. For example, the generation AI can make this determination based on the camera's serial number and lens characteristics. The generation AI can also analyze the characteristics of the camera or device to determine whether they were taken with a specific device. The generation AI can also analyze the consistency of the characteristics of the camera or device to detect signs of counterfeiting. This effectively determines whether they were taken with a specific device.

[0066] When analyzing videos and images, the fake video / image detection unit can use the emotion estimation function to detect unnatural editing or manipulation based on the viewer's emotional response. For example, when analyzing videos and images, the fake video / image detection unit uses the emotion estimation function to analyze the viewer's emotional response. For example, the generation AI prioritizes analysis of parts with high emotion scores and detects unnatural editing or manipulation. The generation AI can also analyze the viewer's emotional response and identify parts that are likely to evoke emotional empathy. The generation AI can also analyze the viewer's emotional response and detect videos and images that contain emotionally provocative content. This makes it possible to effectively detect unnatural editing or manipulation based on the viewer's emotional response.

[0067] The fake video / image detection unit can simultaneously analyze audio data when analyzing video or images, and detect inconsistencies between audio and video. For example, when analyzing video or images, the generation AI can simultaneously analyze audio data and detect inconsistencies between audio and video. For example, the generation AI can display a warning if the timing of audio and video does not match. The generation AI can also analyze the content of audio and video to identify inconsistencies. The generation AI can also analyze the consistency between audio and video to detect contradictory information. This allows for effective detection of inconsistencies between audio and video.

[0068] When analyzing videos and images, the forged video / image detection unit can compare multiple videos and images taken from different perspectives to detect unnatural editing or manipulation. For example, when analyzing videos and images, the generation AI compares multiple videos and images taken from different perspectives to detect unnatural editing or manipulation. For example, the generation AI compares videos of the same scene taken from different angles to identify traces of editing. The generation AI can also analyze the characteristics of videos and images from different perspectives to detect traces of forgery. The generation AI can also analyze the consistency of videos and images from different perspectives to detect contradictory information. This allows for effective detection of unnatural editing or manipulation by comparing videos and images from different perspectives.

[0069] When analyzing videos and images, the fake video and image detection unit uses an emotion estimation function to monitor viewers' emotional responses in real time, allowing it to prioritize the detection of fake videos and images that are likely to evoke emotional empathy. For example, when analyzing videos and images, the fake video and image detection unit uses an emotion estimation function to monitor viewers' emotional responses in real time. For example, the generation AI prioritizes the detection of videos and images with high emotion scores. The generation AI can also analyze viewers' emotional responses and identify fake videos and images that are likely to evoke emotional empathy. The generation AI can also analyze viewers' emotional tone and detect videos and images that contain emotionally provocative content. This allows for the effective detection of fake videos and images that are likely to evoke emotional empathy.

[0070] The social media monitoring unit performs sentiment analysis of social media post content and is able to prioritize monitoring of emotionally extreme posts. For example, the social media monitoring unit inputs social media post content into the generation AI and performs sentiment analysis. For example, the generation AI calculates an emotional score for the post content and prioritizes monitoring of emotionally extreme posts. The generation AI can also analyze the emotional expressions in the post content and detect extreme posts. The generation AI can also analyze the emotional tone of the post content and detect posts that contain emotionally provocative content. This enables effective monitoring of emotionally extreme posts.

[0071] When analyzing the content of social media posts, the social media monitoring unit can refer to the poster's past reliability history and prioritize monitoring information about posters with low reliability. For example, the social media monitoring unit registers the past reliability history of social media posters in a database, and the generation AI refers to that data to evaluate reliability. For example, the generation AI prioritizes monitoring information about posters who have a history of posting fake news in the past. The generation AI can also analyze the poster's past reliability score and detect information about posters with low reliability. The generation AI can also analyze the evaluation of the poster's past post content and detect information about posters with low reliability. This allows for effective monitoring of information about posters with low reliability.

[0072] When analyzing social media posts, the social media monitoring unit can use an emotion estimation function to detect suspicious information based on the user's emotional reactions. For example, the social media monitoring unit inputs the social media post content into the generation AI and analyzes the user's emotional reactions using the emotion estimation function. For example, the generation AI calculates an emotion score for the post content and prioritizes monitoring emotionally extreme posts. The generation AI can also analyze the emotional expressions in the post content to detect extreme posts. The generation AI can also analyze the emotional tone of the post content to detect posts that contain emotionally provocative content. This makes it possible to effectively detect suspicious information based on the user's emotional reactions.

[0073] When analyzing social media posts, the social media monitoring unit can automatically translate posts in different languages ​​to monitor from an international perspective. For example, the social media monitoring unit automatically translates social media posts into different languages, and the generation AI analyzes them based on the translated data. For example, the generation AI can translate social media posts into multiple languages, such as English, French, and Chinese, to monitor from an international perspective. The generation AI can also compare posts in different languages ​​to detect unreliable information. The generation AI can also analyze the consistency of posts in different languages ​​to detect contradictory information. This enables effective monitoring of social media posts from an international perspective.

[0074] When analyzing social media posts, the social media monitoring unit can also analyze multimedia content, including images and videos, to detect visual fake information. For example, the social media monitoring unit uses generative AI to analyze images and videos included in social media posts to detect visual fake information. For example, generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. Generative AI can also analyze the characteristics of images and videos to detect traces of forgery. Generative AI can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake information.

[0075] When analyzing social media posts, the social media monitoring unit uses an emotion estimation function to monitor users' emotional reactions in real time, allowing it to prioritize monitoring of suspicious information that is likely to resonate emotionally. For example, when analyzing social media posts, the social media monitoring unit uses the emotion estimation function to monitor users' emotional reactions in real time. For example, the generation AI prioritizes monitoring posts with a high emotion score. The generation AI can also analyze users' emotional reactions and identify suspicious information that is likely to resonate emotionally. The generation AI can also analyze users' emotional tone and detect posts that contain emotionally provocative content. This allows for effective monitoring of suspicious information that is likely to resonate emotionally.

[0076] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0077] The Truth Guard system also includes a user credibility evaluation unit. This unit can analyze a user's past behavioral history and posted content to calculate a credibility score. For example, if a user has a history of spreading false information in the past, the system can set the user's credibility score low. It can also analyze the consistency of a user's posted content and lower the credibility score if the user posts contradictory information. Furthermore, the system can perform a comprehensive credibility evaluation by taking into account the credibility of the user's followers and the accounts they follow. This allows the system to prioritize monitoring information from low-reliability users and display warnings.

[0078] The Truth Guard system also includes a news article topic classification unit. The news article topic classification unit can analyze the content of news articles and classify them into specific topics. For example, it can classify them into categories such as politics, economics, sports, and entertainment. It can also perform a credibility assessment for each topic and prioritize the detection of unreliable information in a specific topic. Furthermore, the topic classification unit can calculate a credibility score for each topic and warn of information related to unreliable topics. This can prevent the spread of fake news in a specific topic.

[0079] The Truth Guard system can also use user emotion estimation to evaluate the credibility of news articles. For example, it analyzes the content of a news article and evaluates its credibility based on the user's emotional response. The generative AI calculates an emotional score for each news article and prioritizes detecting articles that are likely to resonate emotionally. It can also monitor users' emotional responses in real time to detect articles that contain emotionally provocative content. Furthermore, it can analyze users' emotional tone and prioritize detecting articles that contain emotionally extreme content. This allows for effective detection of fake news that is likely to resonate emotionally.

[0080] The Truth Guard system can also automatically translate news articles in different languages ​​to evaluate their credibility from an international perspective. For example, it can translate a news article into multiple languages, such as English, French, and Chinese, to evaluate its credibility from an international perspective. It can also compare news articles in different languages ​​to detect unreliable information. It can also analyze the consistency of news articles in different languages ​​to detect contradictory information. This allows it to evaluate the credibility of news articles from an international perspective.

[0081] The Truth Guard system can also analyze multimedia content, including images and videos, when assessing the credibility of news articles to detect visual fake news. For example, the images and videos included in news articles can be analyzed using generative AI to detect visual fake news. Generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. It can also analyze the characteristics of images and videos to detect signs of forgery. It can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake news.

[0082] The Truth Guard system can also use emotion estimation to analyze social media posts and detect suspicious information based on users' emotional reactions. For example, it analyzes social media posts and calculates an emotion score. The generative AI prioritizes monitoring emotionally extreme posts. It can also analyze the emotional expressions in posts to detect extreme posts. It can also analyze the emotional tone of posts to detect posts that contain emotionally provocative content. This allows for effective detection of suspicious information based on users' emotional reactions.

[0083] The Truth Guard system can also automatically translate posts in different languages ​​when analyzing social media posts, allowing for monitoring from an international perspective. For example, social media posts can be automatically translated into different languages, and the generation AI can analyze them based on the translated data. The generation AI can translate social media posts into multiple languages, such as English, French, and Chinese, allowing for monitoring from an international perspective. It can also compare posts in different languages ​​to detect unreliable information. It can also analyze the consistency of posts in different languages ​​to detect contradictory information. This allows for effective monitoring of social media posts from an international perspective.

[0084] The Truth Guard system can also analyze multimedia content, including images and videos, in its analysis of social media posts to detect visual fake information. For example, it uses generative AI to analyze images and videos included in social media posts to detect visual fake information. Generative AI can identify traces of editing or manipulation in images and videos to detect unreliable content. It can also analyze the characteristics of images and videos to detect signs of forgery. It can also analyze the consistency of images and videos to detect contradictory information. This allows for effective detection of visual fake information.

[0085] The Truth Guard system also uses emotion estimation to monitor users' emotional reactions in real time when analyzing social media posts, allowing it to prioritize monitoring of suspicious information that is likely to resonate emotionally. For example, when analyzing social media posts, the generation AI uses emotion estimation to monitor users' emotional reactions in real time. The generation AI prioritizes monitoring posts with high emotion scores. It can also analyze users' emotional reactions to identify suspicious information that is likely to resonate emotionally. It can also analyze users' emotional tone to detect posts that contain emotionally provocative content. This allows for effective monitoring of suspicious information that is likely to resonate emotionally.

[0086] The Truth Guard system can also analyze social media posts by referencing the poster's past credibility history and prioritize monitoring information from posters with low credibility. For example, the past credibility history of social media posters can be registered in a database, and the generation AI can refer to that data to evaluate their credibility. The generation AI can prioritize monitoring information from posters who have a history of posting fake news in the past. It can also analyze the poster's past credibility score to detect information from posters with low credibility. It can also analyze the evaluation of the poster's past posts to detect information from posters with low credibility. This allows for effective monitoring of information from posters with low credibility.

[0087] The processing flow of the second embodiment will be briefly explained below.

[0088] Step 1: The fake news detection unit uses generation AI to evaluate the reliability of news and information and detect fake news. The generation AI checks the sources and citations of news articles and detects information from unreliable sources as fake news. The generation AI also analyzes the content of news articles and can prioritize detecting articles containing emotionally extreme content. Furthermore, the generation AI refers to the past reliability history of the news article's author and prioritizes detecting articles written by authors with low reliability. Step 2: The fake video and image detection unit uses generative AI to analyze the characteristics of the video and image and detect signs of unnatural deformation or editing. Generative AI analyzes the color tone and light reflection of the video and image to identify areas where unnatural deformation or editing has occurred. Generative AI can also analyze the metadata of the video and image to detect inconsistencies in the shooting date and time or location. Furthermore, generative AI can learn the characteristics of different cameras and devices and determine whether a photo was taken with a specific device. Step 3: The social media monitoring unit uses generation AI to monitor information on social media and issue warnings for suspicious information. The generation AI analyzes the content of social media posts and the poster's history, and displays warnings for suspicious information. The generation AI can also perform sentiment analysis of the content of social media posts and prioritize monitoring of emotionally extreme posts. Furthermore, the generation AI can use its emotion estimation function to detect suspicious information based on the user's emotional reactions.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0093] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] 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).

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0108] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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."

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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, in order to avoid confusion and to 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.

[0155] 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]

[0156] 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 fake news detection unit that uses generative AI to evaluate the reliability of news and information and detect fake news; A fake video / image detection unit uses generative AI to analyze the characteristics of videos and images and detect unnatural deformations and traces of editing. A social media monitoring unit that uses generation AI to monitor information on social media and issues a warning for suspicious information. A system characterized by:

2. The fake news detection unit Check the source and citation of news articles and detect information from unreliable sources as fake news.

2. The system of claim 1.

3. The forged video / image detection unit Analyzing the color tone and light reflection of the video or image, and identifying the unnatural deformation or edited portion.

2. The system of claim 1.

4. The social media monitoring unit: Analyzing the content of posts on the social media and the poster's history, and displaying the warning for any suspicious information 2. The system of claim 1.

5. The fake news detection unit In assessing the credibility of news articles, we automatically translate news articles in different languages ​​and evaluate their credibility from an international perspective.

2. The system of claim 1.

6. The forged video / image detection unit Analyzing the metadata of the video or image to detect inconsistencies in the date and time of shooting or the location of shooting 2. The system of claim 1.

7. The social media monitoring unit: Conduct sentiment analysis of the content of social media posts and prioritize monitoring of emotionally extreme posts.

2. The system of claim 1.

8. The social media monitoring unit: When analyzing the content of posts on the social media, the emotional reactions of users are monitored in real time, and the suspicious information that is likely to evoke emotional empathy is monitored with priority.

2. The system of claim 1.

Images