system

Abstract

An object of the system according to the embodiment is to efficiently detect and automatically block a fake image or a fake news uploaded on an SNS.SOLUTION: A system according to an embodiment includes a content analysis part, a fake image detection part, a fake news detection part, and a block executing part. The content analysis unit analyzes content uploaded to the SNS. The fake image detection part detects a fake image from the content analyzed by the content analysis part. The fake news detection unit detects fake news from the content analyzed by the content analysis unit. The blocking executing part automatically blocks the fake content detected by the fake image detecting part and the fake news detecting part.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of not being able to efficiently detect and deal with fake images and fake news uploaded to social media.

[0005] The system according to the embodiment aims to efficiently detect and automatically block fake images and fake news uploaded to social networking sites. [Means for solving the problem]

[0006] The system according to the embodiment includes a content analysis unit, a fake image detection unit, a fake news detection unit, and a block execution unit. The content analysis unit analyzes content uploaded to SNS. The fake image detection unit detects fake images from the content analyzed by the content analysis unit. The fake news detection unit detects fake news from the content analyzed by the content analysis unit. The block execution unit automatically blocks fake content detected by the fake image detection unit and the fake news detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently detect and automatically block fake images and fake news uploaded to social networking sites. [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) A fake content detection system according to an embodiment of the present invention is a system that detects fake images and fake news generated by AI that are uploaded to social media and automatically blocks (hides) them. This enables the fake content detection system to efficiently detect and automatically block fake images and fake news on social media.

[0029] A fake content detection system according to an embodiment includes a content analysis unit, a fake image detection unit, a fake news detection unit, and a block execution unit. The content analysis unit analyzes content uploaded to social media. For example, the content analysis unit analyzes image metadata and pixel patterns to determine whether the image is a fake image generated by AI. The content analysis unit also analyzes the text of news articles to evaluate the credibility of the content. The fake image detection unit detects fake images from the content analyzed by the content analysis unit. For example, the fake image detection unit analyzes image metadata to detect editing history and traces of use of generation AI. The fake image detection unit also analyzes the pixel pattern of the image to determine whether it has characteristics that differ from natural images. The fake news detection unit detects fake news from the content analyzed by the content analysis unit. For example, the fake news detection unit analyzes the text of news articles to detect patterns of unreliable sources and misinformation. The fake news detection unit also compares the content of the article with other reliable sources to check for inconsistencies. The block execution unit automatically blocks fake content detected by the fake image detection unit and the fake news detection unit. For example, if a post on a social networking site is determined to be a fake image or fake news, the block execution unit hides the post so that other users cannot view it. The block execution unit also issues a warning to the poster and prevents the uploading of fake content. In this way, the fake content detection system according to the embodiment can automatically detect and block fake content on social networking sites, thereby preventing misunderstandings and confusion among users.

[0030] The content analysis unit can analyze the background information of images and news articles to evaluate the credibility of the content. For example, the content analysis unit uses generative AI to analyze the background information of an image and identify the location and time of the photo. For example, it analyzes the image's metadata and extracts the GPS information of the photo location and the date and time of the photo. The content analysis unit also analyzes the background information of a news article to evaluate the article's credibility. For example, it analyzes the article's citation sources and reference links to determine whether the information source is reliable. The content analysis unit also analyzes the background information of images and news articles and compares them with similar content from the past. For example, it compares them with images taken in the same location or articles on the same topic in the past to evaluate their credibility. In this way, analyzing the background information of the content can increase its credibility.

[0031] The content analysis unit can compare content with similar content from the past and identify elements that increase the likelihood of it being fake. For example, the generation AI compares it with similar images from the past and identifies elements that increase the likelihood of it being fake. For example, it analyzes the pixel patterns and color tones of an image to detect features that match those of past fake images. The content analysis unit also compares the text of a news article with similar articles from the past and identifies elements that increase the likelihood of it being fake. For example, it analyzes whether specific phrases or expressions match those of past fake news. The generation AI also compares it with similar content from the past and identifies elements that increase the likelihood of it being fake. For example, it analyzes the editing history of an image and the source of a news article to detect features that are common to past fake content. This allows the generation AI to identify elements that increase the likelihood of it being fake by comparing it with similar content from the past.

[0032] The content analysis unit analyzes and detects video content to identify fake videos. The content analysis unit, for example, uses generative AI to analyze each frame of a video to identify fake videos. For example, it detects unnatural changes between frames and traces of editing. The content analysis unit also analyzes the audio data of a video to identify fake videos. For example, it detects unnatural audio editing and the use of synthetic voices. The content analysis unit also analyzes video metadata to identify fake videos. For example, it detects inconsistencies in filming location or time and evaluates the possibility of a fake video. This makes it possible to identify fake videos by analyzing video content.

[0033] The content analysis unit can analyze audio data and detect fake audio. For example, the content analysis unit uses generative AI to analyze the waveform of audio data to detect fake audio. For example, it detects unnatural audio editing or characteristics of synthetic audio. The content analysis unit also performs spectral analysis of audio data to detect fake audio. For example, it analyzes the frequency components of the audio to determine whether it has characteristics that differ from natural audio. The content analysis unit also analyzes the metadata of the audio data to detect fake audio. For example, it detects inconsistencies in recording location or time and evaluates the possibility of fake audio. This makes it possible to detect fake audio by analyzing audio data.

[0034] The fake image detection unit can identify fake images by analyzing the optical characteristics and shadows of an image. The fake image detection unit can, for example, use generative AI to analyze the optical characteristics of an image to identify fake images. For example, it detects unnatural points in light reflection or refraction. The fake image detection unit can also analyze shadows in an image to identify fake images. For example, if the direction or length of a shadow is unnatural, it determines that the image is likely to be fake. The fake image detection unit can also identify fake images by combining the analysis of the optical characteristics and shadows of an image. For example, if the reflection of light and the position of the shadow do not match, it determines that the image is likely to be fake. This makes it possible to identify fake images by analyzing the optical characteristics and shadows of an image.

[0035] The fake image detection unit can evaluate the relative positions of objects within an image and detect unnatural placements. The fake image detection unit, for example, uses a generation AI to analyze the relative positions of objects within an image and detect unnatural placements. For example, if the size or distance of an object is unnatural, it determines that the image is likely to be a fake. The fake image detection unit also evaluates the relative positions of objects within an image and identifies fake images. For example, if the position or direction of an object's shadow does not match, it determines that the image is likely to be a fake. The fake image detection unit also uses a generation AI to evaluate the relative positions of objects within an image and detect unnatural placements. For example, if the overlap or transparency of objects is unnatural, it determines that the image is likely to be a fake. In this way, unnatural placements can be detected by evaluating the relative positions of objects within an image.

[0036] The fake image detection unit can analyze text in an image and detect fake text. The fake image detection unit, for example, uses a generation AI to analyze text in an image and detect fake text. For example, if the font or placement of the text is unnatural, it determines that there is a high possibility that it is fake. The fake image detection unit also analyzes the content of the text in an image and detects fake text. For example, if the content of the text contradicts other reliable information sources, it determines that there is a high possibility that it is fake. The fake image detection unit also uses a generation AI to analyze text in an image and detect fake text. For example, it detects the editing history of the text and traces of use of the generation AI and evaluates the possibility that it is fake. This makes it possible to detect fake text by analyzing the text in an image.

[0037] The fake news detection unit can analyze the writing style and phrasing of news articles to identify characteristics of fake news. For example, the fake news detection unit uses generative AI to analyze the writing style of news articles to identify characteristics of fake news. For example, it detects overly emotional expressions and exaggerated language. The fake news detection unit also analyzes the wording of news articles to identify characteristics of fake news. For example, it analyzes whether specific phrases or wording matches past fake news. The fake news detection unit also uses generative AI to analyze the combined writing style and wording of news articles to identify characteristics of fake news. For example, if the writing style and content do not match, it determines that the news is likely to be fake news. In this way, the characteristics of fake news can be identified by analyzing the writing style and wording of news articles.

[0038] The fake news detection unit can evaluate the citation source and reference links of news articles to determine their credibility. For example, the fake news detection unit uses generation AI to analyze the citation source of a news article and determine its credibility. For example, if the citation source is a low-reliability site or blog, it will determine that it is likely to be fake news. The fake news detection unit also analyzes the reference links of a news article to determine its credibility. For example, it evaluates whether the information source at the linked destination is a highly reliable media. The fake news detection unit also uses generation AI to evaluate the citation source and reference links of a news article to determine its credibility. For example, it analyzes whether the information at the citation source or link destination matches that of other highly reliable information sources. This makes it possible to determine the credibility by evaluating the citation source and reference links of a news article.

[0039] The fake news detection unit can analyze and detect blog articles and forum posts to identify fake content. The fake news detection unit, for example, uses generative AI to analyze blog articles to identify fake content. For example, it analyzes the article's writing style and source to evaluate its credibility. The fake news detection unit also analyzes forum posts to identify fake content. For example, it evaluates the credibility of the post content and detects features that match past fake posts. The fake news detection unit also uses generative AI to combine the analysis of blog articles and forum posts to identify fake content. For example, it analyzes the content of the article and the poster's history to evaluate the likelihood of it being fake. This makes it possible to identify fake content by analyzing blog articles and forum posts.

[0040] The fake news detection unit can analyze comments and feedback on news articles to assess the impact of fake news. For example, the fake news detection unit uses a generation AI to analyze comments on news articles to assess the impact of fake news. For example, it analyzes the content and sentiment of comments and determines that if there are a lot of negative reactions, the news is likely fake. The fake news detection unit also analyzes feedback on articles to assess the impact of fake news. For example, it analyzes the content of feedback and evaluation scores to determine credibility. The fake news detection unit also uses a generation AI to analyze comments and feedback on news articles to assess the impact of fake news. For example, it analyzes whether the content of comments and feedback matches other reliable information sources. This makes it possible to assess the impact of fake news by analyzing comments and feedback on news articles.

[0041] The block execution unit can block fake content and automatically warn about related content. For example, the block execution unit uses generation AI to automatically display warnings about related content when blocking fake content. For example, it displays a warning message on articles related to fake news. The block execution unit also issues a warning to posters of related content at the same time as blocking fake content. For example, it sends a warning message to posters related to fake images. The block execution unit also uses generation AI to display warnings to viewers of related content in addition to blocking fake content. For example, it displays a warning message to users who view articles related to fake news. This makes it possible to draw users' attention by automatically displaying warnings on related content in addition to blocking fake content.

[0042] When automatically blocking, the block execution unit can provide detailed reasons to the poster of the content to encourage understanding. For example, when the generation AI blocks fake content, the block execution unit provides detailed reasons to the poster. For example, it may explain the reason why a fake image was detected and the analysis results. In addition, when automatically blocking, the block execution unit may point out specific problems with the fake content to the poster. For example, it may explain why a news article is unreliable or problems with the source. In addition, when the generation AI blocks fake content, the block execution unit provides information to encourage understanding to the poster. For example, it may explain the impact and risks of fake content. In this way, by providing detailed reasons when automatically blocking, it is possible to encourage understanding by the poster.

[0043] The block execution unit displays a warning to viewers of content when automatically blocking it, thereby preventing the spread of fake content. For example, the block execution unit displays a warning to viewers when the generation AI blocks fake content. For example, it displays a warning message to users who attempt to view fake news. The block execution unit also displays a warning to viewers when automatically blocking, explaining the risks of fake content. For example, it explains the effects of fake images and the risks of misinformation. The block execution unit also displays a warning to viewers when the generation AI blocks fake content, thereby preventing the spread of fake content. For example, it displays a warning message to users who attempt to share fake news. In this way, by displaying a warning to viewers when automatically blocking, it is possible to prevent the spread of fake content.

[0044] When receiving feedback, the generative AI can introduce new algorithms to improve its accuracy in detecting fake content. For example, when receiving feedback, the generative AI introduces new algorithms to improve its accuracy in detecting fake content. For example, it uses deep learning technology to improve the detection model. The generative AI can also develop new algorithms based on the feedback data to improve its detection accuracy. For example, it can analyze patterns of false positives and false negatives and optimize the algorithm. The generative AI can also introduce new algorithms to continuously improve its detection accuracy when receiving feedback. For example, it can learn from the feedback data in real time and update its algorithm. In this way, the introduction of new algorithms can improve the accuracy of detecting fake content.

[0045] When analyzing feedback, generative AI can integrate data from different social media platforms and perform learning. For example, generative AI integrates feedback data from different social media platforms and performs learning. For example, data from Facebook and Twitter can be integrated into a single model. Generative AI also analyzes feedback data and integrates information from different social media platforms to perform learning. For example, it builds a learning model that takes into account the characteristics of each platform. Generative AI also develops a system that integrates data from different social media platforms and performs learning. For example, it collects feedback data from each platform in real time and uses it for learning. In this way, the accuracy of learning can be improved by integrating data from different social media platforms.

[0046] When receiving feedback, generative AI can analyze data from different languages ​​and cultural spheres and learn from a global perspective. For example, generative AI analyzes feedback data in different languages ​​and learns from a global perspective. For example, it integrates data from English, French, Chinese, etc. to learn. Generative AI also analyzes feedback data from different cultural spheres and reflects this in the learning process. For example, it builds a learning model that takes cultural background and values ​​into account. Generative AI also analyzes data from different languages ​​and cultural spheres and develops a system that learns from a global perspective. For example, it collects feedback data that takes into account the characteristics of each region and uses it for learning. In this way, analyzing data from different languages ​​and cultural spheres allows learning from a global perspective.

[0047] When analyzing feedback, generative AI can integrate different types of content to learn. For example, generative AI integrates different types of feedback data (text, images, videos) to learn. For example, it learns by combining text comments and emotional reactions to images. Generative AI also analyzes feedback data and integrates different types of content to learn. For example, it builds a learning model by combining video viewing data and text comments. Generative AI also develops systems that integrate different types of content to learn. For example, it collects feedback data of text, images, and videos in real time and uses it for learning. In this way, the accuracy of learning can be improved by integrating different types of content.

[0048] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0049] The fake content detection system can further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit, for example, analyzes a user's past posting and browsing history to identify trends in posting and browsing fake content. For example, it determines that a user who has frequently shared fake news in the past is likely to post fake content again. The behavioral analysis unit also analyzes a user's social networking interaction patterns to assess the risk of spreading fake content. For example, if fake news is frequently shared within a specific group, it can issue a warning to members of that group. Furthermore, the behavioral analysis unit analyzes the time and frequency of a user's posting to detect abnormal behavioral patterns. For example, if a large number of posts are made outside of normal activity hours, it can determine that the account may have been hacked. In this way, by analyzing a user's behavioral history, it is possible to prevent the posting and spreading of fake content.

[0050] The fake content detection system can further include a cross-reference unit for evaluating the credibility of content. The cross-reference unit, for example, compares content with multiple reliable information sources to check for inconsistencies. For example, it compares the content of a news article with reports from other major media outlets to evaluate whether they match. The cross-reference unit also analyzes the content's citation sources and reference links to evaluate their credibility. For example, if the citation source is a low-reliability site or blog, it may determine that the content is likely to be fake news. The cross-reference unit also compares content with similar content from the past to evaluate its credibility. For example, it compares it with articles previously reported on the same topic to check whether the content matches. This allows the credibility of the content to be increased by comparing it with multiple information sources.

[0051] The fake content detection system may further include a visual analysis unit that analyzes the visual features of content. The visual analysis unit may, for example, analyze the color tone and brightness of images and videos to detect unnatural points. For example, if one part of an image has a different color tone from the other parts, it may determine that the image is likely edited. The visual analysis unit may also analyze the composition of images and videos to detect unnatural placement. For example, if the size or position of an object is unnatural, it may determine that the image is likely to be fake. Furthermore, the visual analysis unit may analyze the metadata of images and videos to detect inconsistencies in the location and time of shooting. For example, if the shooting location described in the image metadata does not match the actual background, it may determine that the image is likely to be fake. This allows fake content to be identified by analyzing visual features.

[0052] The fake content detection system may further include an audio analysis unit that analyzes the audio data of the content. The audio analysis unit, for example, analyzes the waveform of the audio data to detect unnatural edited or synthetic audio characteristics. For example, if a portion of the audio has a different sound quality from the other portions, it determines that there is a high possibility that it has been edited. The audio analysis unit also performs a spectral analysis of the audio data to determine whether it has characteristics that differ from natural audio. For example, if the frequency components of the audio are unnatural, it determines that there is a high possibility that the audio is fake. Furthermore, the audio analysis unit analyzes the metadata of the audio data to detect discrepancies in the recording location or time. For example, if the recording location described in the audio metadata does not match the actual background sound, it determines that there is a high possibility that the audio is fake. In this way, fake audio can be identified by analyzing the audio data.

[0053] The fake content detection system can further include a context analysis unit that analyzes the context of the content. The context analysis unit, for example, analyzes the context before and after a news article to evaluate the consistency of the content. For example, if one part of the article contradicts another part, it determines that it is likely to be fake news. The context analysis unit also analyzes the scenes before and after an image or video to detect unnatural points. For example, if one part of a video contradicts the other part in terms of time, it determines that it is likely to have been edited. The context analysis unit also analyzes the context of the content's citation source and reference links to evaluate its reliability. For example, if the citation source is a low-reliability site or blog, it determines that it is likely to be fake news. In this way, fake content can be identified by analyzing the context.

[0054] The fake content detection system can further include a language analysis unit that analyzes the linguistic characteristics of content. The language analysis unit, for example, analyzes the writing style and phrasing of news articles to identify characteristics of fake news. For example, it detects overly emotional expressions and exaggerated language. The language analysis unit also analyzes the phrasing of news articles to identify characteristics of fake news. For example, it analyzes whether specific phrases or phrasing matches past fake news. The language analysis unit also analyzes the combined writing style and phrasing of news articles to identify characteristics of fake news. For example, if the writing style and content do not match, it determines that the news is likely to be fake news. In this way, the characteristics of fake news can be identified by analyzing the writing style and phrasing of news articles.

[0055] The processing flow of the first embodiment will be briefly explained below.

[0056] Step 1: The content analysis unit analyzes content uploaded to social media. For example, it analyzes image metadata and pixel patterns to determine whether the image is fake or not. It also analyzes the text of news articles to assess the credibility of the content. Step 2: The fake image detection unit detects fake images from the content analyzed by the content analysis unit. For example, it analyzes the image metadata to detect editing history and traces of the use of AI to generate the fake images. It also analyzes the pixel patterns of the images to determine whether they have characteristics that differ from natural images. Step 3: The fake news detection unit detects fake news from the content analyzed by the content analysis unit. For example, it analyzes the text of news articles to detect patterns of unreliable sources and misinformation. It also compares the content of the articles with other reliable sources to check for inconsistencies. Step 4: The block execution unit automatically blocks fake content detected by the fake image detection unit and fake news detection unit. For example, if a social media post is determined to contain fake images or fake news, the block execution unit hides the post so that other users cannot view it. It also issues a warning to the poster and prevents them from uploading fake content.

[0057] (Example 2) A fake content detection system according to an embodiment of the present invention is a system that detects fake images and fake news generated by AI that are uploaded to social media and automatically blocks (hides) them. This enables the fake content detection system to efficiently detect and automatically block fake images and fake news on social media.

[0058] A fake content detection system according to an embodiment includes a content analysis unit, a fake image detection unit, a fake news detection unit, and a block execution unit. The content analysis unit analyzes content uploaded to social media. For example, the content analysis unit analyzes image metadata and pixel patterns to determine whether the image is a fake image generated by AI. The content analysis unit also analyzes the text of news articles to evaluate the credibility of the content. The fake image detection unit detects fake images from the content analyzed by the content analysis unit. For example, the fake image detection unit analyzes image metadata to detect editing history and traces of use of generation AI. The fake image detection unit also analyzes the pixel pattern of the image to determine whether it has characteristics that differ from natural images. The fake news detection unit detects fake news from the content analyzed by the content analysis unit. For example, the fake news detection unit analyzes the text of news articles to detect patterns of unreliable sources and misinformation. The fake news detection unit also compares the content of the article with other reliable sources to check for inconsistencies. The block execution unit automatically blocks fake content detected by the fake image detection unit and the fake news detection unit. For example, if a post on a social networking site is determined to be a fake image or fake news, the block execution unit hides the post so that other users cannot view it. The block execution unit also issues a warning to the poster and prevents the uploading of fake content. In this way, the fake content detection system according to the embodiment can automatically detect and block fake content on social networking sites, thereby preventing misunderstandings and confusion among users.

[0059] The content analysis unit can analyze the background information of images and news articles to evaluate the credibility of the content. For example, the content analysis unit uses generative AI to analyze the background information of an image and identify the location and time of the photo. For example, it analyzes the image's metadata and extracts the GPS information of the photo location and the date and time of the photo. The content analysis unit also analyzes the background information of a news article to evaluate the article's credibility. For example, it analyzes the article's citation sources and reference links to determine whether the information source is reliable. The content analysis unit also analyzes the background information of images and news articles and compares them with similar content from the past. For example, it compares them with images taken in the same location or articles on the same topic in the past to evaluate their credibility. In this way, analyzing the background information of the content can increase its credibility.

[0060] The content analysis unit can compare content with similar content from the past and identify elements that increase the likelihood of it being fake. For example, the generation AI compares it with similar images from the past and identifies elements that increase the likelihood of it being fake. For example, it analyzes the pixel patterns and color tones of an image to detect features that match those of past fake images. The content analysis unit also compares the text of a news article with similar articles from the past and identifies elements that increase the likelihood of it being fake. For example, it analyzes whether specific phrases or expressions match those of past fake news. The generation AI also compares it with similar content from the past and identifies elements that increase the likelihood of it being fake. For example, it analyzes the editing history of an image and the source of a news article to detect features that are common to past fake content. This allows the generation AI to identify elements that increase the likelihood of it being fake by comparing it with similar content from the past.

[0061] The content analysis unit can use the emotion estimation function to analyze the emotions of the poster and evaluate the possibility of fake content. The content analysis unit, for example, uses the emotion estimation function to analyze the emotions of the poster of the content. For example, it analyzes the poster's facial expressions and voice and calculates an emotion score. The content analysis unit also evaluates the possibility of fake content based on the poster's emotion data. For example, it determines that a post with strong negative emotions is likely to be fake content. The content analysis unit also uses the emotion estimation function to analyze the poster's emotions in real time and evaluate the possibility of fake content. For example, it monitors emotional changes at the time of posting and determines that there is a high possibility of fake content if there are abnormal emotional fluctuations. In this way, the possibility of fake content can be evaluated by analyzing the poster's emotions.

[0062] The content analysis unit analyzes and detects video content to identify fake videos. The content analysis unit, for example, uses generative AI to analyze each frame of a video to identify fake videos. For example, it detects unnatural changes between frames and traces of editing. The content analysis unit also analyzes the audio data of a video to identify fake videos. For example, it detects unnatural audio editing and the use of synthetic voices. The content analysis unit also analyzes video metadata to identify fake videos. For example, it detects inconsistencies in filming location or time and evaluates the possibility of a fake video. This makes it possible to identify fake videos by analyzing video content.

[0063] The content analysis unit can analyze audio data and detect fake audio. For example, the content analysis unit uses generative AI to analyze the waveform of audio data to detect fake audio. For example, it detects unnatural audio editing or characteristics of synthetic audio. The content analysis unit also performs spectral analysis of audio data to detect fake audio. For example, it analyzes the frequency components of the audio to determine whether it has characteristics that differ from natural audio. The content analysis unit also analyzes the metadata of the audio data to detect fake audio. For example, it detects inconsistencies in recording location or time and evaluates the possibility of fake audio. This makes it possible to detect fake audio by analyzing audio data.

[0064] The content analysis unit can use the emotion estimation function to analyze the viewer's emotional response and evaluate the impact of fake content. The content analysis unit, for example, uses the emotion estimation function to analyze the viewer's emotional response to content in real time. For example, it analyzes the viewer's facial expressions and voice and calculates an emotion score. The content analysis unit also evaluates the impact of fake content based on the viewer's emotional data. For example, it determines that content with a high number of negative emotional responses is likely to be fake. The content analysis unit also uses the emotion estimation function to analyze the viewer's emotional response and evaluate the impact of fake content. For example, it monitors changes in the viewer's emotions and determines that the impact of fake content is significant if there are abnormal emotional fluctuations. In this way, the impact of fake content can be evaluated by analyzing the viewer's emotional response.

[0065] The fake image detection unit can identify fake images by analyzing the optical characteristics and shadows of an image. The fake image detection unit can, for example, use generative AI to analyze the optical characteristics of an image to identify fake images. For example, it detects unnatural points in light reflection or refraction. The fake image detection unit can also analyze shadows in an image to identify fake images. For example, if the direction or length of a shadow is unnatural, it determines that the image is likely to be fake. The fake image detection unit can also identify fake images by combining the analysis of the optical characteristics and shadows of an image. For example, if the reflection of light and the position of the shadow do not match, it determines that the image is likely to be fake. This makes it possible to identify fake images by analyzing the optical characteristics and shadows of an image.

[0066] The fake image detection unit can evaluate the relative positions of objects within an image and detect unnatural placements. The fake image detection unit, for example, uses a generation AI to analyze the relative positions of objects within an image and detect unnatural placements. For example, if the size or distance of an object is unnatural, it determines that the image is likely to be a fake. The fake image detection unit also evaluates the relative positions of objects within an image and identifies fake images. For example, if the position or direction of an object's shadow does not match, it determines that the image is likely to be a fake. The fake image detection unit also uses a generation AI to evaluate the relative positions of objects within an image and detect unnatural placements. For example, if the overlap or transparency of objects is unnatural, it determines that the image is likely to be a fake. In this way, unnatural placements can be detected by evaluating the relative positions of objects within an image.

[0067] The fake image detection unit can use the emotion estimation function to analyze the emotional response of the viewer of the image and evaluate the influence of the fake image. The fake image detection unit, for example, uses the emotion estimation function to analyze the emotional response of the viewer of the image in real time. For example, it analyzes the viewer's facial expressions and voice and calculates an emotion score. The fake image detection unit also evaluates the influence of the fake image based on the viewer's emotion data. For example, it determines that an image with a high number of negative emotional responses is likely to be fake. The fake image detection unit also uses the emotion estimation function to analyze the viewer's emotional response and evaluate the influence of the fake image. For example, it monitors the viewer's emotional changes and determines that the influence of the fake image is large if there are abnormal emotional fluctuations. In this way, the influence of the fake image can be evaluated by analyzing the viewer's emotional response.

[0068] The fake image detection unit can analyze text in an image and detect fake text. The fake image detection unit, for example, uses a generation AI to analyze text in an image and detect fake text. For example, if the font or placement of the text is unnatural, it determines that there is a high possibility that it is fake. The fake image detection unit also analyzes the content of the text in an image and detects fake text. For example, if the content of the text contradicts other reliable information sources, it determines that there is a high possibility that it is fake. The fake image detection unit also uses a generation AI to analyze text in an image and detect fake text. For example, it detects the editing history of the text and traces of use of the generation AI and evaluates the possibility that it is fake. This makes it possible to detect fake text by analyzing the text in an image.

[0069] The fake image detection unit can use the emotion estimation function to analyze the emotions of the image poster and evaluate the possibility that the image is a fake. The fake image detection unit, for example, uses the emotion estimation function to analyze the emotions of the image poster. For example, it analyzes the poster's facial expressions and voice and calculates an emotion score. The fake image detection unit also evaluates the possibility that the image is a fake based on the poster's emotion data. For example, it determines that a post with strong negative emotions is likely to be a fake image. The fake image detection unit also uses the emotion estimation function to analyze the poster's emotions in real time and evaluate the possibility that the image is a fake. For example, it monitors emotional changes at the time of posting and determines that there is a high possibility that the image is a fake if there is an abnormal emotional fluctuation. In this way, the possibility that the image is a fake can be evaluated by analyzing the poster's emotions.

[0070] The fake news detection unit can analyze the writing style and phrasing of news articles to identify characteristics of fake news. For example, the fake news detection unit uses generative AI to analyze the writing style of news articles to identify characteristics of fake news. For example, it detects overly emotional expressions and exaggerated language. The fake news detection unit also analyzes the wording of news articles to identify characteristics of fake news. For example, it analyzes whether specific phrases or wording matches past fake news. The fake news detection unit also uses generative AI to analyze the combined writing style and wording of news articles to identify characteristics of fake news. For example, if the writing style and content do not match, it determines that the news is likely to be fake news. In this way, the characteristics of fake news can be identified by analyzing the writing style and wording of news articles.

[0071] The fake news detection unit can evaluate the citation source and reference links of news articles to determine their credibility. For example, the fake news detection unit uses generation AI to analyze the citation source of a news article and determine its credibility. For example, if the citation source is a low-reliability site or blog, it will determine that it is likely to be fake news. The fake news detection unit also analyzes the reference links of a news article to determine its credibility. For example, it evaluates whether the information source at the linked destination is a highly reliable media. The fake news detection unit also uses generation AI to evaluate the citation source and reference links of a news article to determine its credibility. For example, it analyzes whether the information at the citation source or link destination matches that of other highly reliable information sources. This makes it possible to determine the credibility by evaluating the citation source and reference links of a news article.

[0072] The fake news detection unit can use the emotion estimation function to analyze the emotions of the poster of a news article and evaluate the possibility of it being fake news. The fake news detection unit, for example, uses the emotion estimation function to analyze the emotions of the poster of a news article. For example, it analyzes the poster's facial expressions and voice and calculates an emotion score. The fake news detection unit also evaluates the possibility of fake news based on the poster's emotion data. For example, it determines that a post with strong negative emotions is likely to be fake news. The fake news detection unit also uses the emotion estimation function to analyze the poster's emotions in real time and evaluate the possibility of fake news. For example, it monitors changes in emotion at the time of posting and determines that there is a high possibility of fake news if there is an abnormal emotional fluctuation. In this way, the possibility of fake news can be evaluated by analyzing the poster's emotions.

[0073] The fake news detection unit can analyze and detect blog articles and forum posts to identify fake content. The fake news detection unit, for example, uses generative AI to analyze blog articles to identify fake content. For example, it analyzes the article's writing style and source to evaluate its credibility. The fake news detection unit also analyzes forum posts to identify fake content. For example, it evaluates the credibility of the post content and detects features that match past fake posts. The fake news detection unit also uses generative AI to combine the analysis of blog articles and forum posts to identify fake content. For example, it analyzes the content of the article and the poster's history to evaluate the likelihood of it being fake. This makes it possible to identify fake content by analyzing blog articles and forum posts.

[0074] The fake news detection unit can analyze comments and feedback on news articles to assess the impact of fake news. For example, the fake news detection unit uses a generation AI to analyze comments on news articles to assess the impact of fake news. For example, it analyzes the content and sentiment of comments and determines that if there are a lot of negative reactions, the news is likely fake. The fake news detection unit also analyzes feedback on articles to assess the impact of fake news. For example, it analyzes the content of feedback and evaluation scores to determine credibility. The fake news detection unit also uses a generation AI to analyze comments and feedback on news articles to assess the impact of fake news. For example, it analyzes whether the content of comments and feedback matches other reliable information sources. This makes it possible to assess the impact of fake news by analyzing comments and feedback on news articles.

[0075] The fake news detection unit can use the emotion estimation function to analyze the emotional reactions of viewers to news articles and evaluate the impact of fake news. The fake news detection unit, for example, uses the emotion estimation function to analyze the emotional reactions of viewers to news articles in real time. For example, it analyzes the viewers' facial expressions and voices and calculates an emotion score. The fake news detection unit also evaluates the impact of fake news based on the viewers' emotional data. For example, it determines that articles with a high number of negative emotional reactions are likely to be fake. The fake news detection unit also uses the emotion estimation function to analyze the viewers' emotional reactions and evaluate the impact of fake news. For example, it monitors the viewers' emotional changes and determines that the impact of fake news is significant if there are abnormal emotional fluctuations. In this way, the impact of fake news can be evaluated by analyzing the viewers' emotional reactions.

[0076] The block execution unit can block fake content and automatically warn about related content. For example, the block execution unit uses generation AI to automatically display warnings about related content when blocking fake content. For example, it displays a warning message on articles related to fake news. The block execution unit also issues a warning to posters of related content at the same time as blocking fake content. For example, it sends a warning message to posters related to fake images. The block execution unit also uses generation AI to display warnings to viewers of related content in addition to blocking fake content. For example, it displays a warning message to users who view articles related to fake news. This makes it possible to draw users' attention by automatically displaying warnings on related content in addition to blocking fake content.

[0077] When automatically blocking, the block execution unit can provide detailed reasons to the poster of the content to encourage understanding. For example, when the generation AI blocks fake content, the block execution unit provides detailed reasons to the poster. For example, it may explain the reason why a fake image was detected and the analysis results. In addition, when automatically blocking, the block execution unit may point out specific problems with the fake content to the poster. For example, it may explain why a news article is unreliable or problems with the source. In addition, when the generation AI blocks fake content, the block execution unit provides information to encourage understanding to the poster. For example, it may explain the impact and risks of fake content. In this way, by providing detailed reasons when automatically blocking, it is possible to encourage understanding by the poster.

[0078] The block execution unit uses the emotion estimation function to analyze the emotional response of the poster of the blocked content and can take appropriate action. The block execution unit, for example, uses the emotion estimation function to analyze the emotional response of the poster of the blocked content in real time. For example, it analyzes the poster's facial expressions and voice and calculates an emotion score. The block execution unit also takes appropriate action based on the poster's emotion data. For example, if the poster has strong negative emotions, it sends a support message to the poster. The block execution unit also uses the emotion estimation function to analyze the emotional response of the poster of the blocked content and can take appropriate action. For example, it monitors changes in the poster's emotions and follows up as necessary. In this way, it is possible to take appropriate action by analyzing the emotional response of the poster of the blocked content.

[0079] The block execution unit displays a warning to viewers of content when automatically blocking it, thereby preventing the spread of fake content. For example, the block execution unit displays a warning to viewers when the generation AI blocks fake content. For example, it displays a warning message to users who attempt to view fake news. The block execution unit also displays a warning to viewers when automatically blocking, explaining the risks of fake content. For example, it explains the effects of fake images and the risks of misinformation. The block execution unit also displays a warning to viewers when the generation AI blocks fake content, thereby preventing the spread of fake content. For example, it displays a warning message to users who attempt to share fake news. In this way, by displaying a warning to viewers when automatically blocking, it is possible to prevent the spread of fake content.

[0080] The block execution unit uses the emotion estimation function to analyze the emotional response of the viewer of the blocked content and can take appropriate action. The block execution unit, for example, uses the emotion estimation function to analyze the emotional response of the viewer of the blocked content in real time. For example, it analyzes the viewer's facial expressions and voice and calculates an emotion score. The block execution unit also takes appropriate action based on the viewer's emotion data. For example, if the viewer has strong negative emotions, it sends a support message to the viewer. The block execution unit also uses the emotion estimation function to analyze the emotional response of the viewer of the blocked content and can take appropriate action. For example, it monitors changes in the viewer's emotions and follows up as necessary. In this way, it is possible to take appropriate action by analyzing the emotional response of the viewer of the blocked content.

[0081] When receiving feedback, the generative AI can introduce new algorithms to improve its accuracy in detecting fake content. For example, when receiving feedback, the generative AI introduces new algorithms to improve its accuracy in detecting fake content. For example, it uses deep learning technology to improve the detection model. The generative AI can also develop new algorithms based on the feedback data to improve its detection accuracy. For example, it can analyze patterns of false positives and false negatives and optimize the algorithm. The generative AI can also introduce new algorithms to continuously improve its detection accuracy when receiving feedback. For example, it can learn from the feedback data in real time and update its algorithm. In this way, the introduction of new algorithms can improve the accuracy of detecting fake content.

[0082] When analyzing feedback, generative AI can integrate data from different social media platforms and perform learning. For example, generative AI integrates feedback data from different social media platforms and performs learning. For example, data from Facebook and Twitter can be integrated into a single model. Generative AI also analyzes feedback data and integrates information from different social media platforms to perform learning. For example, it builds a learning model that takes into account the characteristics of each platform. Generative AI also develops a system that integrates data from different social media platforms and performs learning. For example, it collects feedback data from each platform in real time and uses it for learning. In this way, the accuracy of learning can be improved by integrating data from different social media platforms.

[0083] The generation AI can use the emotion estimation function to analyze the emotions of the user providing feedback and reflect them in the learning process. The generation AI, for example, uses the emotion estimation function to analyze the emotions of the user providing feedback. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The generation AI also reflects this in the learning process based on the user's emotion data. For example, it prioritizes feedback with strong positive emotions as learning data. The generation AI also uses the emotion estimation function to analyze the emotions of the user providing feedback in real time and reflect them in the learning process. For example, it monitors emotional changes and updates learning data at the appropriate time. In this way, the emotions of the user providing feedback can be analyzed and reflected in the learning process.

[0084] When receiving feedback, generative AI can analyze data from different languages ​​and cultural spheres and learn from a global perspective. For example, generative AI analyzes feedback data in different languages ​​and learns from a global perspective. For example, it integrates data from English, French, Chinese, etc. to learn. Generative AI also analyzes feedback data from different cultural spheres and reflects this in the learning process. For example, it builds a learning model that takes cultural background and values ​​into account. Generative AI also analyzes data from different languages ​​and cultural spheres and develops a system that learns from a global perspective. For example, it collects feedback data that takes into account the characteristics of each region and uses it for learning. In this way, analyzing data from different languages ​​and cultural spheres allows learning from a global perspective.

[0085] When analyzing feedback, generative AI can integrate different types of content to learn. For example, generative AI integrates different types of feedback data (text, images, videos) to learn. For example, it learns by combining text comments and emotional reactions to images. Generative AI also analyzes feedback data and integrates different types of content to learn. For example, it builds a learning model by combining video viewing data and text comments. Generative AI also develops systems that integrate different types of content to learn. For example, it collects feedback data of text, images, and videos in real time and uses it for learning. In this way, the accuracy of learning can be improved by integrating different types of content.

[0086] The generation AI can use the emotion estimation function to analyze the emotional reactions of users who provide feedback and reflect them in the learning process. For example, the generation AI uses the emotion estimation function to analyze the emotional reactions of users who provide feedback in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The generation AI also reflects the user's emotional reaction data in the learning process. For example, it prioritizes feedback with strong positive emotions as learning data. The generation AI also uses the emotion estimation function to analyze the emotional reactions of users who provide feedback and reflect them in the learning process. For example, it monitors emotional changes and updates learning data at appropriate times. In this way, the emotional reactions of users who provide feedback can be analyzed and reflected in the learning process.

[0087] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0088] The fake content detection system can further include a behavioral analysis unit that analyzes a user's behavioral history. The behavioral analysis unit, for example, analyzes a user's past posting and browsing history to identify trends in posting and browsing fake content. For example, it determines that a user who has frequently shared fake news in the past is likely to post fake content again. The behavioral analysis unit also analyzes a user's social networking interaction patterns to assess the risk of spreading fake content. For example, if fake news is frequently shared within a specific group, it can issue a warning to members of that group. Furthermore, the behavioral analysis unit analyzes the time and frequency of a user's posting to detect abnormal behavioral patterns. For example, if a large number of posts are made outside of normal activity hours, it can determine that the account may have been hacked. In this way, by analyzing a user's behavioral history, it is possible to prevent the posting and spreading of fake content.

[0089] The fake content detection system can further include a cross-reference unit for evaluating the credibility of content. The cross-reference unit, for example, compares content with multiple reliable information sources to check for inconsistencies. For example, it compares the content of a news article with reports from other major media outlets to evaluate whether they match. The cross-reference unit also analyzes the content's citation sources and reference links to evaluate their credibility. For example, if the citation source is a low-reliability site or blog, it may determine that the content is likely to be fake news. The cross-reference unit also compares content with similar content from the past to evaluate its credibility. For example, it compares it with articles previously reported on the same topic to check whether the content matches. This allows the credibility of the content to be increased by comparing it with multiple information sources.

[0090] The fake content detection system can further include an emotion analysis unit that estimates a user's emotions and evaluates the authenticity of content based on the estimated emotions. The emotion analysis unit, for example, analyzes the user's emotions at the time of posting and determines that a post is likely to be fake content if the user's emotions are strong. For example, a post expressing anger or anxiety may be fake news created to provoke an emotional response. The emotion analysis unit also monitors changes in the user's emotions and determines that any abnormal emotional fluctuations are likely to be fake content. For example, if a user who normally expresses calm emotions suddenly expresses strong negative emotions, the post may be fake content. The emotion analysis unit further evaluates the impact of fake content based on the user's emotion data. For example, it determines that content that elicits a large number of negative emotional responses is likely to be fake. This allows the authenticity of fake content to be evaluated by analyzing user emotions.

[0091] The fake content detection system may further include a visual analysis unit that analyzes the visual features of content. The visual analysis unit may, for example, analyze the color tone and brightness of images and videos to detect unnatural points. For example, if one part of an image has a different color tone from the other parts, it may determine that the image is likely edited. The visual analysis unit may also analyze the composition of images and videos to detect unnatural placement. For example, if the size or position of an object is unnatural, it may determine that the image is likely to be fake. Furthermore, the visual analysis unit may analyze the metadata of images and videos to detect inconsistencies in the location and time of shooting. For example, if the shooting location described in the image metadata does not match the actual background, it may determine that the image is likely to be fake. This allows fake content to be identified by analyzing visual features.

[0092] The fake content detection system can further include an emotional impact analysis unit that estimates user emotions and evaluates the impact of content based on the estimated emotions. The emotional impact analysis unit, for example, analyzes viewers' emotional reactions to content in real time and determines that content is likely fake if there are many negative emotional reactions. For example, if there are many comments expressing anger or fear, the content may be fake news created to provoke an emotional reaction. The emotional impact analysis unit also monitors viewers' emotional changes and determines that the impact of fake content is significant if there are abnormal emotional fluctuations. For example, if a viewer who normally displays calm emotions suddenly displays strong negative emotions, the content may be fake. The emotional impact analysis unit further evaluates the impact of fake content based on viewers' emotional data. For example, it determines that content with many negative emotional reactions is likely fake. This allows the impact of fake content to be evaluated by analyzing viewers' emotions.

[0093] The fake content detection system may further include an audio analysis unit that analyzes the audio data of the content. The audio analysis unit, for example, analyzes the waveform of the audio data to detect unnatural edited or synthetic audio characteristics. For example, if a portion of the audio has a different sound quality from the other portions, it determines that there is a high possibility that it has been edited. The audio analysis unit also performs a spectral analysis of the audio data to determine whether it has characteristics that differ from natural audio. For example, if the frequency components of the audio are unnatural, it determines that there is a high possibility that the audio is fake. Furthermore, the audio analysis unit analyzes the metadata of the audio data to detect discrepancies in the recording location or time. For example, if the recording location described in the audio metadata does not match the actual background sound, it determines that there is a high possibility that the audio is fake. In this way, fake audio can be identified by analyzing the audio data.

[0094] The fake content detection system can further include an emotion credibility analysis unit that estimates a user's emotions and evaluates the credibility of the content based on the estimated emotions. The emotion credibility analysis unit, for example, analyzes the emotions of the content poster and determines that the content is likely to be fake content if the emotions are strong. For example, a post expressing anger or anxiety may be fake news created to provoke an emotional response. The emotion credibility analysis unit also monitors the poster's emotional changes and determines that the content is likely to be fake content if there are abnormal emotional fluctuations. For example, if a poster who normally expresses calm emotions suddenly expresses strong negative emotions, the post may be fake content. Furthermore, the emotion credibility analysis unit evaluates the credibility of the fake content based on the poster's emotional data. For example, it determines that a post with a high number of negative emotional responses is likely to be fake. In this way, the credibility of fake content can be evaluated by analyzing the poster's emotions.

[0095] The fake content detection system can further include a context analysis unit that analyzes the context of the content. The context analysis unit, for example, analyzes the context before and after a news article to evaluate the consistency of the content. For example, if one part of the article contradicts another part, it determines that it is likely to be fake news. The context analysis unit also analyzes the scenes before and after an image or video to detect unnatural points. For example, if one part of a video contradicts the other part in terms of time, it determines that it is likely to have been edited. The context analysis unit also analyzes the context of the content's citation source and reference links to evaluate its reliability. For example, if the citation source is a low-reliability site or blog, it determines that it is likely to be fake news. In this way, fake content can be identified by analyzing the context.

[0096] The fake content detection system can further include an emotional impact assessment unit that estimates user emotions and evaluates the impact of content based on the estimated emotions. The emotional impact assessment unit, for example, analyzes viewers' emotional reactions to content in real time and determines that content is likely fake if there are many negative emotional reactions. For example, if there are many comments expressing anger or fear, the content may be fake news created to provoke an emotional reaction. The emotional impact assessment unit also monitors viewers' emotional changes and determines that the impact of fake content is significant if there are abnormal emotional fluctuations. For example, if a viewer who normally displays calm emotions suddenly displays strong negative emotions, the content may be fake. The emotional impact assessment unit further evaluates the impact of fake content based on viewers' emotional data. For example, it determines that content with many negative emotional reactions is likely fake. This allows the impact of fake content to be evaluated by analyzing viewers' emotions.

[0097] The fake content detection system can further include a language analysis unit that analyzes the linguistic characteristics of content. The language analysis unit, for example, analyzes the writing style and phrasing of news articles to identify characteristics of fake news. For example, it detects overly emotional expressions and exaggerated language. The language analysis unit also analyzes the phrasing of news articles to identify characteristics of fake news. For example, it analyzes whether specific phrases or phrasing matches past fake news. The language analysis unit also analyzes the combined writing style and phrasing of news articles to identify characteristics of fake news. For example, if the writing style and content do not match, it determines that the news is likely to be fake news. In this way, the characteristics of fake news can be identified by analyzing the writing style and phrasing of news articles.

[0098] The processing flow of the second embodiment will be briefly explained below.

[0099] Step 1: The content analysis unit analyzes content uploaded to social media. For example, it analyzes image metadata and pixel patterns to determine whether the image is fake or not. It also analyzes the text of news articles to assess the credibility of the content. Step 2: The fake image detection unit detects fake images from the content analyzed by the content analysis unit. For example, it analyzes the image metadata to detect editing history and traces of the use of AI to generate the fake images. It also analyzes the pixel patterns of the images to determine whether they have characteristics that differ from natural images. Step 3: The fake news detection unit detects fake news from the content analyzed by the content analysis unit. For example, it analyzes the text of news articles to detect patterns of unreliable sources and misinformation. It also compares the content of the articles with other reliable sources to check for inconsistencies. Step 4: The block execution unit automatically blocks fake content detected by the fake image detection unit and fake news detection unit. For example, if a social media post is determined to contain fake images or fake news, the block execution unit hides the post so that other users cannot view it. It also issues a warning to the poster and prevents them from uploading fake content.

[0100] 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.

[0101] 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.

[0102] 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.

[0103] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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).

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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).

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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."

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0166] 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]

[0167] 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 content analysis unit that analyzes content uploaded to SNS; a fake image detection unit that detects fake images from the content analyzed by the content analysis unit; a fake news detection unit that detects fake news from the content analyzed by the content analysis unit; a block execution unit that automatically blocks fake content detected by the fake image detection unit and the fake news detection unit. A system characterized by:

2. The fake image detection unit Analyzing the optical characteristics and shadows of the image to identify the fake image 2. The system of claim 1.

3. The fake news detection unit Analyzing the style and phrasing of news articles to identify the characteristics of said fake news 2. The system of claim 1.

4. The block execution unit In addition to blocking fake content, it will also automatically warn users of related content.

2. The system of claim 1.

5. The generating AI is Analyze the emotions of users who provide feedback and incorporate them into the learning process 2. The system of claim 1.

Images