System

Abstract

An object of the system according to the embodiment is to detect an unauthorized video and prevent the unauthorized video from spreading.SOLUTION: In one embodiment, a system comprises a feature analyzer, a detector, a context analyzer, and a monitor. The feature analysis unit analyzes a feature of the moving image. The detection unit detects an unauthorized moving image based on the feature analyzed by the feature analysis unit. The context analysis unit analyzes the context of the video detected by the detection unit and verifies the reliability. The monitoring unit monitors the moving image in real time on the basis of the reliability verified by the context analysis unit and prevents unauthorized spreading of the moving image.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 not adequately detected or prevented the spread of fraudulent videos, making it difficult to identify reliable content.

[0005] The system according to the embodiment aims to detect unauthorized videos and prevent their spread. [Means for solving the problem]

[0006] The system according to the embodiment includes a feature analysis unit, a detection unit, a context analysis unit, and a monitoring unit. The feature analysis unit analyzes features of a video. The detection unit detects fraudulent videos based on the features analyzed by the feature analysis unit. The context analysis unit analyzes the context of the video detected by the detection unit and verifies its authenticity. The monitoring unit monitors videos in real time based on the authenticity verified by the context analysis unit to prevent the spread of fraudulent videos. [Effects of the Invention]

[0007] The system according to the embodiment can detect unauthorized videos and prevent their spread. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0028] (Example 1) A deepfake detection system according to an embodiment of the present invention utilizes AI technology to detect and prevent deepfake videos. The system analyzes video characteristics, uses a learning model to detect fraudulent videos, analyzes the video context to verify authenticity, and monitors in real time to prevent the spread of fraudulent videos. In this way, the deepfake detection system minimizes the risks posed by deepfake technology, allowing users to enjoy content with peace of mind.

[0029] A deepfake detection system according to an embodiment includes a feature analysis unit, a detection unit, a context analysis unit, and a monitoring unit. The feature analysis unit analyzes video features. For example, the generation AI analyzes facial movements, facial expressions, voice consistency, background changes, and the like. The generation AI receives a video file as input and analyzes features based on the video file. The detection unit detects fraudulent videos based on the features analyzed by the feature analysis unit. For example, the generation AI uses a pre-trained model to detect fraudulent videos based on the analyzed features. The generation AI is trained using a large number of deepfake videos and legitimate videos, enabling it to identify fraudulent videos with high accuracy. The context analysis unit analyzes the context of the video detected by the detection unit to verify its authenticity. For example, the generation AI checks whether the content of the video is consistent with news articles or official announcements, and whether the information in the video is consistent with other reliable sources. The generation AI receives text data related to the video content as input and verifies its authenticity based on the text data. The monitoring unit monitors videos in real time based on the reliability verified by the context analysis unit and prevents the spread of fraudulent videos. For example, the generation AI analyzes videos uploaded to social media and video sharing sites in real time, and if a fraudulent video is detected, it immediately issues a warning or deletes it. The generation AI receives video data streamed in real time as input and performs monitoring and prevention based on that data. As a result, the deepfake detection system according to the embodiment minimizes the risks posed by deepfake technology, allowing users to use content with peace of mind. For example, it prevents the spread of fraudulent information on news sites and social media, ensuring that only reliable information is disseminated. It also reduces the risk of companies and individuals suffering reputational damage due to deepfakes.

[0030] The feature analysis unit analyzes minute pixel changes in a video and can identify unnatural changes that cannot be detected by the naked eye. For example, the feature analysis unit uses generative AI to perform a detailed analysis of pixel changes in each frame of a video to detect subtle changes. For example, it analyzes color changes and brightness fluctuations in specific areas to identify unnatural changes. This makes it possible to identify unnatural changes by analyzing subtle pixel changes.

[0031] The feature analysis unit can analyze minute fluctuations in the audio waveform of a video and detect mismatches between audio and video. For example, the feature analysis unit uses generative AI to analyze the audio waveform in a video and evaluate the synchronization between audio and video. For example, it compares the start timing of the audio with the timing of mouth movements to detect mismatches. This makes it possible to identify fraudulent videos by detecting mismatches between audio and video.

[0032] The feature analysis unit can be applied to still images and GIF animations to detect fraudulent image content. The feature analysis unit uses, for example, generative AI to analyze the features of still images and detect fraudulent image content. For example, it identifies unnatural facial features and inconsistencies in the background. This makes it possible to detect fraudulent image content by applying it to still images and GIF animations.

[0033] The feature analysis unit can also be applied to live streaming videos, enabling fraud detection in real time. The feature analysis unit uses, for example, generative AI to analyze the features of live streaming videos in real time and detect fraudulent changes. For example, it identifies unnatural facial movements and background changes in real time. This makes it possible to apply it to live streaming videos and enable fraud detection in real time.

[0034] The detection unit can develop specialized learning models for different deepfake technologies to improve detection accuracy. For example, the detection unit uses generative AI to develop a learning model specialized for GANs to improve the detection accuracy of deepfake videos. For example, it can detect facial synthesis and deformation by GANs with high accuracy. This improves detection accuracy by developing specialized learning models for different deepfake technologies.

[0035] The detection unit incorporates video metadata into the learning model and can detect inconsistencies between the metadata and video content. For example, the detection unit incorporates the shooting date and time of the video into the learning model and detects inconsistencies between the video content and the metadata. For example, it identifies cases where the season or time of day in the video does not match the shooting date and time. This makes it possible to identify fraudulent videos by detecting inconsistencies between the metadata and video content.

[0036] The detection unit can also apply the learning model to audio-only content to detect fraudulent audio. For example, the detection unit uses the learning model to analyze podcast audio and detect fraudulent audio. For example, it identifies unnatural changes in audio and signs of editing. This allows fraudulent audio to be detected by applying it to audio-only content.

[0037] The detection unit can apply the learning model to videos in different languages ​​and cultures, enabling fraud detection from a global perspective. The detection unit, for example, uses the learning model to analyze videos in different languages ​​and detect fraudulent videos. For example, it identifies mismatches between subtitles and audio and unnatural translations. This allows fraud detection to be achieved from a global perspective by applying the model to videos in different languages ​​and cultures.

[0038] The context analysis unit can analyze text information in a video and detect inconsistencies between the text and the video content. For example, the context analysis unit can use generative AI to analyze subtitles in a video and detect inconsistencies between the video content and the text. For example, it can identify cases where the content of the subtitles does not match the video. This allows the reliability of the video to be evaluated by detecting inconsistencies between the text and the video content.

[0039] The context analysis unit can analyze related social media posts and comments to verify the reliability of a video. The context analysis unit can, for example, use generative AI to analyze social media posts related to a video to verify the reliability of the video. For example, it can evaluate user reactions and comments to the content of the video. This allows the reliability of a video to be evaluated by analyzing social media posts and comments.

[0040] The context analysis unit can also be applied to news articles and blog posts to verify the reliability of text content. For example, the context analysis unit uses generative AI to analyze the content of a news article and verify whether it matches the context of the video. For example, it checks whether the content of the news article is consistent with the content of the video. This allows the reliability of text content to be verified by applying it to news articles and blog posts.

[0041] The context analysis unit can be applied to different media formats to verify the authenticity of multimedia content. For example, the context analysis unit uses generative AI to analyze the content of audio content and verify whether it matches the context of the video. For example, it checks whether the content of the audio is consistent with the content of the video. This allows the authenticity of multimedia content to be verified by applying it to different media formats.

[0042] The monitoring unit can detect network traffic anomalies during real-time video analysis and prevent the spread of fraudulent videos. The monitoring unit, for example, uses generative AI to detect network traffic anomalies during real-time video analysis. For example, it can identify large amounts of data being sent from a specific IP address. This allows the detection of network traffic anomalies and the prevention of the spread of fraudulent videos.

[0043] During real-time monitoring, the monitoring unit can analyze the IP address and device information of the video upload source to detect unauthorized uploads. For example, the monitoring unit uses generation AI to analyze the IP address of the video upload source in real time to detect unauthorized uploads. For example, it identifies unauthorized uploads from specific IP addresses. This makes it possible to detect unauthorized uploads by analyzing IP addresses and device information.

[0044] The monitoring unit can also be applied to live events and webinars to detect unauthorized content in real time. For example, the monitoring unit uses generative AI to monitor live events in real time and detect unauthorized content. For example, it identifies unauthorized video and audio during live streaming. This allows it to be applied to live events and webinars to detect unauthorized content in real time.

[0045] The monitoring unit can link different platforms to achieve integrated monitoring of fraudulent content. For example, the monitoring unit uses generative AI to link real-time monitoring of social media and video sharing sites to detect fraudulent content in an integrated manner. For example, it identifies fraudulent videos on multiple platforms. This allows different platforms to link together to achieve integrated monitoring of fraudulent content.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The deepfake detection system can also include a multimedia analyzer to accommodate different media formats. For example, the multimedia analyzer can analyze audio and text content to verify whether it matches the video. For example, it can verify whether the audio content of a podcast matches the video content. It can also verify whether the text content of a news article or blog post contradicts the video content. This allows for a comprehensive assessment of the authenticity of multimedia content by addressing different media formats.

[0048] Deepfake detection systems can also improve detection accuracy by developing specialized learning models for different deepfake technologies. For example, specialized learning models can be developed for GANs to improve the accuracy of detecting deepfake videos. For example, they can detect facial synthesis and deformations created by GANs with high accuracy. Furthermore, developing specialized learning models for different deepfake technologies can improve detection accuracy.

[0049] The deepfake detection system can also incorporate video metadata into the learning model to detect inconsistencies between the metadata and video content. The metadata analysis unit, for example, incorporates the video's shooting date and time into the learning model to detect inconsistencies between the video content and the metadata. For example, it identifies cases where the season or time of day in the video does not match the shooting date and time. It also analyzes the video's location information and device information to detect inconsistencies between the metadata and video content. This makes it possible to identify fraudulent videos by detecting inconsistencies between the metadata and video content.

[0050] The deepfake detection system can also apply the learning model to audio-only content to detect fraudulent audio. The audio analysis unit, for example, uses the learning model to analyze podcast audio and detect fraudulent audio. For example, it identifies unnatural changes in audio and signs of editing. Furthermore, by applying the learning model to audio-only content, fraudulent audio can be detected.

[0051] The deepfake detection system can also be applied to videos in different languages ​​and cultures, enabling fraud detection from a global perspective. The cross-cultural support unit, for example, uses a learning model to analyze videos in different languages ​​and detect fraudulent videos. For example, it identifies mismatches between subtitles and audio and unnatural translations. It also performs fraud detection that takes into account differences in emotional expression in different cultures. This allows the system to be applied to videos in different languages ​​and cultures, enabling fraud detection from a global perspective.

[0052] The deepfake detection system can further enhance the context analysis unit to analyze related social media posts and comments to verify the authenticity of a video. The social media analysis unit, for example, uses generative AI to analyze social media posts related to the video to verify the authenticity of the video. For example, it evaluates user reactions and comments to the video content. It also evaluates the authenticity of the video by analyzing social media posts and comments. This allows the authenticity of a video to be evaluated by analyzing social media posts and comments.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The feature analysis unit analyzes the features of the video. For example, the generation AI analyzes facial movements, facial expressions, voice consistency, background changes, etc. The generation AI receives a video file as input and analyzes the features based on that video file. Step 2: The detection unit detects fraudulent videos based on the features analyzed by the feature analysis unit. For example, the generation AI uses a pre-trained model to detect fraudulent videos based on the analyzed features. The generation AI is trained using a large number of deepfake videos and legitimate videos, and can identify fraudulent videos with high accuracy. Step 3: The context analysis unit analyzes the context of the video detected by the detection unit and verifies its reliability. For example, the generation AI checks whether the content of the video is consistent with news articles or official announcements, and whether the information in the video contradicts other reliable sources. The generation AI receives the video content and related text data as input and verifies its reliability based on them. Step 4: The monitoring unit monitors videos in real time based on the reliability verified by the context analysis unit and prevents the spread of fraudulent videos. For example, the generation AI analyzes videos uploaded to social media and video sharing sites in real time, and if a fraudulent video is detected, it immediately issues a warning or deletes it. The generation AI receives video data streamed in real time as input and uses that data to monitor and prevent the spread of fraud.

[0055] (Example 2) A deepfake detection system according to an embodiment of the present invention utilizes AI technology to detect and prevent deepfake videos. The system analyzes video characteristics, uses a learning model to detect fraudulent videos, analyzes the video context to verify authenticity, and monitors in real time to prevent the spread of fraudulent videos. In this way, the deepfake detection system minimizes the risks posed by deepfake technology, allowing users to enjoy content with peace of mind.

[0056] A deepfake detection system according to an embodiment includes a feature analysis unit, a detection unit, a context analysis unit, and a monitoring unit. The feature analysis unit analyzes video features. For example, the generation AI analyzes facial movements, facial expressions, voice consistency, background changes, and the like. The generation AI receives a video file as input and analyzes features based on the video file. The detection unit detects fraudulent videos based on the features analyzed by the feature analysis unit. For example, the generation AI uses a pre-trained model to detect fraudulent videos based on the analyzed features. The generation AI is trained using a large number of deepfake videos and legitimate videos, enabling it to identify fraudulent videos with high accuracy. The context analysis unit analyzes the context of the video detected by the detection unit to verify its authenticity. For example, the generation AI checks whether the content of the video is consistent with news articles or official announcements, and whether the information in the video is consistent with other reliable sources. The generation AI receives text data related to the video content as input and verifies its authenticity based on the text data. The monitoring unit monitors videos in real time based on the reliability verified by the context analysis unit and prevents the spread of fraudulent videos. For example, the generation AI analyzes videos uploaded to social media and video sharing sites in real time, and if a fraudulent video is detected, it immediately issues a warning or deletes it. The generation AI receives video data streamed in real time as input and performs monitoring and prevention based on that data. As a result, the deepfake detection system according to the embodiment minimizes the risks posed by deepfake technology, allowing users to use content with peace of mind. For example, it prevents the spread of fraudulent information on news sites and social media, ensuring that only reliable information is disseminated. It also reduces the risk of companies and individuals suffering reputational damage due to deepfakes.

[0057] The feature analysis unit analyzes minute pixel changes in a video and can identify unnatural changes that cannot be detected by the naked eye. For example, the feature analysis unit uses generative AI to perform a detailed analysis of pixel changes in each frame of a video to detect subtle changes. For example, it analyzes color changes and brightness fluctuations in specific areas to identify unnatural changes. This makes it possible to identify unnatural changes by analyzing subtle pixel changes.

[0058] The feature analysis unit can analyze minute fluctuations in the audio waveform of a video and detect mismatches between audio and video. For example, the feature analysis unit uses generative AI to analyze the audio waveform in a video and evaluate the synchronization between audio and video. For example, it compares the start timing of the audio with the timing of mouth movements to detect mismatches. This makes it possible to identify fraudulent videos by detecting mismatches between audio and video.

[0059] The feature analysis unit uses an emotion estimation function to estimate emotions from the facial expressions and tone of voice of people in the video, and can detect unnatural changes in emotions. For example, the feature analysis unit uses generative AI to analyze the facial expressions of people in the video and estimate emotions. For example, it detects unnatural changes in emotions, such as a sudden change from smiling to anger. This makes it possible to identify fraudulent videos by detecting unnatural changes in emotions.

[0060] The feature analysis unit can be applied to still images and GIF animations to detect fraudulent image content. The feature analysis unit uses, for example, generative AI to analyze the features of still images and detect fraudulent image content. For example, it identifies unnatural facial features and inconsistencies in the background. This makes it possible to detect fraudulent image content by applying it to still images and GIF animations.

[0061] The feature analysis unit can also be applied to live streaming videos, enabling fraud detection in real time. The feature analysis unit uses, for example, generative AI to analyze the features of live streaming videos in real time and detect fraudulent changes. For example, it identifies unnatural facial movements and background changes in real time. This makes it possible to apply it to live streaming videos and enable fraud detection in real time.

[0062] The feature analysis unit uses an emotion estimation function to analyze emotional changes of people in a video in real time and detect emotional inconsistencies. For example, the feature analysis unit uses generative AI to analyze the facial expressions of people in a video in real time and detect emotional changes. For example, it identifies unnatural emotional changes, such as a sudden change from smiling to anger, in real time. This makes it possible to identify fraudulent videos by detecting emotional inconsistencies in real time.

[0063] The detection unit can develop specialized learning models for different deepfake technologies to improve detection accuracy. For example, the detection unit uses generative AI to develop a learning model specialized for GANs to improve the detection accuracy of deepfake videos. For example, it can detect facial synthesis and deformation by GANs with high accuracy. This improves detection accuracy by developing specialized learning models for different deepfake technologies.

[0064] The detection unit incorporates video metadata into the learning model and can detect inconsistencies between the metadata and video content. For example, the detection unit incorporates the shooting date and time of the video into the learning model and detects inconsistencies between the video content and the metadata. For example, it identifies cases where the season or time of day in the video does not match the shooting date and time. This makes it possible to identify fraudulent videos by detecting inconsistencies between the metadata and video content.

[0065] The detection unit can use the emotion estimation function to add emotion data to the learning model and detect fraudulent videos based on emotional discrepancies. For example, the detection unit adds emotion data to the learning model and detects emotional discrepancies from the facial expressions and tone of voice of people in the video. For example, it identifies cases where a person is smiling but speaking with an angry voice. This improves detection accuracy by detecting fraudulent videos based on emotional discrepancies.

[0066] The detection unit can also apply the learning model to audio-only content to detect fraudulent audio. For example, the detection unit uses the learning model to analyze podcast audio and detect fraudulent audio. For example, it identifies unnatural changes in audio and signs of editing. This allows fraudulent audio to be detected by applying it to audio-only content.

[0067] The detection unit can apply the learning model to videos in different languages ​​and cultures, enabling fraud detection from a global perspective. The detection unit, for example, uses the learning model to analyze videos in different languages ​​and detect fraudulent videos. For example, it identifies mismatches between subtitles and audio and unnatural translations. This allows fraud detection to be achieved from a global perspective by applying the model to videos in different languages ​​and cultures.

[0068] The detection unit can use the emotion estimation function to add emotion data to the learning model and perform fraud detection that takes into account differences in emotional expression across different cultures. For example, the detection unit adds emotion data from different cultures to the learning model and performs fraud detection that takes into account differences in emotional expression. For example, it identifies changes in emotions based on cultural background. This improves the accuracy of fraud detection by taking into account differences in emotional expression across different cultures.

[0069] The context analysis unit can analyze text information in a video and detect inconsistencies between the text and the video content. For example, the context analysis unit can use generative AI to analyze subtitles in a video and detect inconsistencies between the video content and the text. For example, it can identify cases where the content of the subtitles does not match the video. This allows the reliability of the video to be evaluated by detecting inconsistencies between the text and the video content.

[0070] The context analysis unit can analyze related social media posts and comments to verify the reliability of a video. The context analysis unit can, for example, use generative AI to analyze social media posts related to a video to verify the reliability of the video. For example, it can evaluate user reactions and comments to the content of the video. This allows the reliability of a video to be evaluated by analyzing social media posts and comments.

[0071] The context analysis unit uses an emotion estimation function to verify the match between the content of a person's speech and their emotion in the video, and can detect unnatural changes in emotion. For example, the context analysis unit uses generative AI to analyze the content of a person's speech in the video and verify the match between their emotion. For example, it identifies cases where the speech is positive but the facial expression is negative. This allows unnatural changes in emotion to be detected by verifying the match between the content of the speech and their emotion.

[0072] The context analysis unit can also be applied to news articles and blog posts to verify the reliability of text content. For example, the context analysis unit uses generative AI to analyze the content of a news article and verify whether it matches the context of the video. For example, it checks whether the content of the news article is consistent with the content of the video. This allows the reliability of text content to be verified by applying it to news articles and blog posts.

[0073] The context analysis unit can be applied to different media formats to verify the authenticity of multimedia content. For example, the context analysis unit uses generative AI to analyze the content of audio content and verify whether it matches the context of the video. For example, it checks whether the content of the audio is consistent with the content of the video. This allows the authenticity of multimedia content to be verified by applying it to different media formats.

[0074] The context analysis unit uses an emotion estimation function to analyze changes in the emotions of people in a video and can verify the reliability of the context based on emotional inconsistencies. The context analysis unit, for example, uses generative AI to analyze the facial expressions of people in a video and verify the reliability of the context based on changes in emotions. For example, it identifies cases where facial expressions change unnaturally. This allows the reliability of the context to be verified based on emotional inconsistencies, thereby evaluating the reliability of the video.

[0075] The monitoring unit can detect network traffic anomalies during real-time video analysis and prevent the spread of fraudulent videos. The monitoring unit, for example, uses generative AI to detect network traffic anomalies during real-time video analysis. For example, it can identify large amounts of data being sent from a specific IP address. This allows the detection of network traffic anomalies and the prevention of the spread of fraudulent videos.

[0076] During real-time monitoring, the monitoring unit can analyze the IP address and device information of the video upload source to detect unauthorized uploads. For example, the monitoring unit uses generation AI to analyze the IP address of the video upload source in real time to detect unauthorized uploads. For example, it identifies unauthorized uploads from specific IP addresses. This makes it possible to detect unauthorized uploads by analyzing IP addresses and device information.

[0077] The monitoring unit uses an emotion estimation function to monitor viewers' emotional reactions during real-time video analysis, thereby preventing the spread of fraudulent videos. The monitoring unit uses, for example, generative AI to monitor viewers' emotional reactions during real-time video analysis. For example, it analyzes viewers' facial expressions and tone of voice to detect changes in emotion. In this way, by monitoring viewers' emotional reactions, it is possible to prevent the spread of fraudulent videos.

[0078] The monitoring unit can also be applied to live events and webinars to detect unauthorized content in real time. For example, the monitoring unit uses generative AI to monitor live events in real time and detect unauthorized content. For example, it identifies unauthorized video and audio during live streaming. This allows it to be applied to live events and webinars to detect unauthorized content in real time.

[0079] The monitoring unit can link different platforms to achieve integrated monitoring of fraudulent content. For example, the monitoring unit uses generative AI to link real-time monitoring of social media and video sharing sites to detect fraudulent content in an integrated manner. For example, it identifies fraudulent videos on multiple platforms. This allows different platforms to link together to achieve integrated monitoring of fraudulent content.

[0080] The monitoring unit can use the emotion estimation function to prevent the spread of fraudulent videos based on viewers' emotional reactions in real-time video analysis. The monitoring unit, for example, uses generative AI to prevent the spread of fraudulent videos based on viewers' emotional reactions in real-time video analysis. For example, it analyzes viewers' facial expressions and tone of voice to detect changes in emotions. This allows the detection of fraudulent videos in real time by preventing the spread of fraudulent videos based on viewers' emotional reactions.

[0081] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0082] The deepfake detection system can also include a multimedia analyzer to accommodate different media formats. For example, the multimedia analyzer can analyze audio and text content to verify whether it matches the video. For example, it can verify whether the audio content of a podcast matches the video content. It can also verify whether the text content of a news article or blog post contradicts the video content. This allows for a comprehensive assessment of the authenticity of multimedia content by addressing different media formats.

[0083] The deepfake detection system may also include an emotion evaluation unit that estimates the user's emotions and evaluates the reliability of the video based on the estimated emotions. The emotion evaluation unit, for example, analyzes the facial expressions and tone of voice of people in the video to detect changes in their emotions. For example, it identifies unnatural emotional changes, such as a sudden change from smiling to anger. It also monitors the viewer's emotional reactions and analyzes their facial expressions and tone of voice to detect changes in their emotions. This improves detection accuracy by evaluating the reliability of the video based on emotional discrepancies.

[0084] The deepfake detection system can also include an emotion analysis unit that takes into account differences in emotional expression across different cultures. For example, the emotion analysis unit adds emotional data from different cultures to the learning model to detect fraud that takes differences in emotional expression into account. For example, it identifies changes in emotions based on cultural background. It also analyzes videos in different languages ​​to identify discrepancies between subtitles and audio and unnatural translations. This improves the accuracy of fraud detection by taking into account differences in emotional expression across different cultures.

[0085] Deepfake detection systems can also improve detection accuracy by developing specialized learning models for different deepfake technologies. For example, specialized learning models can be developed for GANs to improve the accuracy of detecting deepfake videos. For example, they can detect facial synthesis and deformations created by GANs with high accuracy. Furthermore, developing specialized learning models for different deepfake technologies can improve detection accuracy.

[0086] The deepfake detection system can also incorporate video metadata into the learning model to detect inconsistencies between the metadata and video content. The metadata analysis unit, for example, incorporates the video's shooting date and time into the learning model to detect inconsistencies between the video content and the metadata. For example, it identifies cases where the season or time of day in the video does not match the shooting date and time. It also analyzes the video's location information and device information to detect inconsistencies between the metadata and video content. This makes it possible to identify fraudulent videos by detecting inconsistencies between the metadata and video content.

[0087] The deepfake detection system can also use an emotion estimation function to add emotional data to the learning model and detect fraudulent videos based on emotional discrepancies. The emotion data analysis unit, for example, adds emotional data to the learning model and detects emotional discrepancies from the facial expressions and tone of voice of people in the video. For example, it can identify cases where a person is smiling but speaking with an angry voice. In addition, by detecting fraudulent videos based on emotional discrepancies, detection accuracy is improved. This improves detection accuracy by detecting fraudulent videos based on emotional discrepancies.

[0088] The deepfake detection system can also apply the learning model to audio-only content to detect fraudulent audio. The audio analysis unit, for example, uses the learning model to analyze podcast audio and detect fraudulent audio. For example, it identifies unnatural changes in audio and signs of editing. Furthermore, by applying the learning model to audio-only content, fraudulent audio can be detected.

[0089] The deepfake detection system can also be applied to videos in different languages ​​and cultures, enabling fraud detection from a global perspective. The cross-cultural support unit, for example, uses a learning model to analyze videos in different languages ​​and detect fraudulent videos. For example, it identifies mismatches between subtitles and audio and unnatural translations. It also performs fraud detection that takes into account differences in emotional expression in different cultures. This allows the system to be applied to videos in different languages ​​and cultures, enabling fraud detection from a global perspective.

[0090] The deepfake detection system can also use an emotion estimation function to add emotional data to the learning model and perform fraud detection that takes into account differences in emotional expression across different cultures. The emotional culture analysis unit, for example, adds emotional data from different cultures to the learning model and performs fraud detection that takes into account differences in emotional expression. For example, it identifies changes in emotions based on cultural background. In addition, by taking into account differences in emotional expression across different cultures, the accuracy of fraud detection is improved. This improves the accuracy of fraud detection by taking into account differences in emotional expression across different cultures.

[0091] The deepfake detection system can further enhance the context analysis unit to analyze related social media posts and comments to verify the authenticity of a video. The social media analysis unit, for example, uses generative AI to analyze social media posts related to the video to verify the authenticity of the video. For example, it evaluates user reactions and comments to the video content. It also evaluates the authenticity of the video by analyzing social media posts and comments. This allows the authenticity of a video to be evaluated by analyzing social media posts and comments.

[0092] The processing flow of the second embodiment will be briefly explained below.

[0093] Step 1: The feature analysis unit analyzes the features of the video. For example, the generation AI analyzes facial movements, facial expressions, voice consistency, background changes, etc. The generation AI receives a video file as input and analyzes the features based on that video file. Step 2: The detection unit detects fraudulent videos based on the features analyzed by the feature analysis unit. For example, the generation AI uses a pre-trained model to detect fraudulent videos based on the analyzed features. The generation AI is trained using a large number of deepfake videos and legitimate videos, and can identify fraudulent videos with high accuracy. Step 3: The context analysis unit analyzes the context of the video detected by the detection unit and verifies its reliability. For example, the generation AI checks whether the content of the video is consistent with news articles or official announcements, and whether the information in the video contradicts other reliable sources. The generation AI receives the video content and related text data as input and verifies its reliability based on them. Step 4: The monitoring unit monitors videos in real time based on the reliability verified by the context analysis unit and prevents the spread of fraudulent videos. For example, the generation AI analyzes videos uploaded to social media and video sharing sites in real time, and if a fraudulent video is detected, it immediately issues a warning or deletes it. The generation AI receives video data streamed in real time as input and uses that data to monitor and prevent the spread of fraud.

[0094] 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.

[0095] 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.

[0096] 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.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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).

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0113] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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).

[0118] 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.

[0119] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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."

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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]

[0161] 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 feature analysis unit that analyzes the features of the video; a detection unit that detects fraudulent videos based on the features analyzed by the feature analysis unit; a context analysis unit that analyzes the context of the video detected by the detection unit and verifies its reliability; a monitoring unit that monitors videos in real time based on the reliability verified by the context analysis unit and prevents the spread of unauthorized videos. A system characterized by:

2. The feature analysis unit Analyzes minute pixel changes in video to identify unnatural changes that are invisible to the naked eye 2. The system of claim 1.

3. The feature analysis unit Applies to still images and animated GIFs to detect malicious image content 2. The system of claim 1.

4. The detection unit Develop specialized learning models for different deepfake technologies to improve detection accuracy 2. The system of claim 1.

5. The context analysis unit Analyzes text information in videos and detects discrepancies between the text and video content 2. The system of claim 1.

6. The monitoring unit Real-time video analysis detects anomalies in network traffic and prevents the spread of unauthorized videos.

2. The system of claim 1.

7. The feature analysis unit Using emotion estimation functionality, the system estimates emotions from facial expressions and tone of voice of people in the video and detects unnatural emotional changes.

2. The system of claim 1.

Images