System

Abstract

An object of the system according to the embodiment is to detect violating content of a moving image before the content is released and to appropriately handle the violating content.SOLUTION: A system according to an embodiment includes a video analysis unit, a violation detection unit, a classification unit, a deletion unit, and a feedback unit. The moving image analysis unit analyzes contents of a moving image. The violation detection unit detects violating content from the video analyzed by the video analysis unit. The classification unit classifies the violating content detected by the violation detection unit. The deletion unit deletes the violating content classified by the classification unit. The feedback unit feeds back information on the violating content to the poster.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] With conventional technology, it is difficult to detect 100% of infringing video content before it is published, which could lead to greater damage.

[0005] The system according to the embodiment aims to detect infringing content in a video before it is made public and to deal with it appropriately. [Means for solving the problem]

[0006] The system according to the embodiment includes a video analysis unit, a violation detection unit, a classification unit, a deletion unit, and a feedback unit. The video analysis unit analyzes the content of a video. The violation detection unit detects violating content from the video analyzed by the video analysis unit. The classification unit classifies the violating content detected by the violation detection unit. The deletion unit deletes the violating content classified by the classification unit. The feedback unit provides feedback regarding the violating content to the poster. [Effects of the Invention]

[0007] The system according to the embodiment can detect infringing content in a video before it is published and deal with it appropriately. [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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) The AI ​​monitoring system according to the embodiment of the present invention is a system that detects 100% of infringing video content before it is published, thereby minimizing damage to victims.

[0029] An AI surveillance system according to an embodiment includes a video analysis unit, a violation detection unit, a classification unit, a deletion unit, and a feedback unit. The video analysis unit analyzes the content of a video. For example, the video analysis unit receives a video file as input and analyzes its content. The video analysis unit can analyze elements such as video, audio, and text. For example, the video analysis unit analyzes each frame of a video to detect specific scenes. The video analysis unit can also analyze audio data to detect specific audio patterns. Furthermore, the video analysis unit can analyze text data within a video to detect inappropriate words and expressions. The violation detection unit detects violating content from the video analyzed by the video analysis unit. For example, the violation detection unit detects violent scenes and inappropriate words. The violation detection unit can also detect discriminatory remarks and privacy-violating content. Furthermore, the violation detection unit can analyze background and environmental sounds in a video to detect signs of violating content. The classification unit classifies the violating content detected by the violation detection unit. For example, the classification unit classifies the content into violent content, discriminatory content, privacy-violating content, etc. The classification unit can also classify content according to the type and severity of the violation. The deletion unit deletes the violating content classified by the classification unit. For example, the deletion unit automatically deletes the violating content before the video is uploaded. The deletion unit can also delete the violating content based on a manual deletion instruction. The deletion unit can also set the timing and method of deletion. The feedback unit provides feedback regarding the violating content to the poster. For example, the feedback unit can specifically explain which part of the content is violating and how to correct it. The feedback unit can also set the notification method and detailed feedback information. As a result, the AI ​​monitoring system according to the embodiment can detect 100% of violating content in videos before they are published, minimizing damage to victims. For example, videos containing violent scenes or discriminatory remarks can be detected and automatically deleted before they are published, protecting the privacy and safety of victims.Additionally, providing specific feedback to posters can help prevent the recurrence of infringing content.

[0030] The video analysis unit analyzes not only the content of a video but also its metadata, enabling a comprehensive assessment of the possibility of violating content. For example, before a video is uploaded, the generation AI analyzes metadata such as the video title, description, and tags to assess the possibility of violating content. For example, if a violent title or discriminatory tags are included, this will be detected. The generation AI also analyzes the video metadata to check whether it contains inappropriate information that does not match the content. For example, if the description contains misleading language, this will be detected. Furthermore, the video metadata is analyzed to detect patterns similar to past violating content. For example, if tags or titles that have previously been problematic are used again, this will be detected. This improves the accuracy of detecting violating content by also analyzing video metadata.

[0031] The video analysis unit can analyze background and environmental sounds of a video to detect signs of violating content. For example, the video analysis unit analyzes the background sounds of a video to detect whether it contains violent sounds or inappropriate language. For example, it detects sounds such as gunshots and screams. The generative AI also analyzes environmental sounds to detect signs of violating content. For example, it detects discriminatory remarks or insulting language. Furthermore, it analyzes the audio data of the video to identify inappropriate elements contained in the background sounds. For example, it detects violent music or inappropriate sound effects. This improves the accuracy of detecting violating content by analyzing the background and environmental sounds of a video.

[0032] The video analysis unit analyzes the video's scenario and script, and is able to assess the possibility of violating content in advance. For example, the video analysis unit uses a generation AI to analyze the video's scenario and script and assess the possibility of violating content. For example, it checks whether it contains violent scenes or discriminatory remarks. The generation AI also analyzes the video's script to detect whether the content contains inappropriate elements. For example, it detects if it contains privacy violations or offensive language. Furthermore, it analyzes the video's scenario and detects patterns similar to past violating content. For example, it detects if elements from a scenario that has previously been problematic are used again. This makes it possible to assess the possibility of violating content in advance by analyzing the video's scenario and script.

[0033] The video analysis unit can analyze video thumbnail images to detect whether they contain visually inappropriate elements. For example, the video analysis unit uses a generation AI to analyze video thumbnail images to detect whether they contain visually inappropriate elements. For example, if they contain violent scenes or discriminatory language, this will be detected. The generation AI also analyzes thumbnail images to check whether they contain inappropriate information that does not match the content. For example, if misleading images are used, this will be detected. Furthermore, the video thumbnail images are analyzed to detect patterns similar to past violating content. For example, if image elements that have previously been problematic are used again, this will be detected. This makes it possible to detect visually inappropriate elements with a high degree of accuracy by also analyzing video thumbnail images.

[0034] The violation detection unit takes into account the continuity and context between frames when analyzing each frame of a video, thereby improving the accuracy of detecting violating content. For example, when the generation AI analyzes each frame of a video, the violation detection unit takes into account the continuity between frames, thereby improving the accuracy of detecting violating content. For example, it detects violent scenes in consecutive frames. Furthermore, by analyzing the context of the video and considering the relationship between frames, the accuracy of detecting violating content is improved. For example, it understands the flow of scenes and identifies inappropriate content. Furthermore, by taking into account the continuity and context between frames, a system is constructed in which the generation AI detects violating content with high accuracy. For example, it analyzes the context of scenes and identifies violating content. In this way, by considering the continuity and context between frames, the accuracy of detecting violating content is improved.

[0035] The violation detection unit can analyze text within a video to detect inappropriate words and expressions. For example, the generation AI analyzes subtitles and captions within a video to detect inappropriate words and expressions. For example, if discriminatory remarks or insulting language are included, this will be detected. The generation AI also analyzes text data within the video to check whether the content contains inappropriate elements. For example, if violent language or language that violates privacy is included, this will be detected. Furthermore, the text within the video is analyzed to detect patterns similar to past violating content. For example, if words or expressions that have been problematic in the past are used again, this will be detected. In this way, by analyzing the text within the video, inappropriate words and expressions can be detected with high accuracy.

[0036] When analyzing each frame of a video, the violation detection unit simultaneously analyzes footage from different viewpoints and camera angles, thereby improving the accuracy of detecting violating content. For example, when the generation AI analyzes each frame of a video, the violation detection unit simultaneously analyzes footage from different viewpoints and camera angles, thereby improving the accuracy of detecting violating content. For example, it analyzes footage from multiple camera angles to detect violent scenes. Furthermore, by analyzing footage from different viewpoints and considering the correlation between frames, the accuracy of detecting violating content is improved. For example, it integrates footage from different camera angles to identify inappropriate content. Furthermore, it simultaneously analyzes footage from different viewpoints and camera angles, building a system in which the generation AI detects violating content with high accuracy. For example, it analyzes footage from multiple viewpoints and identifies violating content. In this way, by analyzing footage from different viewpoints and camera angles, the accuracy of detecting violating content is improved.

[0037] The violation detection unit can analyze the audio data of a video and detect inappropriate words and expressions using speech recognition technology. For example, the violation detection unit uses a generation AI to analyze the audio data of a video and detect inappropriate words and expressions using speech recognition technology. For example, if discriminatory remarks or insulting language are included, this will be detected. The generation AI also analyzes the audio data to check whether the content contains inappropriate elements. For example, if violent language or language that violates privacy is included, this will be detected. Furthermore, the audio data of the video is analyzed to detect patterns similar to past violating content. For example, if words or expressions that have been problematic in the past are used again, this will be detected. As a result, using speech recognition technology makes it possible to detect inappropriate words and expressions from audio data with a high degree of accuracy.

[0038] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0039] The AI ​​monitoring system can also analyze users' viewing history and improve the accuracy of detecting violating content based on trends in past viewing of content. For example, it can analyze the genre and content of videos a user has previously viewed, and if there is a lot of violating content in a particular genre, it can focus on analyzing videos of that genre. It can also detect new videos with similar patterns based on particularly problematic content among the videos a user has previously viewed. Furthermore, by analyzing a user's viewing history and finding that violating content tends to be viewed more frequently during certain times of the day or on certain days of the week, it can focus on analyzing videos uploaded during those times or on those days. In this way, utilizing users' viewing history can improve the accuracy of detecting violating content.

[0040] AI monitoring systems can also be equipped with real-time detection of violating content. For example, they can analyze videos in real time during live streaming and immediately issue a warning if violating content is detected. Real-time analysis can also be used to automatically block scenes containing violating content. Furthermore, feedback from viewers can be collected in real time during live streaming to help detect violating content. This real-time detection of violating content can prevent the spread of violating content during live streaming.

[0041] AI monitoring systems can also be equipped with multilingual analysis capabilities to accommodate different languages ​​and cultures. For example, they can analyze audio and text in videos in multiple languages ​​to detect inappropriate words and expressions in each language. They can also take into account standards for violating content in different cultures and perform appropriate analysis for each culture. Furthermore, multilingual analysis capabilities can be used to automatically translate video subtitles and captions, and then detect violating content based on the translated content. This ability to accommodate different languages ​​and cultures improves the accuracy of detecting violating content from a global perspective.

[0042] The AI ​​monitoring system can also analyze a poster's past posting history to evaluate the possibility of violating content before uploading a video. For example, if a poster has a history of posting violating content in the past, it will focus on analyzing that poster's new videos. It can also detect violating content with specific patterns based on a poster's past posting history. Furthermore, it can analyze a poster's past posting history and provide feedback to prevent the recurrence of violating content. In this way, by utilizing a poster's past posting history, the accuracy of detecting violating content can be improved.

[0043] The AI ​​monitoring system can also analyze the poster's intent before uploading a video to assess the possibility of violating content. For example, it can analyze the intention stated by the poster in the video description and tags to assess the possibility of violating content. It can also analyze the poster's past posting history and comments to detect violating content with specific intent. It can also analyze the poster's intent and provide feedback to prevent the recurrence of violating content. By analyzing the poster's intent, the system can improve the accuracy of detecting violating content.

[0044] The AI ​​monitoring system can also analyze the poster's social media activity before uploading a video to assess the possibility of violating content. For example, it can analyze what the poster has previously said on social media to assess the possibility of violating content. It can also detect violating content with specific patterns based on the poster's social media activity history. It can also analyze the poster's social media activity and provide feedback to prevent the recurrence of violating content. In this way, by utilizing the poster's social media activity, the accuracy of detecting violating content can be improved.

[0045] The processing flow of the first embodiment will be briefly explained below.

[0046] Step 1: The video analysis unit analyzes the content of the video. For example, the video analysis unit receives a video file as input and analyzes its content. The video analysis unit can analyze elements such as video, audio, and text. For example, the video analysis unit analyzes each frame of the video to detect specific scenes. The video analysis unit can also analyze audio data to detect specific audio patterns. Furthermore, the video analysis unit can analyze text data within the video to detect inappropriate words and expressions. Step 2: The violation detection unit detects violating content from the video analyzed by the video analysis unit. For example, the violation detection unit detects violent scenes and inappropriate language. The violation detection unit can also detect discriminatory remarks and privacy violation content. Furthermore, the violation detection unit can analyze background and environmental sounds in the video to detect signs of violating content. Step 3: The classification unit classifies the violating content detected by the violation detection unit. For example, the classification unit classifies the content into violent content, discriminatory content, privacy violation content, etc. The classification unit can also classify the content according to the type and degree of violation. Step 4: The deletion unit deletes the violating content classified by the classification unit. For example, the deletion unit automatically deletes the violating content before the video is uploaded. The deletion unit can also delete the violating content based on a manual deletion instruction. Furthermore, the deletion unit can set the timing and method of deletion. Step 5: The feedback unit provides the poster with information about the infringing content. For example, the feedback unit may explain in detail which part is in violation and how to correct it. The feedback unit may also set notification methods and detailed feedback information.

[0047] (Example 2) The AI ​​monitoring system according to the embodiment of the present invention is a system that detects 100% of infringing video content before it is published, thereby minimizing damage to victims.

[0048] An AI surveillance system according to an embodiment includes a video analysis unit, a violation detection unit, a classification unit, a deletion unit, and a feedback unit. The video analysis unit analyzes the content of a video. For example, the video analysis unit receives a video file as input and analyzes its content. The video analysis unit can analyze elements such as video, audio, and text. For example, the video analysis unit analyzes each frame of a video to detect specific scenes. The video analysis unit can also analyze audio data to detect specific audio patterns. Furthermore, the video analysis unit can analyze text data within a video to detect inappropriate words and expressions. The violation detection unit detects violating content from the video analyzed by the video analysis unit. For example, the violation detection unit detects violent scenes and inappropriate words. The violation detection unit can also detect discriminatory remarks and privacy-violating content. Furthermore, the violation detection unit can analyze background and environmental sounds in a video to detect signs of violating content. The classification unit classifies the violating content detected by the violation detection unit. For example, the classification unit classifies the content into violent content, discriminatory content, privacy-violating content, etc. The classification unit can also classify content according to the type and severity of the violation. The deletion unit deletes the violating content classified by the classification unit. For example, the deletion unit automatically deletes the violating content before the video is uploaded. The deletion unit can also delete the violating content based on a manual deletion instruction. The deletion unit can also set the timing and method of deletion. The feedback unit provides feedback regarding the violating content to the poster. For example, the feedback unit can specifically explain which part of the content is violating and how to correct it. The feedback unit can also set the notification method and detailed feedback information. As a result, the AI ​​monitoring system according to the embodiment can detect 100% of violating content in videos before they are published, minimizing damage to victims. For example, videos containing violent scenes or discriminatory remarks can be detected and automatically deleted before they are published, protecting the privacy and safety of victims.Additionally, providing specific feedback to posters can help prevent the recurrence of infringing content.

[0049] The video analysis unit analyzes not only the content of a video but also its metadata, enabling a comprehensive assessment of the possibility of violating content. For example, before a video is uploaded, the generation AI analyzes metadata such as the video title, description, and tags to assess the possibility of violating content. For example, if a violent title or discriminatory tags are included, this will be detected. The generation AI also analyzes the video metadata to check whether it contains inappropriate information that does not match the content. For example, if the description contains misleading language, this will be detected. Furthermore, the video metadata is analyzed to detect patterns similar to past violating content. For example, if tags or titles that have previously been problematic are used again, this will be detected. This improves the accuracy of detecting violating content by also analyzing video metadata.

[0050] The video analysis unit can analyze background and environmental sounds of a video to detect signs of violating content. For example, the video analysis unit analyzes the background sounds of a video to detect whether it contains violent sounds or inappropriate language. For example, it detects sounds such as gunshots and screams. The generative AI also analyzes environmental sounds to detect signs of violating content. For example, it detects discriminatory remarks or insulting language. Furthermore, it analyzes the audio data of the video to identify inappropriate elements contained in the background sounds. For example, it detects violent music or inappropriate sound effects. This improves the accuracy of detecting violating content by analyzing the background and environmental sounds of a video.

[0051] The video analysis unit can use the emotion estimation function to analyze the facial expressions and tone of voice of characters in a video to detect emotionally inappropriate scenes. For example, the video analysis unit uses the emotion estimation function to analyze the facial expressions of characters in a video to detect scenes with strong negative emotions such as anger or sadness. It also analyzes the tone of voice of characters in a video to identify emotionally inappropriate scenes. For example, if yelling or crying is included, it is detected. Furthermore, the emotion estimation function is used to track emotional changes of characters in a video to identify emotionally inappropriate scenes. For example, it detects scenes with sudden emotional changes. As a result, the emotion estimation function can be used to detect emotionally inappropriate scenes with high accuracy.

[0052] The video analysis unit analyzes the video's scenario and script, and is able to assess the possibility of violating content in advance. For example, the video analysis unit uses a generation AI to analyze the video's scenario and script and assess the possibility of violating content. For example, it checks whether it contains violent scenes or discriminatory remarks. The generation AI also analyzes the video's script to detect whether the content contains inappropriate elements. For example, it detects if it contains privacy violations or offensive language. Furthermore, it analyzes the video's scenario and detects patterns similar to past violating content. For example, it detects if elements from a scenario that has previously been problematic are used again. This makes it possible to assess the possibility of violating content in advance by analyzing the video's scenario and script.

[0053] The video analysis unit can analyze video thumbnail images to detect whether they contain visually inappropriate elements. For example, the video analysis unit uses a generation AI to analyze video thumbnail images to detect whether they contain visually inappropriate elements. For example, if they contain violent scenes or discriminatory language, this will be detected. The generation AI also analyzes thumbnail images to check whether they contain inappropriate information that does not match the content. For example, if misleading images are used, this will be detected. Furthermore, the video thumbnail images are analyzed to detect patterns similar to past violating content. For example, if image elements that have previously been problematic are used again, this will be detected. This makes it possible to detect visually inappropriate elements with a high degree of accuracy by also analyzing video thumbnail images.

[0054] The video analysis unit uses the emotion estimation function to predict what emotions the viewer of a video will feel and can provide advance warning of videos that may evoke negative emotions. The video analysis unit, for example, uses the emotion estimation function to predict what emotions the viewer of a video will feel and can provide advance warning of videos that may evoke negative emotions. For example, it detects scenes that make the viewer feel anger or sadness. It also analyzes the content of videos and builds a system that predicts the viewer's emotional response. For example, it identifies scenes that may make the viewer feel uncomfortable. It also uses the emotion estimation function to predict the viewer's emotional response and develops a system that provides advance warning of videos that may evoke negative emotions. For example, it detects scenes that make the viewer feel fear. This makes it possible to predict the viewer's emotions and provide advance warning of videos that may evoke negative emotions.

[0055] The violation detection unit takes into account the continuity and context between frames when analyzing each frame of a video, thereby improving the accuracy of detecting violating content. For example, when the generation AI analyzes each frame of a video, the violation detection unit takes into account the continuity between frames, thereby improving the accuracy of detecting violating content. For example, it detects violent scenes in consecutive frames. Furthermore, by analyzing the context of the video and considering the relationship between frames, the accuracy of detecting violating content is improved. For example, it understands the flow of scenes and identifies inappropriate content. Furthermore, by taking into account the continuity and context between frames, a system is constructed in which the generation AI detects violating content with high accuracy. For example, it analyzes the context of scenes and identifies violating content. In this way, by considering the continuity and context between frames, the accuracy of detecting violating content is improved.

[0056] The violation detection unit can analyze text within a video to detect inappropriate words and expressions. For example, the generation AI analyzes subtitles and captions within a video to detect inappropriate words and expressions. For example, if discriminatory remarks or insulting language are included, this will be detected. The generation AI also analyzes text data within the video to check whether the content contains inappropriate elements. For example, if violent language or language that violates privacy is included, this will be detected. Furthermore, the text within the video is analyzed to detect patterns similar to past violating content. For example, if words or expressions that have been problematic in the past are used again, this will be detected. In this way, by analyzing the text within the video, inappropriate words and expressions can be detected with high accuracy.

[0057] When analyzing each frame of a video, the violation detection unit simultaneously analyzes footage from different viewpoints and camera angles, thereby improving the accuracy of detecting violating content. For example, when the generation AI analyzes each frame of a video, the violation detection unit simultaneously analyzes footage from different viewpoints and camera angles, thereby improving the accuracy of detecting violating content. For example, it analyzes footage from multiple camera angles to detect violent scenes. Furthermore, by analyzing footage from different viewpoints and considering the correlation between frames, the accuracy of detecting violating content is improved. For example, it integrates footage from different camera angles to identify inappropriate content. Furthermore, it simultaneously analyzes footage from different viewpoints and camera angles, building a system in which the generation AI detects violating content with high accuracy. For example, it analyzes footage from multiple viewpoints and identifies violating content. In this way, by analyzing footage from different viewpoints and camera angles, the accuracy of detecting violating content is improved.

[0058] The violation detection unit can analyze the audio data of a video and detect inappropriate words and expressions using speech recognition technology. For example, the violation detection unit uses a generation AI to analyze the audio data of a video and detect inappropriate words and expressions using speech recognition technology. For example, if discriminatory remarks or insulting language are included, this will be detected. The generation AI also analyzes the audio data to check whether the content contains inappropriate elements. For example, if violent language or language that violates privacy is included, this will be detected. Furthermore, the audio data of the video is analyzed to detect patterns similar to past violating content. For example, if words or expressions that have been problematic in the past are used again, this will be detected. As a result, using speech recognition technology makes it possible to detect inappropriate words and expressions from audio data with a high degree of accuracy.

[0059] The violation detection unit can use the emotion estimation function to predict what emotions the viewer of a video will feel and provide advance warning of scenes that may evoke negative emotions. The violation detection unit, for example, uses the emotion estimation function to predict what emotions the viewer of a video will feel and provide advance warning of scenes that may evoke negative emotions. For example, it detects scenes in which the viewer feels anger or sadness. It also builds a system that analyzes the content of the video and predicts the viewer's emotional response. For example, it identifies scenes that may cause the viewer to feel uncomfortable. It also uses the emotion estimation function to predict the viewer's emotional response and develops a system that provides advance warning of scenes that may evoke negative emotions. For example, it detects scenes in which the viewer feels fear. This makes it possible to predict the viewer's emotions and provide advance warning of scenes that may evoke negative emotions.

[0060] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0061] The AI ​​monitoring system can also analyze users' viewing history and improve the accuracy of detecting violating content based on trends in past viewing of content. For example, it can analyze the genre and content of videos a user has previously viewed, and if there is a lot of violating content in a particular genre, it can focus on analyzing videos of that genre. It can also detect new videos with similar patterns based on particularly problematic content among the videos a user has previously viewed. Furthermore, by analyzing a user's viewing history and finding that violating content tends to be viewed more frequently during certain times of the day or on certain days of the week, it can focus on analyzing videos uploaded during those times or on those days. In this way, utilizing users' viewing history can improve the accuracy of detecting violating content.

[0062] AI monitoring systems can also be equipped with real-time detection of violating content. For example, they can analyze videos in real time during live streaming and immediately issue a warning if violating content is detected. Real-time analysis can also be used to automatically block scenes containing violating content. Furthermore, feedback from viewers can be collected in real time during live streaming to help detect violating content. This real-time detection of violating content can prevent the spread of violating content during live streaming.

[0063] AI monitoring systems can also be equipped with multilingual analysis capabilities to accommodate different languages ​​and cultures. For example, they can analyze audio and text in videos in multiple languages ​​to detect inappropriate words and expressions in each language. They can also take into account standards for violating content in different cultures and perform appropriate analysis for each culture. Furthermore, multilingual analysis capabilities can be used to automatically translate video subtitles and captions, and then detect violating content based on the translated content. This ability to accommodate different languages ​​and cultures improves the accuracy of detecting violating content from a global perspective.

[0064] The AI ​​surveillance system can also use emotion estimation to analyze changes in the emotions of characters in a video and detect emotionally inappropriate scenes. For example, it can analyze the facial expressions and tone of voice of characters in a video to identify scenes with sudden changes in emotion. It can also use emotion estimation to detect scenes in which a character's emotion changes in a negative direction. It can also use emotion estimation to predict the impact that a character's emotion will have on the viewer and provide advance warning of emotionally inappropriate scenes. As a result, the emotion estimation function can detect emotionally inappropriate scenes with high accuracy.

[0065] The AI ​​surveillance system can also use emotion estimation capabilities to monitor viewers' emotional responses in real time and provide advance warnings of scenes that may evoke negative emotions. For example, it can analyze viewers' facial expressions and heart rates to identify scenes that may cause discomfort. It can also predict scenes that may evoke negative emotions based on viewers' emotional responses and issue advance warnings. It can also monitor viewers' emotional responses in real time and automatically block scenes that evoke negative emotions. This allows it to provide advance warnings of scenes that may evoke negative emotions by monitoring viewers' emotional responses in real time.

[0066] The AI ​​monitoring system can also analyze a poster's past posting history to evaluate the possibility of violating content before uploading a video. For example, if a poster has a history of posting violating content in the past, it will focus on analyzing that poster's new videos. It can also detect violating content with specific patterns based on a poster's past posting history. Furthermore, it can analyze a poster's past posting history and provide feedback to prevent the recurrence of violating content. In this way, by utilizing a poster's past posting history, the accuracy of detecting violating content can be improved.

[0067] The AI ​​monitoring system can also use emotion estimation to analyze music and sound effects in videos to detect emotionally inappropriate elements. For example, it can detect when music in a video may evoke negative emotions in viewers. It can also identify when sound effects may cause discomfort to viewers. Furthermore, it can use emotion estimation to predict the emotional impact of music and sound effects on viewers and provide advance warning of emotionally inappropriate elements. As a result, the emotion estimation function can detect emotionally inappropriate elements in music and sound effects with high accuracy.

[0068] The AI ​​monitoring system can also analyze the poster's intent before uploading a video to assess the possibility of violating content. For example, it can analyze the intention stated by the poster in the video description and tags to assess the possibility of violating content. It can also analyze the poster's past posting history and comments to detect violating content with specific intent. It can also analyze the poster's intent and provide feedback to prevent the recurrence of violating content. By analyzing the poster's intent, the system can improve the accuracy of detecting violating content.

[0069] The AI ​​monitoring system can also use emotion estimation to analyze narration and comments in videos to detect emotionally inappropriate elements. For example, it can detect when narration may evoke negative emotions in viewers. It can also identify when comments may cause discomfort to viewers. Furthermore, it can use emotion estimation to predict the emotional impact of narration and comments on viewers and provide advance warning of emotionally inappropriate elements. As a result, the emotion estimation function can detect emotionally inappropriate elements in narration and comments with high accuracy.

[0070] The AI ​​monitoring system can also analyze the poster's social media activity before uploading a video to assess the possibility of violating content. For example, it can analyze what the poster has previously said on social media to assess the possibility of violating content. It can also detect violating content with specific patterns based on the poster's social media activity history. It can also analyze the poster's social media activity and provide feedback to prevent the recurrence of violating content. In this way, by utilizing the poster's social media activity, the accuracy of detecting violating content can be improved.

[0071] The processing flow of the second embodiment will be briefly explained below.

[0072] Step 1: The video analysis unit analyzes the content of the video. For example, the video analysis unit receives a video file as input and analyzes its content. The video analysis unit can analyze elements such as video, audio, and text. For example, the video analysis unit analyzes each frame of the video to detect specific scenes. The video analysis unit can also analyze audio data to detect specific audio patterns. Furthermore, the video analysis unit can analyze text data within the video to detect inappropriate words and expressions. Step 2: The violation detection unit detects violating content from the video analyzed by the video analysis unit. For example, the violation detection unit detects violent scenes and inappropriate language. The violation detection unit can also detect discriminatory remarks and privacy violation content. Furthermore, the violation detection unit can analyze background and environmental sounds in the video to detect signs of violating content. Step 3: The classification unit classifies the violating content detected by the violation detection unit. For example, the classification unit classifies the content into violent content, discriminatory content, privacy violation content, etc. The classification unit can also classify the content according to the type and degree of violation. Step 4: The deletion unit deletes the violating content classified by the classification unit. For example, the deletion unit automatically deletes the violating content before the video is uploaded. The deletion unit can also delete the violating content based on a manual deletion instruction. Furthermore, the deletion unit can set the timing and method of deletion. Step 5: The feedback unit provides the poster with information about the infringing content. For example, the feedback unit may explain in detail which part is in violation and how to correct it. The feedback unit may also set notification methods and detailed feedback information.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0077] 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.

[0078] 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.

[0079] 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.

[0080] 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.

[0081] 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).

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0086] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0087] 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.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0092] 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.

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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).

[0097] 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.

[0098] 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.

[0099] 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.

[0100] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0101] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0107] 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.

[0108] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0109] The 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.

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

[0111] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS 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).

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

[0113] 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.

[0114] 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.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the robot 414, 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. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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).

[0126] 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.

[0127] 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."

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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]

[0140] 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 video analysis unit that analyzes the content of the video; a violation detection unit that detects violating content from the video analyzed by the video analysis unit; a classification unit that classifies the violating content detected by the violation detection unit; a deletion unit that deletes the infringing content classified by the classification unit; a feedback unit that provides feedback on information regarding the infringing content to the poster. A system characterized by:

2. The video analysis unit Analyze not only the content of the video but also its metadata to comprehensively assess the possibility of violating content 2. The system of claim 1.

3. The video analysis unit Analyzes background and environmental sounds in videos to detect signs of violating content 2. The system of claim 1.

4. The video analysis unit Analyzes facial expressions and tone of voice of characters in videos to detect emotionally inappropriate scenes 2. The system of claim 1.

5. The video analysis unit Analyze video scenarios and scripts to proactively assess potential violations 2. The system of claim 1.

Images