System

Abstract

An object of a system according to an embodiment is to detect occurrence of an illegal operation in real time and promptly notify the user of the occurrence.SOLUTION: A system includes a collection unit, an analysis unit, a detection unit, and a notification unit. The collection unit collects audio or video. The analysis unit analyzes the audio or video collected by the collection unit. The detection unit detects occurrence of a fake based on the information analyzed by the analysis unit. The notification unit notifies the occurrence of the image detected by the detection unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to detect bullying in real time and deal with it quickly.

[0005] The system according to the embodiment aims to detect occurrences of bullying in real time and to notify the occurrences promptly. [Means for solving the problem]

[0006] The system according to the embodiment includes a collection unit, an analysis unit, a detection unit, and a notification unit. The collection unit collects audio or video. The analysis unit analyzes the audio or video collected by the collection unit. The detection unit detects the occurrence of bullying based on the information analyzed by the analysis unit. The notification unit notifies the occurrence of bullying detected by the detection unit. [Effects of the Invention]

[0007] The system according to the embodiment can detect the occurrence of bullying in real time and notify the occurrence quickly. [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) A bullying detection system according to an embodiment of the present invention collects audio and video, analyzes it using a generation AI, and detects and notifies users when bullying occurs. The bullying detection system collects audio and video from the microphones and cameras of smartphones and IoT devices, and then uses a generation AI to analyze the collected audio and video to detect bullying. For example, the generation AI analyzes the tone and content of audio, and the movements and facial expressions of video to detect signs of bullying. When bullying is detected, the generation AI immediately notifies the smartphone apps of other users nearby the location that bullying has been detected. The notified users (e.g., users in a specific location) can then take action, such as rushing to the scene or observing it from a distance and reporting it to the police. This enables early detection and rapid response to bullying, and is expected to have a deterrent effect. This allows the bullying detection system to quickly detect and notify users when bullying occurs. For example, when bullying is detected within a school, teachers and staff can respond quickly to minimize the damage. Additionally, if bullying is detected in the street, a large number of people nearby can report it to the police, allowing for a swift response.

[0029] A bullying detection system according to an embodiment includes a collection unit, an analysis unit, a detection unit, and a notification unit. The collection unit collects audio or video. For example, the collection unit collects audio or video from a microphone or camera of a smartphone or IoT device. The collection unit can also automatically filter surrounding environmental sounds and background noise when collecting audio or video. For example, the collection unit can analyze surrounding environmental sounds in real time and remove background noise when collecting audio. Furthermore, the collection unit can start collecting audio or video in response to a specific keyword or action as a trigger. For example, the collection unit can start collecting audio when a specific keyword (e.g., "help me") is detected. The analysis unit uses a generative AI to analyze the audio or video collected by the collection unit. For example, the analysis unit can analyze the tone and content of the audio, and the movements and facial expressions of the video. For example, the analysis unit can analyze the tone of the audio to detect changes in emotions. The analysis unit can also analyze the movements of the video to detect specific behavioral patterns. Furthermore, the analysis unit can analyze both audio and video and output comprehensive analysis results. The detection unit detects the occurrence of bullying based on the information analyzed by the analysis unit. The detection unit can detect signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. The notification unit notifies the occurrence of bullying detected by the detection unit. The notification unit can send a notification to nearby others using, for example, GPS information. For example, the notification unit can immediately notify smartphone apps of others near the location where bullying was detected that bullying has been detected. This allows the bullying detection system according to the embodiment to quickly detect and notify the occurrence of bullying. For example, if bullying is detected in a school, teachers and staff can respond quickly, minimizing damage. Furthermore, if bullying is detected on the street, a rapid response can be achieved by an unspecified number of people nearby reporting the incident to the police.

[0030] The analysis unit can analyze the tone or content of the voice, and the movements or facial expressions of the video. For example, the analysis unit can analyze the tone of the voice to detect changes in emotions. For example, the analysis unit can analyze changes in the tone of the voice to detect emotions such as anger or sadness. The analysis unit can also analyze the content of the voice to detect specific keywords. For example, the analysis unit can analyze the content of the voice to detect keywords such as "help" or "stop." The analysis unit can also analyze the movements in the video to detect specific behavioral patterns. For example, the analysis unit can analyze the movements in the video to detect violent actions or fleeing actions. The analysis unit can also analyze facial expressions in the video to detect changes in emotions. For example, the analysis unit can analyze facial expressions in the video to detect emotions such as anger or sadness. This enables the detailed analysis of the voice and video to detect signs of bullying with high accuracy. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can use a generative AI model that takes inputs such as the tone and content of audio, and the movements and facial expressions of video, and outputs signs of bullying.

[0031] The notification unit can use GPS information to send notifications to nearby others. The notification unit can, for example, use GPS information to send notifications to nearby others. For example, the notification unit can immediately notify the smartphone apps of others near the location where bullying was detected that bullying has been detected. The notification unit can also use GPS information to limit the scope of the notification. For example, the notification unit can send notifications only to others within a certain range from the location where bullying was detected. Furthermore, the notification unit can also use GPS information to set notification priorities. For example, the notification unit can prioritize notifications to others closest to the location where bullying was detected. In this way, using GPS information allows for quick and accurate notification. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can perform notifications using an AI model that inputs GPS information and outputs the notification destination.

[0032] The collection unit can collect audio or video from a microphone or camera of a smartphone or IoT device. The collection unit, for example, collects audio using a smartphone's microphone. For example, the collection unit can collect surrounding audio in real time using the smartphone's microphone. The collection unit can also collect video using the smartphone's camera. For example, the collection unit can collect surrounding video in real time using the smartphone's camera. The collection unit can also collect audio and video using the IoT device's microphone or camera. For example, the collection unit can collect audio within a specific area using the IoT device's microphone. The collection unit can also collect video within a specific area using the IoT device's camera. This allows audio and video to be collected over a wide area using a smartphone or IoT device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can collect audio and video using an AI model that receives audio and video collected from the smartphone's or IoT device's microphone or camera and outputs collected data.

[0033] The detection unit can detect signs of bullying. The detection unit detects signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. The detection unit can also detect the occurrence of bullying when a specific behavioral pattern (e.g., violent behavior) is detected. Furthermore, the detection unit can analyze both audio and video and detect signs of bullying based on the comprehensive analysis results. For example, the detection unit can detect signs of bullying by analyzing the tone and content of audio and the movements and facial expressions of video. This enables highly accurate detection of signs of bullying and enables rapid response. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can perform detection using a generative AI model that inputs the tone and content of audio and the movements and facial expressions of video and outputs signs of bullying.

[0034] The notification unit can enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. The notification unit can, for example, enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. For example, the notification unit can notify other people who are near the location where bullying was detected that bullying has been detected and encourage them to rush to the scene. The notification unit can also enable other people who receive the notification to check from a distance and report it to the police. For example, the notification unit can encourage other people who are near the location where bullying was detected to report it to the police. This allows other people who receive the notification to respond quickly, thereby minimizing the damage caused by bullying. Some or all of the above-described processing by the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can perform notification using an AI model that inputs the behavior of the notified other person and outputs a response method.

[0035] The collection unit can automatically filter ambient environmental sounds and background noise when collecting audio and video. For example, the collection unit can analyze ambient environmental sounds in real time and remove background noise when collecting audio. For example, the collection unit can automatically remove noise in a specific frequency band when collecting audio to collect clear data. The collection unit can also automatically filter areas with little movement in the video to highlight important movements when collecting video. For example, the collection unit can filter background areas with little movement and highlight areas with a lot of movement when collecting video. Furthermore, the collection unit can automatically remove specific noise when collecting audio and video to collect clear data. For example, the collection unit can remove noise in a specific frequency band when collecting audio and video to collect clear data. This allows clear data to be collected by removing ambient sounds and background noise. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can perform filtering using an AI model that receives audio and video data as input and outputs noise-removed data.

[0036] When collecting audio or video, the collection unit can start collection when a specific keyword or action is triggered. For example, the collection unit can start audio collection when a specific keyword (e.g., "help me") is detected. For example, the collection unit can start audio collection and collect detailed data when a specific keyword is detected. The collection unit can also start video collection when a specific action (e.g., waving one's hand) is detected. For example, the collection unit can start video collection and collect detailed data when a specific action is detected. Furthermore, the collection unit can simultaneously start collecting audio and video when a combination of a keyword and action (e.g., waving one's hand while shouting "help") is detected. For example, when a combination of a keyword and action is detected, the collection unit can simultaneously start collecting audio and video and collect detailed data. In this way, by starting collection when a specific keyword or action is triggered, important data can be collected without missing anything. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can start collection using an AI model that receives a specific keyword or action as input and outputs a trigger to start collection.

[0037] The collection unit can automatically adjust the position and angle of the collection device when collecting audio and video. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. The collection unit can also automatically adjust the angle of a camera when collecting video to collect optimal video. For example, the collection unit can automatically adjust the angle of a camera when collecting video to collect optimal video. Furthermore, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. For example, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. This allows optimal data to be collected by automatically adjusting the position and angle of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can make adjustments using an AI model that inputs the position and angle of the collection device and outputs the optimal position and angle.

[0038] When collecting audio and video, the collection unit can customize the collection method by referring to the user's past behavioral history. The collection unit customizes the collection method by referring to, for example, the user's past behavioral history. For example, the collection unit can customize the collection method based on patterns of audio and video that the user frequently collected in the past. The collection unit can also determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. For example, the collection unit can determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. Furthermore, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. For example, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. In this way, the optimal collection method can be provided by referring to the user's past behavioral history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can customize the collection method using an AI model that uses the user's past behavioral history data as input and customizes the collection method.

[0039] When collecting audio or video, the collection unit can adjust the collection frequency taking into account the remaining battery level of the collection device. For example, when the remaining battery level of the collection device is low, the collection unit reduces the collection frequency to conserve battery power. For example, when the remaining battery level of the collection device is low, the collection unit can reduce the collection frequency to conserve battery power. Furthermore, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. For example, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. Furthermore, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. For example, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. This enables efficient data collection by taking the remaining battery level of the collection device into account. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can adjust the collection frequency using an AI model that inputs remaining battery level data of the collection device and outputs a collection frequency.

[0040] When collecting audio and video, the collection unit can limit the collection range based on the location information of the collection device. For example, the collection unit collects audio and video only within a specific area based on the location information of the collection device. For example, the collection unit can collect audio and video only within a specific area based on the location information of the collection device. The collection unit can also automatically adjust the collection range based on the location information of the collection device to collect optimal data. For example, the collection unit can automatically adjust the collection range based on the location information of the collection device to collect optimal data. Furthermore, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. For example, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. This enables efficient data collection by limiting the collection range based on the location information of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can limit the collection range using an AI model that inputs the location information of the collection device and outputs the collection range.

[0041] The analysis unit can improve analysis accuracy by combining multiple analysis algorithms when analyzing audio or video. For example, the analysis unit can improve analysis accuracy by combining a voice recognition algorithm and an emotion analysis algorithm when analyzing audio. For example, the analysis unit can analyze audio data using a voice recognition algorithm and detect emotional changes using an emotion analysis algorithm. Furthermore, the analysis unit can improve analysis accuracy by combining a face recognition algorithm and a motion analysis algorithm when analyzing video. For example, the analysis unit can analyze video data using a face recognition algorithm and detect specific behavioral patterns using a motion analysis algorithm. Furthermore, the analysis unit can use multiple algorithms in parallel when analyzing audio and video to improve overall analysis accuracy. For example, the analysis unit can combine a voice recognition algorithm and an emotion analysis algorithm, or a face recognition algorithm and a motion analysis algorithm to improve overall analysis accuracy. Thus, combining multiple analysis algorithms improves analysis accuracy. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can perform analysis using multiple generative AI models that input audio or video data and output analysis results.

[0042] When analyzing audio or video, the analysis unit can optimize analysis parameters by referring to past analysis results. The analysis unit, for example, optimizes current analysis parameters based on past audio analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio analysis results. The analysis unit can also optimize current analysis parameters based on past video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past video analysis results. Furthermore, the analysis unit can optimize current analysis parameters by comprehensively referring to past audio and video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio and video analysis results. In this way, current analysis parameters can be optimized by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can optimize parameters using a generation AI model that inputs past analysis result data and outputs optimal analysis parameters.

[0043] The analysis unit can prioritize analysis of specific patterns or signals when analyzing audio or video. For example, the analysis unit prioritizes analysis of specific keywords or phrases when analyzing audio. For example, the analysis unit can prioritize analysis of specific keywords (e.g., "help me") or phrases to collect detailed data. The analysis unit can also prioritize analysis of specific actions or facial expressions when analyzing video. For example, the analysis unit can prioritize analysis of specific actions (e.g., waving one's hand) or facial expressions to collect detailed data. Furthermore, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. For example, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. By prioritizing analysis of specific patterns or signals, results can be quickly provided. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can perform analysis using a generative AI model that takes specific patterns or signals as input and outputs analysis results.

[0044] When analyzing audio or video, the analysis unit can determine the analysis priority according to the amount of data to be analyzed. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts and collect detailed data. Furthermore, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes. For example, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes and collect detailed data. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data. For example, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data to perform efficient analysis. This enables efficient analysis by determining the priority according to the amount of data to be analyzed. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can determine the priority using a generative AI model that inputs the amount of data to be analyzed and outputs the analysis priority.

[0045] The analysis unit may be added with a function of feeding back analysis results in real time when analyzing audio or video. The analysis unit, for example, may feed back audio analysis results in real time, enabling immediate response. For example, the analysis unit may feed back audio analysis results in real time, enabling immediate response. The analysis unit may also feed back video analysis results in real time, enabling immediate response. For example, the analysis unit may feed back video analysis results in real time, enabling immediate response. The analysis unit may also feed back audio and video analysis results in real time, enabling comprehensive response. For example, the analysis unit may feed back audio and video analysis results in real time, enabling comprehensive response. As a result, real-time feedback enables immediate response. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit may provide feedback using a generative AI model that receives audio and video analysis results as input and provides feedback in real time.

[0046] When analyzing audio or video, the analysis unit can cooperate with other systems to share the analysis results. The analysis unit, for example, cooperates with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. This enables comprehensive data analysis by coordinating with other systems. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can input audio or video analysis results and share the analysis results using a generative AI model that cooperates with other systems to share the analysis results.

[0047] When detecting signs of bullying, the detection unit can improve detection accuracy by integrating multiple data sources. The detection unit, for example, integrates audio data and video data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and video data to detect signs of bullying with high accuracy. The detection unit can also integrate audio data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and text data to detect signs of bullying with high accuracy. The detection unit can also integrate video data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate video data and text data to detect signs of bullying with high accuracy. In this way, by integrating multiple data sources, detection accuracy is improved. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the detection unit can perform detection using a generative AI model that takes multiple data sources as input and outputs signs of bullying.

[0048] When detecting signs of bullying, the detection unit can optimize the detection algorithm by referring to past detection results. The detection unit, for example, optimizes the current detection algorithm based on the detection results of past audio data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio data. The detection unit can also optimize the current detection algorithm based on the detection results of past video data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past video data. The detection unit can also optimize the current detection algorithm by comprehensively referring to past audio and video detection results. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio and video. In this way, the current detection algorithm can be optimized by referring to the past detection results. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the detection unit can optimize the algorithm using a generative AI model that inputs past detection result data and outputs an optimal detection algorithm.

[0049] When detecting signs of bullying, the detection unit can strengthen detection by using specific actions or statements as triggers. For example, the detection unit strengthens detection when a specific action (e.g., violent behavior) is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific action is detected. The detection unit can also strengthen detection when a specific statement (e.g., offensive language such as "die") is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific statement is detected. Furthermore, the detection unit can strengthen detection when a combination of action and statement (e.g., violent actions and offensive language) is detected. For example, the detection unit can strengthen detection and collect detailed data when a combination of action and statement is detected. This enables a rapid response by strengthening detection when specific actions or statements are triggered. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI. For example, the detection unit can strengthen detection by using a generative AI model that inputs specific actions or statements and outputs a trigger for strengthening detection.

[0050] When detecting signs of bullying, the detection unit can determine the detection priority according to the amount of data of the detection target. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts and collect detailed data. Furthermore, when there is a large amount of video data, the detection unit can prioritize detecting important scenes. For example, when there is a large amount of video data, the detection unit can prioritize detecting important scenes and collect detailed data. Furthermore, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data. For example, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data to perform efficient detection. This enables efficient detection by determining the priority according to the amount of data of the detection target. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can determine the priority using a generative AI model that inputs the amount of data of the detection target and outputs the detection priority.

[0051] The detection unit may be added with a function for feeding back detection results in real time when detecting signs of bullying. The detection unit, for example, may feed back detection results of audio data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of audio data in real time, enabling an immediate response. The detection unit may also feed back detection results of video data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of video data in real time, enabling an immediate response. The detection unit may also feed back detection results of audio and video in real time, enabling a comprehensive response. For example, the detection unit may feed back detection results of audio and video in real time, enabling a comprehensive response. As a result, real-time feedback enables an immediate response. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit may provide feedback using a generative AI model that receives detection results of audio and video and provides feedback in real time.

[0052] When detecting signs of bullying, the detection unit can cooperate with other systems to share the detection results. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of video data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of video data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. This enables comprehensive data analysis by cooperating with other systems. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can input the detection results of audio and video and share the detection results using a generative AI model that cooperates with other systems to share the detection results.

[0053] When notifying an occurrence of bullying, the notification unit can set a priority for the notification and provide a notification according to the level of importance. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority to encourage a prompt response. Furthermore, if a sign of minor bullying is detected, the notification unit can send a notification with normal priority to encourage a prompt response. Furthermore, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance. For example, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance to encourage an optimal response. This enables a prompt and appropriate response by providing a notification according to the level of importance. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can make notifications using an AI model that inputs bullying symptom data and outputs notification priorities.

[0054] The notification unit can customize the format of the notification (text, audio, video, etc.) when notifying an occurrence of bullying. For example, the notification unit can send a text notification and provide detailed information. For example, the notification unit can send a text notification and provide detailed information. The notification unit can also send an audio notification to encourage a prompt response. For example, the notification unit can send an audio notification to encourage a prompt response. Furthermore, the notification unit can send a video notification to visually convey the situation at the scene. For example, the notification unit can send a video notification to visually convey the situation at the scene. In this way, customizing the notification format makes it possible to provide optimal information to the recipient. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can customize the notification using an AI model that inputs the content of the notification and outputs the format of the notification.

[0055] When notifying an occurrence of bullying, the notification unit can save the notification history so that it can be referenced later. For example, the notification unit can save the notification history and perform a detailed analysis later. For example, the notification unit can save the notification history and perform a detailed analysis later. The notification unit can also save the notification history and check past response statuses. For example, the notification unit can save the notification history and check past response statuses. Furthermore, the notification unit can save the notification history and use it for future improvements. For example, the notification unit can save the notification history and use it for future improvements. In this way, saving the notification history enables later detailed analysis and confirmation. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can manage the history using an AI model that receives notification history data as input and stores and references it.

[0056] When notifying the user of an incident of bullying, the notification unit can select the optimal notification method by taking into consideration device information of the notification target. For example, if the user is using a smartphone, the notification unit sends a push notification. For example, if the user is using a smartphone, the notification unit can send a push notification to encourage a prompt response. Furthermore, if the user is using a tablet, the notification unit can send a notification optimized for a large screen. For example, if the user is using a tablet, the notification unit can send a notification optimized for a large screen and provide detailed information. Furthermore, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification. For example, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification to encourage a prompt response. This makes it possible to provide the optimal notification method by taking into consideration device information of the notification target. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that inputs device information of the notification target and outputs the optimal notification method.

[0057] When notifying an occurrence of bullying, the notification unit can make the content of the notification multilingual. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. The notification unit can also automatically set the language of the notification based on the language setting of the user's device. For example, the notification unit can automatically set the language of the notification based on the language setting of the user's device. Furthermore, the notification unit can provide a language switching function when a user speaks multiple languages. For example, when a user speaks multiple languages, the notification unit can provide a language switching function and provide a notification in an appropriate language. This provides multilingual support to accommodate users who speak different languages. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can provide a notification using an AI model that inputs the content of the notification and translates it into multiple languages.

[0058] When notifying an occurrence of bullying, the notification unit can customize the content of the notification to provide information according to the recipient's attributes. For example, the notification unit can send a notification including detailed response procedures to faculty and staff. For example, the notification unit can send a notification including detailed response procedures to faculty and staff to encourage a prompt response. The notification unit can also send a concise, easy-to-understand notification to students. For example, the notification unit can send a concise, easy-to-understand notification to students to encourage an appropriate response. Furthermore, the notification unit can send a notification encouraging a prompt response to an unspecified number of people. For example, the notification unit can send a notification encouraging a prompt response to an unspecified number of people to encourage an appropriate response. This enables a more appropriate response by providing information according to the recipient's attributes. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can send a notification using an AI model that inputs the recipient's attribute data and customizes the content of the notification.

[0059] The analysis unit can analyze the tone and content of audio, as well as the movements and facial expressions of video. The analysis unit, for example, analyzes the tone of audio to detect changes in emotions. For example, the analysis unit can analyze changes in the tone of audio to detect emotions such as anger or sadness. The analysis unit can also analyze the content of audio to detect specific keywords. For example, the analysis unit can analyze the content of audio to detect keywords such as "help" or "stop." The analysis unit can also analyze the movements in video to detect specific behavioral patterns. For example, the analysis unit can analyze the movements in video to detect violent actions or fleeing actions. The analysis unit can also analyze facial expressions in video to detect changes in emotions. For example, the analysis unit can analyze facial expressions in video to detect emotions such as anger or sadness. This enables the detailed analysis of audio and video to detect signs of bullying with high accuracy. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can use a generative AI model that takes inputs such as the tone and content of audio, and the movements and facial expressions of video, and outputs signs of bullying.

[0060] The notification unit can use GPS information to send notifications to nearby others. The notification unit can, for example, use GPS information to send notifications to nearby others. For example, the notification unit can immediately notify the smartphone apps of others near the location where bullying was detected that bullying has been detected. The notification unit can also use GPS information to limit the scope of the notification. For example, the notification unit can send notifications only to others within a certain range from the location where bullying was detected. Furthermore, the notification unit can also use GPS information to set notification priorities. For example, the notification unit can prioritize notifications to others closest to the location where bullying was detected. In this way, using GPS information allows for quick and accurate notification. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can perform notifications using an AI model that inputs GPS information and outputs the notification destination.

[0061] The collection unit can collect audio and video from a microphone or camera of a smartphone or IoT device. The collection unit, for example, collects audio using a smartphone's microphone. For example, the collection unit can collect surrounding audio in real time using the smartphone's microphone. The collection unit can also collect video using the smartphone's camera. For example, the collection unit can collect surrounding video in real time using the smartphone's camera. The collection unit can also collect audio and video using the IoT device's microphone or camera. For example, the collection unit can collect audio within a specific area using the IoT device's microphone. The collection unit can also collect video within a specific area using the IoT device's camera. This allows audio and video to be collected over a wide area using a smartphone or IoT device. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can perform collection using an AI model that receives audio and video collected from the smartphone's or IoT device's microphone or camera and outputs collected data.

[0062] The detection unit can detect signs of bullying. The detection unit detects signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. The detection unit can also detect the occurrence of bullying when a specific behavioral pattern (e.g., violent behavior) is detected. Furthermore, the detection unit can analyze both audio and video and detect signs of bullying based on the comprehensive analysis results. For example, the detection unit can detect signs of bullying by analyzing the tone and content of audio and the movements and facial expressions of video. This enables highly accurate detection of signs of bullying and enables rapid response. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can perform detection using a generative AI model that inputs the tone and content of audio and the movements and facial expressions of video and outputs signs of bullying.

[0063] The notification unit can enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. The notification unit can, for example, enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. For example, the notification unit can notify other people who are near the location where bullying was detected that bullying has been detected and encourage them to rush to the scene. The notification unit can also enable other people who receive the notification to check from a distance and report it to the police. For example, the notification unit can encourage other people who are near the location where bullying was detected to report it to the police. This allows other people who receive the notification to respond quickly, thereby minimizing the damage caused by bullying. Some or all of the above-described processing by the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can perform notification using an AI model that inputs the behavior of the notified other person and outputs a response method.

[0064] The collection unit can automatically filter ambient environmental sounds and background noise when collecting audio and video. For example, the collection unit can analyze ambient environmental sounds in real time and remove background noise when collecting audio. For example, the collection unit can automatically remove noise in a specific frequency band when collecting audio to collect clear data. The collection unit can also automatically filter areas with little movement in the video to highlight important movements when collecting video. For example, the collection unit can filter background areas with little movement and highlight areas with a lot of movement when collecting video. Furthermore, the collection unit can automatically remove specific noise when collecting audio and video to collect clear data. For example, the collection unit can remove noise in a specific frequency band when collecting audio and video to collect clear data. This allows clear data to be collected by removing ambient sounds and background noise. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can perform filtering using an AI model that receives audio and video data as input and outputs noise-removed data.

[0065] When collecting audio or video, the collection unit can start collection when a specific keyword or action is triggered. For example, the collection unit can start audio collection when a specific keyword (e.g., "help me") is detected. For example, the collection unit can start audio collection and collect detailed data when a specific keyword is detected. The collection unit can also start video collection when a specific action (e.g., waving one's hand) is detected. For example, the collection unit can start video collection and collect detailed data when a specific action is detected. Furthermore, the collection unit can simultaneously start collecting audio and video when a combination of a keyword and action (e.g., waving one's hand while shouting "help") is detected. For example, when a combination of a keyword and action is detected, the collection unit can simultaneously start collecting audio and video and collect detailed data. In this way, by starting collection when a specific keyword or action is triggered, important data can be collected without missing anything. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can start collection using an AI model that receives a specific keyword or action as input and outputs a trigger to start collection.

[0066] The collection unit can automatically adjust the position and angle of the collection device when collecting audio and video. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. The collection unit can also automatically adjust the angle of a camera when collecting video to collect optimal video. For example, the collection unit can automatically adjust the angle of a camera when collecting video to collect optimal video. Furthermore, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. For example, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. This allows optimal data to be collected by automatically adjusting the position and angle of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can make adjustments using an AI model that inputs the position and angle of the collection device and outputs the optimal position and angle.

[0067] When collecting audio and video, the collection unit can customize the collection method by referring to the user's past behavioral history. The collection unit customizes the collection method by referring to, for example, the user's past behavioral history. For example, the collection unit can customize the collection method based on patterns of audio and video that the user frequently collected in the past. The collection unit can also determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. For example, the collection unit can determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. Furthermore, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. For example, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. In this way, the optimal collection method can be provided by referring to the user's past behavioral history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can customize the collection method using an AI model that uses the user's past behavioral history data as input and customizes the collection method.

[0068] When collecting audio or video, the collection unit can adjust the collection frequency taking into account the remaining battery level of the collection device. For example, when the remaining battery level of the collection device is low, the collection unit reduces the collection frequency to conserve battery power. For example, when the remaining battery level of the collection device is low, the collection unit can reduce the collection frequency to conserve battery power. Furthermore, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. For example, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. Furthermore, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. For example, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. This enables efficient data collection by taking the remaining battery level of the collection device into account. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can adjust the collection frequency using an AI model that inputs remaining battery level data of the collection device and outputs a collection frequency.

[0069] When collecting audio and video, the collection unit can limit the collection range based on the location information of the collection device. For example, the collection unit collects audio and video only within a specific area based on the location information of the collection device. For example, the collection unit can collect audio and video only within a specific area based on the location information of the collection device. The collection unit can also automatically adjust the collection range based on the location information of the collection device to collect optimal data. For example, the collection unit can automatically adjust the collection range based on the location information of the collection device to collect optimal data. Furthermore, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. For example, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. This enables efficient data collection by limiting the collection range based on the location information of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can limit the collection range using an AI model that inputs the location information of the collection device and outputs the collection range.

[0070] The analysis unit can improve analysis accuracy by combining multiple analysis algorithms when analyzing audio or video. For example, the analysis unit can improve analysis accuracy by combining a voice recognition algorithm and an emotion analysis algorithm when analyzing audio. For example, the analysis unit can analyze audio data using a voice recognition algorithm and detect emotional changes using an emotion analysis algorithm. Furthermore, the analysis unit can improve analysis accuracy by combining a face recognition algorithm and a motion analysis algorithm when analyzing video. For example, the analysis unit can analyze video data using a face recognition algorithm and detect specific behavioral patterns using a motion analysis algorithm. Furthermore, the analysis unit can use multiple algorithms in parallel when analyzing audio and video to improve overall analysis accuracy. For example, the analysis unit can combine a voice recognition algorithm and an emotion analysis algorithm, or a face recognition algorithm and a motion analysis algorithm to improve overall analysis accuracy. Thus, combining multiple analysis algorithms improves analysis accuracy. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can perform analysis using multiple generative AI models that input audio or video data and output analysis results.

[0071] When analyzing audio or video, the analysis unit can optimize analysis parameters by referring to past analysis results. The analysis unit, for example, optimizes current analysis parameters based on past audio analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio analysis results. The analysis unit can also optimize current analysis parameters based on past video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past video analysis results. Furthermore, the analysis unit can optimize current analysis parameters by comprehensively referring to past audio and video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio and video analysis results. In this way, current analysis parameters can be optimized by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can optimize parameters using a generation AI model that inputs past analysis result data and outputs optimal analysis parameters.

[0072] The analysis unit can prioritize analysis of specific patterns or signals when analyzing audio or video. For example, the analysis unit prioritizes analysis of specific keywords or phrases when analyzing audio. For example, the analysis unit can prioritize analysis of specific keywords (e.g., "help me") or phrases to collect detailed data. The analysis unit can also prioritize analysis of specific actions or facial expressions when analyzing video. For example, the analysis unit can prioritize analysis of specific actions (e.g., waving one's hand) or facial expressions to collect detailed data. Furthermore, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. For example, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. By prioritizing analysis of specific patterns or signals, results can be quickly provided. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can perform analysis using a generative AI model that takes specific patterns or signals as input and outputs analysis results.

[0073] When analyzing audio or video, the analysis unit can determine the analysis priority according to the amount of data to be analyzed. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts and collect detailed data. Furthermore, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes. For example, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes and collect detailed data. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data. For example, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data to perform efficient analysis. This enables efficient analysis by determining the priority according to the amount of data to be analyzed. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can determine the priority using a generative AI model that inputs the amount of data to be analyzed and outputs the analysis priority.

[0074] The analysis unit may be added with a function of feeding back analysis results in real time when analyzing audio or video. The analysis unit, for example, may feed back audio analysis results in real time, enabling immediate response. For example, the analysis unit may feed back audio analysis results in real time, enabling immediate response. The analysis unit may also feed back video analysis results in real time, enabling immediate response. For example, the analysis unit may feed back video analysis results in real time, enabling immediate response. The analysis unit may also feed back audio and video analysis results in real time, enabling comprehensive response. For example, the analysis unit may feed back audio and video analysis results in real time, enabling comprehensive response. As a result, real-time feedback enables immediate response. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit may provide feedback using a generative AI model that receives audio and video analysis results as input and provides feedback in real time.

[0075] When analyzing audio or video, the analysis unit can cooperate with other systems to share the analysis results. The analysis unit, for example, cooperates with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. This enables comprehensive data analysis by coordinating with other systems. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can input audio or video analysis results and share the analysis results using a generative AI model that cooperates with other systems to share the analysis results.

[0076] When detecting signs of bullying, the detection unit can improve detection accuracy by integrating multiple data sources. The detection unit, for example, integrates audio data and video data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and video data to detect signs of bullying with high accuracy. The detection unit can also integrate audio data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and text data to detect signs of bullying with high accuracy. The detection unit can also integrate video data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate video data and text data to detect signs of bullying with high accuracy. In this way, by integrating multiple data sources, detection accuracy is improved. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the detection unit can perform detection using a generative AI model that takes multiple data sources as input and outputs signs of bullying.

[0077] When detecting signs of bullying, the detection unit can optimize the detection algorithm by referring to past detection results. The detection unit, for example, optimizes the current detection algorithm based on the detection results of past audio data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio data. The detection unit can also optimize the current detection algorithm based on the detection results of past video data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past video data. The detection unit can also optimize the current detection algorithm by comprehensively referring to past audio and video detection results. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio and video. In this way, the current detection algorithm can be optimized by referring to the past detection results. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the detection unit can optimize the algorithm using a generative AI model that inputs past detection result data and outputs an optimal detection algorithm.

[0078] When detecting signs of bullying, the detection unit can strengthen detection by using specific actions or statements as triggers. For example, the detection unit strengthens detection when a specific action (e.g., violent behavior) is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific action is detected. The detection unit can also strengthen detection when a specific statement (e.g., offensive language such as "die") is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific statement is detected. Furthermore, the detection unit can strengthen detection when a combination of action and statement (e.g., violent actions and offensive language) is detected. For example, the detection unit can strengthen detection and collect detailed data when a combination of action and statement is detected. This enables a rapid response by strengthening detection when specific actions or statements are triggered. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI. For example, the detection unit can strengthen detection by using a generative AI model that inputs specific actions or statements and outputs a trigger for strengthening detection.

[0079] When detecting signs of bullying, the detection unit can determine the detection priority according to the amount of data of the detection target. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts and collect detailed data. Furthermore, when there is a large amount of video data, the detection unit can prioritize detecting important scenes. For example, when there is a large amount of video data, the detection unit can prioritize detecting important scenes and collect detailed data. Furthermore, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data. For example, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data to perform efficient detection. This enables efficient detection by determining the priority according to the amount of data of the detection target. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can determine the priority using a generative AI model that inputs the amount of data of the detection target and outputs the detection priority.

[0080] The detection unit may be added with a function for feeding back detection results in real time when detecting signs of bullying. The detection unit, for example, may feed back detection results of audio data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of audio data in real time, enabling an immediate response. The detection unit may also feed back detection results of video data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of video data in real time, enabling an immediate response. The detection unit may also feed back detection results of audio and video in real time, enabling a comprehensive response. For example, the detection unit may feed back detection results of audio and video in real time, enabling a comprehensive response. As a result, real-time feedback enables an immediate response. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit may provide feedback using a generative AI model that receives detection results of audio and video and provides feedback in real time.

[0081] When detecting signs of bullying, the detection unit can cooperate with other systems to share the detection results. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of video data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of video data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. This enables comprehensive data analysis by cooperating with other systems. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can input the detection results of audio and video and share the detection results using a generative AI model that cooperates with other systems to share the detection results.

[0082] When notifying an occurrence of bullying, the notification unit can set a priority for the notification and provide a notification according to the level of importance. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority to encourage a prompt response. Furthermore, if a sign of minor bullying is detected, the notification unit can send a notification with normal priority to encourage a prompt response. Furthermore, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance. For example, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance to encourage an optimal response. This enables a prompt and appropriate response by providing a notification according to the level of importance. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can make notifications using an AI model that inputs bullying symptom data and outputs notification priorities.

[0083] The notification unit can customize the format of the notification (text, audio, video, etc.) when notifying an occurrence of bullying. For example, the notification unit can send a text notification and provide detailed information. For example, the notification unit can send a text notification and provide detailed information. The notification unit can also send an audio notification to encourage a prompt response. For example, the notification unit can send an audio notification to encourage a prompt response. Furthermore, the notification unit can send a video notification to visually convey the situation at the scene. For example, the notification unit can send a video notification to visually convey the situation at the scene. In this way, customizing the notification format makes it possible to provide optimal information to the recipient. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can customize the notification using an AI model that inputs the content of the notification and outputs the format of the notification.

[0084] When notifying an occurrence of bullying, the notification unit can save the notification history so that it can be referenced later. For example, the notification unit can save the notification history and perform a detailed analysis later. For example, the notification unit can save the notification history and perform a detailed analysis later. The notification unit can also save the notification history and check past response statuses. For example, the notification unit can save the notification history and check past response statuses. Furthermore, the notification unit can save the notification history and use it for future improvements. For example, the notification unit can save the notification history and use it for future improvements. In this way, saving the notification history enables later detailed analysis and confirmation. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can manage the history using an AI model that receives notification history data as input and stores and references it.

[0085] When notifying the user of an incident of bullying, the notification unit can select the optimal notification method by taking into consideration device information of the notification target. For example, if the user is using a smartphone, the notification unit sends a push notification. For example, if the user is using a smartphone, the notification unit can send a push notification to encourage a prompt response. Furthermore, if the user is using a tablet, the notification unit can send a notification optimized for a large screen. For example, if the user is using a tablet, the notification unit can send a notification optimized for a large screen and provide detailed information. Furthermore, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification. For example, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification to encourage a prompt response. This makes it possible to provide the optimal notification method by taking into consideration device information of the notification target. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that inputs device information of the notification target and outputs the optimal notification method.

[0086] When notifying an occurrence of bullying, the notification unit can make the content of the notification multilingual. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. The notification unit can also automatically set the language of the notification based on the language setting of the user's device. For example, the notification unit can automatically set the language of the notification based on the language setting of the user's device. Furthermore, the notification unit can provide a language switching function when a user speaks multiple languages. For example, when a user speaks multiple languages, the notification unit can provide a language switching function and provide a notification in an appropriate language. This provides multilingual support to accommodate users who speak different languages. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can provide a notification using an AI model that inputs the content of the notification and translates it into multiple languages.

[0087] When notifying an occurrence of bullying, the notification unit can customize the content of the notification to provide information according to the recipient's attributes. For example, the notification unit can send a notification including detailed response procedures to faculty and staff. For example, the notification unit can send a notification including detailed response procedures to faculty and staff to encourage a prompt response. The notification unit can also send a concise, easy-to-understand notification to students. For example, the notification unit can send a concise, easy-to-understand notification to students to encourage an appropriate response. Furthermore, the notification unit can send a notification encouraging a prompt response to an unspecified number of people. For example, the notification unit can send a notification encouraging a prompt response to an unspecified number of people to encourage an appropriate response. This enables a more appropriate response by providing information according to the recipient's attributes. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can send a notification using an AI model that inputs the recipient's attribute data and customizes the content of the notification.

[0088] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0089] When analyzing audio and video, the analysis unit can optimize the analysis algorithm by referring to the user's past behavioral history. For example, the analysis unit can adjust the current analysis algorithm based on the user's past behavior. This enables more accurate analysis based on the user's behavioral patterns. For example, if a specific behavioral pattern has been detected in the past as a sign of bullying, that pattern can be prioritized in the analysis. Furthermore, the analysis accuracy for specific time periods or situations can be improved based on the user's behavioral history. Furthermore, by referring to the user's behavioral history, the reliability of the analysis results can be improved.

[0090] When collecting audio or video, the collection unit can adjust the collection frequency taking into account the remaining battery level of the collection device. For example, if the battery level of the collection device is low, the collection frequency can be reduced to conserve battery power. Alternatively, if the battery level is sufficient, the collection frequency can be increased to collect more detailed data. Furthermore, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. This enables efficient data collection taking into account the remaining battery level. For example, the collection frequency can be halved when the battery level is 50% or less, and maximized when the battery level is 80% or more.

[0091] The analysis unit can prioritize specific patterns and signals when analyzing audio and video. For example, when analyzing audio, it can prioritize the analysis of specific keywords and phrases to collect detailed data. It can also prioritize the analysis of specific actions and facial expressions when analyzing video. Furthermore, when analyzing audio and video, it can prioritize the analysis of specific patterns and signals to quickly produce results. This makes it possible to analyze without missing important data. For example, if the keyword "help" or violent actions are detected, it can prioritize analysis.

[0092] When detecting signs of bullying, the detection unit can improve detection accuracy by integrating multiple data sources. For example, signs of bullying can be detected with high accuracy by integrating audio data and video data. Detection accuracy can also be improved by integrating audio data and text data. Furthermore, signs of bullying can be detected with high accuracy by integrating video data and text data. In this way, by integrating multiple data sources, detection accuracy is improved and more reliable detection is possible. For example, if the keyword "help" is detected in audio data and violent behavior is simultaneously detected in video data, it can be detected with a high probability as a sign of bullying.

[0093] When notifying an occurrence of bullying, the notification unit can save the notification history so that it can be referenced later. For example, the notification history can be saved and a detailed analysis can be performed later. The notification history can also be saved and past response status can be checked. Furthermore, the notification history can be saved and used to help with future improvements. In this way, by saving the notification history, detailed analysis and checking can be performed later. For example, based on the past notification history, it is possible to analyze which responses were effective and use this information in future responses. Furthermore, by referring to the notification history, it is possible to check past response status and respond quickly to similar situations.

[0094] When collecting audio or video, the collection unit can start collection using a specific keyword or action as a trigger. For example, if a specific keyword (e.g., "help me") is detected, audio collection can be started. Also, if a specific action (e.g., waving one's hand) is detected, video collection can be started. Furthermore, if a combination of a keyword and action (e.g., waving one's hand while shouting "help me") is detected, audio and video collection can be started simultaneously. In this way, by starting collection using a specific keyword or action as a trigger, it is possible to collect important data without missing anything. For example, if the keyword "help me" is detected, audio collection can be started immediately, and if the action of waving one's hand is detected, video collection can be started immediately.

[0095] When notifying an occurrence of bullying, the notification unit can make the content of the notification multilingual. For example, the content of the notification can be translated into multiple languages ​​to accommodate users who speak different languages. The notification language can also be automatically set based on the language setting of the user's device. Furthermore, if a user speaks multiple languages, a language switching function can be provided. This makes it possible to support multiple languages ​​and accommodate users who speak different languages. For example, a notification can be sent in English to an English-speaking user, and in Japanese to a Japanese-speaking user. Furthermore, if a user speaks multiple languages, a language switching function can be provided to send the notification in the appropriate language.

[0096] The processing flow of the first embodiment will be briefly explained below.

[0097] Step 1: The collection unit collects audio or video. The collection unit collects audio or video, for example, from the microphone or camera of a smartphone or IoT device. The collection unit can also automatically filter surrounding environmental sounds and background noise when collecting audio or video. For example, the collection unit can analyze surrounding environmental sounds in real time and remove background noise when collecting audio or video. Furthermore, the collection unit can start collection when a specific keyword or action is triggered when collecting audio or video. For example, the collection unit can start collecting audio when a specific keyword (e.g., "help") is detected. Step 2: The analysis unit uses the generation AI to analyze the audio and video collected by the collection unit. The analysis unit analyzes, for example, the tone and content of the audio, and the movements and facial expressions of the video. For example, the analysis unit can analyze the tone of the audio to detect changes in emotions. The analysis unit can also analyze the movements of the video to detect specific behavioral patterns. Furthermore, the analysis unit can analyze both the audio and video and output comprehensive analysis results. Step 3: The detection unit detects the occurrence of bullying based on the information analyzed by the analysis unit. The detection unit can detect signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. Step 4: The notification unit notifies the occurrence of bullying detected by the detection unit. The notification unit can send a notification to other people nearby using GPS information, for example. For example, the notification unit can immediately notify the smartphone apps of other people near the location where the bullying was detected that bullying has been detected.

[0098] (Example 2) A bullying detection system according to an embodiment of the present invention collects audio and video, analyzes it using a generation AI, and detects and notifies users when bullying occurs. The bullying detection system collects audio and video from the microphones and cameras of smartphones and IoT devices, and then uses a generation AI to analyze the collected audio and video to detect bullying. For example, the generation AI analyzes the tone and content of audio, and the movements and facial expressions of video to detect signs of bullying. When bullying is detected, the generation AI immediately notifies the smartphone apps of other users nearby the location that bullying has been detected. The notified users (e.g., users in a specific location) can then take action, such as rushing to the scene or observing it from a distance and reporting it to the police. This enables early detection and rapid response to bullying, and is expected to have a deterrent effect. This allows the bullying detection system to quickly detect and notify users when bullying occurs. For example, when bullying is detected within a school, teachers and staff can respond quickly to minimize the damage. Additionally, if bullying is detected in the street, a large number of people nearby can report it to the police, allowing for a swift response.

[0099] A bullying detection system according to an embodiment includes a collection unit, an analysis unit, a detection unit, and a notification unit. The collection unit collects audio or video. For example, the collection unit collects audio or video from a microphone or camera of a smartphone or IoT device. The collection unit can also automatically filter surrounding environmental sounds and background noise when collecting audio or video. For example, the collection unit can analyze surrounding environmental sounds in real time and remove background noise when collecting audio. Furthermore, the collection unit can start collecting audio or video in response to a specific keyword or action as a trigger. For example, the collection unit can start collecting audio when a specific keyword (e.g., "help me") is detected. The analysis unit uses a generative AI to analyze the audio or video collected by the collection unit. For example, the analysis unit can analyze the tone and content of the audio, and the movements and facial expressions of the video. For example, the analysis unit can analyze the tone of the audio to detect changes in emotions. The analysis unit can also analyze the movements of the video to detect specific behavioral patterns. Furthermore, the analysis unit can analyze both audio and video and output comprehensive analysis results. The detection unit detects the occurrence of bullying based on the information analyzed by the analysis unit. The detection unit can detect signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. The notification unit notifies the occurrence of bullying detected by the detection unit. The notification unit can send a notification to nearby others using, for example, GPS information. For example, the notification unit can immediately notify smartphone apps of others near the location where bullying was detected that bullying has been detected. This allows the bullying detection system according to the embodiment to quickly detect and notify the occurrence of bullying. For example, if bullying is detected in a school, teachers and staff can respond quickly, minimizing damage. Furthermore, if bullying is detected on the street, a rapid response can be achieved by an unspecified number of people nearby reporting the incident to the police.

[0100] The analysis unit can analyze the tone or content of the voice, and the movements or facial expressions of the video. For example, the analysis unit can analyze the tone of the voice to detect changes in emotions. For example, the analysis unit can analyze changes in the tone of the voice to detect emotions such as anger or sadness. The analysis unit can also analyze the content of the voice to detect specific keywords. For example, the analysis unit can analyze the content of the voice to detect keywords such as "help" or "stop." The analysis unit can also analyze the movements in the video to detect specific behavioral patterns. For example, the analysis unit can analyze the movements in the video to detect violent actions or fleeing actions. The analysis unit can also analyze facial expressions in the video to detect changes in emotions. For example, the analysis unit can analyze facial expressions in the video to detect emotions such as anger or sadness. This enables the detailed analysis of the voice and video to detect signs of bullying with high accuracy. Some or all of the above-mentioned processing in the analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the analysis unit can use a generative AI model that takes inputs such as the tone and content of audio, and the movements and facial expressions of video, and outputs signs of bullying.

[0101] The notification unit can use GPS information to send notifications to nearby others. The notification unit can, for example, use GPS information to send notifications to nearby others. For example, the notification unit can immediately notify the smartphone apps of others near the location where bullying was detected that bullying has been detected. The notification unit can also use GPS information to limit the scope of the notification. For example, the notification unit can send notifications only to others within a certain range from the location where bullying was detected. Furthermore, the notification unit can also use GPS information to set notification priorities. For example, the notification unit can prioritize notifications to others closest to the location where bullying was detected. In this way, using GPS information allows for quick and accurate notification. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can perform notifications using an AI model that inputs GPS information and outputs the notification destination.

[0102] The collection unit can collect audio or video from a microphone or camera of a smartphone or IoT device. The collection unit, for example, collects audio using a smartphone's microphone. For example, the collection unit can collect surrounding audio in real time using the smartphone's microphone. The collection unit can also collect video using the smartphone's camera. For example, the collection unit can collect surrounding video in real time using the smartphone's camera. The collection unit can also collect audio and video using the IoT device's microphone or camera. For example, the collection unit can collect audio within a specific area using the IoT device's microphone. The collection unit can also collect video within a specific area using the IoT device's camera. This allows audio and video to be collected over a wide area using a smartphone or IoT device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can collect audio and video using an AI model that receives audio and video collected from the smartphone's or IoT device's microphone or camera and outputs collected data.

[0103] The detection unit can detect signs of bullying. The detection unit detects signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. The detection unit can also detect the occurrence of bullying when a specific behavioral pattern (e.g., violent behavior) is detected. Furthermore, the detection unit can analyze both audio and video and detect signs of bullying based on the comprehensive analysis results. For example, the detection unit can detect signs of bullying by analyzing the tone and content of audio and the movements and facial expressions of video. This enables highly accurate detection of signs of bullying and enables rapid response. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can perform detection using a generative AI model that inputs the tone and content of audio and the movements and facial expressions of video and outputs signs of bullying.

[0104] The notification unit can enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. The notification unit can, for example, enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. For example, the notification unit can notify other people who are near the location where bullying was detected that bullying has been detected and encourage them to rush to the scene. The notification unit can also enable other people who receive the notification to check from a distance and report it to the police. For example, the notification unit can encourage other people who are near the location where bullying was detected to report it to the police. This allows other people who receive the notification to respond quickly, thereby minimizing the damage caused by bullying. Some or all of the above-described processing by the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can perform notification using an AI model that inputs the behavior of the notified other person and outputs a response method.

[0105] The collection unit can estimate the user's emotions and adjust the timing of collecting audio and video based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of collecting audio and video based on the estimated user emotions. For example, when the user is nervous, the collection unit can collect detailed data by increasing the collection timing. Furthermore, when the user is relaxed, the collection unit can also collect data at intervals to collect the minimum amount of data necessary. Furthermore, when the user is excited, the collection unit can also collect data immediately by increasing the collection timing to closer to real time. This allows for more appropriate data to be collected by adjusting the collection timing according to the user's emotions. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can adjust the collection timing using an AI model that inputs user emotion data and outputs the collection timing.

[0106] The collection unit can automatically filter ambient environmental sounds and background noise when collecting audio and video. For example, the collection unit can analyze ambient environmental sounds in real time and remove background noise when collecting audio. For example, the collection unit can automatically remove noise in a specific frequency band when collecting audio to collect clear data. The collection unit can also automatically filter areas with little movement in the video to highlight important movements when collecting video. For example, the collection unit can filter background areas with little movement and highlight areas with a lot of movement when collecting video. Furthermore, the collection unit can automatically remove specific noise when collecting audio and video to collect clear data. For example, the collection unit can remove noise in a specific frequency band when collecting audio and video to collect clear data. This allows clear data to be collected by removing ambient sounds and background noise. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can perform filtering using an AI model that receives audio and video data as input and outputs noise-removed data.

[0107] When collecting audio or video, the collection unit can start collection when a specific keyword or action is triggered. For example, the collection unit can start audio collection when a specific keyword (e.g., "help me") is detected. For example, the collection unit can start audio collection and collect detailed data when a specific keyword is detected. The collection unit can also start video collection when a specific action (e.g., waving one's hand) is detected. For example, the collection unit can start video collection and collect detailed data when a specific action is detected. Furthermore, the collection unit can simultaneously start collecting audio and video when a combination of a keyword and action (e.g., waving one's hand while shouting "help") is detected. For example, when a combination of a keyword and action is detected, the collection unit can simultaneously start collecting audio and video and collect detailed data. In this way, by starting collection when a specific keyword or action is triggered, important data can be collected without missing anything. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can start collection using an AI model that receives a specific keyword or action as input and outputs a trigger to start collection.

[0108] The collection unit can automatically adjust the position and angle of the collection device when collecting audio and video. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. The collection unit can also automatically adjust the angle of a camera when collecting video to collect optimal video. For example, the collection unit can automatically adjust the angle of a camera when collecting video to collect optimal video. Furthermore, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. For example, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. This allows optimal data to be collected by automatically adjusting the position and angle of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can make adjustments using an AI model that inputs the position and angle of the collection device and outputs the optimal position and angle.

[0109] The collection unit can estimate the user's emotions and determine the priority of the audio and video to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and determines the priority of the audio and video to be collected based on the estimated user emotions. For example, when the user is nervous, the collection unit can prioritize collecting audio and collect detailed conversation content. Furthermore, when the user is relaxed, the collection unit can prioritize collecting video and collect detailed information about the surrounding situation. Furthermore, when the user is excited, the collection unit can simultaneously collect both audio and video to collect comprehensive data. In this way, by determining the priority of the audio and video to be collected according to the user's emotions, important data can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can determine the priority using an AI model that inputs user emotion data and outputs the priority of the audio and video to be collected.

[0110] When collecting audio and video, the collection unit can customize the collection method by referring to the user's past behavioral history. The collection unit customizes the collection method by referring to, for example, the user's past behavioral history. For example, the collection unit can customize the collection method based on patterns of audio and video that the user frequently collected in the past. The collection unit can also determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. For example, the collection unit can determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. Furthermore, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. For example, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. In this way, the optimal collection method can be provided by referring to the user's past behavioral history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can customize the collection method using an AI model that uses the user's past behavioral history data as input and customizes the collection method.

[0111] When collecting audio or video, the collection unit can adjust the collection frequency taking into account the remaining battery level of the collection device. For example, when the remaining battery level of the collection device is low, the collection unit reduces the collection frequency to conserve battery power. For example, when the remaining battery level of the collection device is low, the collection unit can reduce the collection frequency to conserve battery power. Furthermore, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. For example, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. Furthermore, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. For example, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. This enables efficient data collection by taking the remaining battery level of the collection device into account. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can adjust the collection frequency using an AI model that inputs remaining battery level data of the collection device and outputs a collection frequency.

[0112] When collecting audio and video, the collection unit can limit the collection range based on the location information of the collection device. For example, the collection unit collects audio and video only within a specific area based on the location information of the collection device. For example, the collection unit can collect audio and video only within a specific area based on the location information of the collection device. The collection unit can also automatically adjust the collection range based on the location information of the collection device to collect optimal data. For example, the collection unit can automatically adjust the collection range based on the location information of the collection device to collect optimal data. Furthermore, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. For example, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. This enables efficient data collection by limiting the collection range based on the location information of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can limit the collection range using an AI model that inputs the location information of the collection device and outputs the collection range.

[0113] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. For example, if the user is nervous, the analysis unit can use an algorithm that is sensitive to changes in emotions for analysis. Also, if the user is relaxed, the analysis unit can use an algorithm that is insensitive to changes in emotions for analysis. Furthermore, if the user is excited, the analysis unit can use an algorithm that is neutral to changes in emotions for analysis. This allows for more appropriate analysis by adjusting the analysis algorithm according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can adjust the algorithm using a generative AI model that inputs user emotion data and outputs an analysis algorithm.

[0114] The analysis unit can improve analysis accuracy by combining multiple analysis algorithms when analyzing audio or video. For example, the analysis unit can improve analysis accuracy by combining a voice recognition algorithm and an emotion analysis algorithm when analyzing audio. For example, the analysis unit can analyze audio data using a voice recognition algorithm and detect emotional changes using an emotion analysis algorithm. Furthermore, the analysis unit can improve analysis accuracy by combining a face recognition algorithm and a motion analysis algorithm when analyzing video. For example, the analysis unit can analyze video data using a face recognition algorithm and detect specific behavioral patterns using a motion analysis algorithm. Furthermore, the analysis unit can use multiple algorithms in parallel when analyzing audio and video to improve overall analysis accuracy. For example, the analysis unit can combine a voice recognition algorithm and an emotion analysis algorithm, or a face recognition algorithm and a motion analysis algorithm to improve overall analysis accuracy. Thus, combining multiple analysis algorithms improves analysis accuracy. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can perform analysis using multiple generative AI models that input audio or video data and output analysis results.

[0115] When analyzing audio or video, the analysis unit can optimize analysis parameters by referring to past analysis results. The analysis unit, for example, optimizes current analysis parameters based on past audio analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio analysis results. The analysis unit can also optimize current analysis parameters based on past video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past video analysis results. Furthermore, the analysis unit can optimize current analysis parameters by comprehensively referring to past audio and video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio and video analysis results. In this way, current analysis parameters can be optimized by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can optimize parameters using a generation AI model that inputs past analysis result data and outputs optimal analysis parameters.

[0116] The analysis unit can prioritize analysis of specific patterns or signals when analyzing audio or video. For example, the analysis unit prioritizes analysis of specific keywords or phrases when analyzing audio. For example, the analysis unit can prioritize analysis of specific keywords (e.g., "help me") or phrases to collect detailed data. The analysis unit can also prioritize analysis of specific actions or facial expressions when analyzing video. For example, the analysis unit can prioritize analysis of specific actions (e.g., waving one's hand) or facial expressions to collect detailed data. Furthermore, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. For example, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. By prioritizing analysis of specific patterns or signals, results can be quickly provided. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can perform analysis using a generative AI model that takes specific patterns or signals as input and outputs analysis results.

[0117] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is excited, the analysis unit can provide a visually stimulating display method. This allows for more appropriate information provision by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the display method using a generation AI model that inputs user emotion data and outputs a display method of the analysis results.

[0118] When analyzing audio or video, the analysis unit can determine the analysis priority according to the amount of data to be analyzed. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts and collect detailed data. Furthermore, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes. For example, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes and collect detailed data. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data. For example, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data to perform efficient analysis. This enables efficient analysis by determining the priority according to the amount of data to be analyzed. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can determine the priority using a generative AI model that inputs the amount of data to be analyzed and outputs the analysis priority.

[0119] The analysis unit may be added with a function of feeding back analysis results in real time when analyzing audio or video. The analysis unit, for example, may feed back audio analysis results in real time, enabling immediate response. For example, the analysis unit may feed back audio analysis results in real time, enabling immediate response. The analysis unit may also feed back video analysis results in real time, enabling immediate response. For example, the analysis unit may feed back video analysis results in real time, enabling immediate response. The analysis unit may also feed back audio and video analysis results in real time, enabling comprehensive response. For example, the analysis unit may feed back audio and video analysis results in real time, enabling comprehensive response. As a result, real-time feedback enables immediate response. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit may provide feedback using a generative AI model that receives audio and video analysis results as input and provides feedback in real time.

[0120] When analyzing audio or video, the analysis unit can cooperate with other systems to share the analysis results. The analysis unit, for example, cooperates with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. This enables comprehensive data analysis by coordinating with other systems. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can input audio or video analysis results and share the analysis results using a generative AI model that cooperates with other systems to share the analysis results.

[0121] The detection unit can estimate the user's emotions and adjust the detection threshold based on the estimated user's emotions. The detection unit, for example, estimates the user's emotions and adjusts the detection threshold based on the estimated user's emotions. For example, if the user is nervous, the detection unit can set the detection threshold low and respond sensitively. Furthermore, if the user is relaxed, the detection unit can set the detection threshold high and respond only to the minimum required level. Furthermore, if the user is excited, the detection unit can set the detection threshold neutrally and respond in a balanced manner. This enables more appropriate detection by adjusting the detection threshold according to the user's emotions. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can adjust the threshold using a generative AI model that inputs user emotion data and outputs a detection threshold.

[0122] When detecting signs of bullying, the detection unit can improve detection accuracy by integrating multiple data sources. The detection unit, for example, integrates audio data and video data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and video data to detect signs of bullying with high accuracy. The detection unit can also integrate audio data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and text data to detect signs of bullying with high accuracy. The detection unit can also integrate video data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate video data and text data to detect signs of bullying with high accuracy. In this way, by integrating multiple data sources, detection accuracy is improved. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the detection unit can perform detection using a generative AI model that takes multiple data sources as input and outputs signs of bullying.

[0123] When detecting signs of bullying, the detection unit can optimize the detection algorithm by referring to past detection results. The detection unit, for example, optimizes the current detection algorithm based on the detection results of past audio data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio data. The detection unit can also optimize the current detection algorithm based on the detection results of past video data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past video data. The detection unit can also optimize the current detection algorithm by comprehensively referring to past audio and video detection results. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio and video. In this way, the current detection algorithm can be optimized by referring to the past detection results. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the detection unit can optimize the algorithm using a generative AI model that inputs past detection result data and outputs an optimal detection algorithm.

[0124] When detecting signs of bullying, the detection unit can strengthen detection by using specific actions or statements as triggers. For example, the detection unit strengthens detection when a specific action (e.g., violent behavior) is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific action is detected. The detection unit can also strengthen detection when a specific statement (e.g., offensive language such as "die") is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific statement is detected. Furthermore, the detection unit can strengthen detection when a combination of action and statement (e.g., violent actions and offensive language) is detected. For example, the detection unit can strengthen detection and collect detailed data when a combination of action and statement is detected. This enables a rapid response by strengthening detection when specific actions or statements are triggered. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI. For example, the detection unit can strengthen detection by using a generative AI model that inputs specific actions or statements and outputs a trigger for strengthening detection.

[0125] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, the detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, if the user is nervous, the detection unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the detection unit can provide a display method including detailed information. Furthermore, if the user is excited, the detection unit can provide a visually stimulating display method. This enables more appropriate information provision by adjusting the display method of the detection result according to the user's emotion. Some or all of the above-described processing in the detection unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the detection unit can adjust the display method using a generative AI model that inputs user emotion data and outputs a display method of the detection result.

[0126] When detecting signs of bullying, the detection unit can determine the detection priority according to the amount of data of the detection target. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts and collect detailed data. Furthermore, when there is a large amount of video data, the detection unit can prioritize detecting important scenes. For example, when there is a large amount of video data, the detection unit can prioritize detecting important scenes and collect detailed data. Furthermore, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data. For example, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data to perform efficient detection. This enables efficient detection by determining the priority according to the amount of data of the detection target. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can determine the priority using a generative AI model that inputs the amount of data of the detection target and outputs the detection priority.

[0127] The detection unit may be added with a function for feeding back detection results in real time when detecting signs of bullying. The detection unit, for example, may feed back detection results of audio data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of audio data in real time, enabling an immediate response. The detection unit may also feed back detection results of video data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of video data in real time, enabling an immediate response. The detection unit may also feed back detection results of audio and video in real time, enabling a comprehensive response. For example, the detection unit may feed back detection results of audio and video in real time, enabling a comprehensive response. As a result, real-time feedback enables an immediate response. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit may provide feedback using a generative AI model that receives detection results of audio and video and provides feedback in real time.

[0128] When detecting signs of bullying, the detection unit can cooperate with other systems to share the detection results. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of video data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of video data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. This enables comprehensive data analysis by cooperating with other systems. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can input the detection results of audio and video and share the detection results using a generative AI model that cooperates with other systems to share the detection results.

[0129] The notification unit can estimate the user's emotions and adjust the content and timing of notifications based on the estimated user emotions. The notification unit, for example, estimates the user's emotions and adjusts the content and timing of notifications based on the estimated user emotions. For example, if the user is nervous, the notification unit can immediately send a concise and clear notification. Furthermore, if the user is relaxed, the notification unit can also send a notification containing detailed information at an appropriate time. Furthermore, if the user is excited, the notification unit can also immediately send a visually stimulating notification. This allows for more appropriate notifications by adjusting the content and timing of notifications according to the user's emotions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can adjust notifications using an AI model that inputs user emotion data and outputs the content and timing of notifications.

[0130] When notifying an occurrence of bullying, the notification unit can set a priority for the notification and provide a notification according to the level of importance. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority to encourage a prompt response. Furthermore, if a sign of minor bullying is detected, the notification unit can send a notification with normal priority to encourage a prompt response. Furthermore, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance. For example, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance to encourage an optimal response. This enables a prompt and appropriate response by providing a notification according to the level of importance. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can make notifications using an AI model that inputs bullying symptom data and outputs notification priorities.

[0131] The notification unit can customize the format of the notification (text, audio, video, etc.) when notifying an occurrence of bullying. For example, the notification unit can send a text notification and provide detailed information. For example, the notification unit can send a text notification and provide detailed information. The notification unit can also send an audio notification to encourage a prompt response. For example, the notification unit can send an audio notification to encourage a prompt response. Furthermore, the notification unit can send a video notification to visually convey the situation at the scene. For example, the notification unit can send a video notification to visually convey the situation at the scene. In this way, customizing the notification format makes it possible to provide optimal information to the recipient. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can customize the notification using an AI model that inputs the content of the notification and outputs the format of the notification.

[0132] When notifying an occurrence of bullying, the notification unit can save the notification history so that it can be referenced later. For example, the notification unit can save the notification history and perform a detailed analysis later. For example, the notification unit can save the notification history and perform a detailed analysis later. The notification unit can also save the notification history and check past response statuses. For example, the notification unit can save the notification history and check past response statuses. Furthermore, the notification unit can save the notification history and use it for future improvements. For example, the notification unit can save the notification history and use it for future improvements. In this way, saving the notification history enables later detailed analysis and confirmation. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can manage the history using an AI model that receives notification history data as input and stores and references it.

[0133] The notification unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. For example, the notification unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. For example, if the user is nervous, the notification unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the notification unit can provide a display method including detailed information. Furthermore, if the user is excited, the notification unit can provide a visually stimulating display method. This allows for more appropriate information provision by adjusting the notification display method according to the user's emotion. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can adjust the display method using an AI model that inputs user emotion data and outputs a notification display method.

[0134] When notifying the user of an incident of bullying, the notification unit can select the optimal notification method by taking into consideration device information of the notification target. For example, if the user is using a smartphone, the notification unit sends a push notification. For example, if the user is using a smartphone, the notification unit can send a push notification to encourage a prompt response. Furthermore, if the user is using a tablet, the notification unit can send a notification optimized for a large screen. For example, if the user is using a tablet, the notification unit can send a notification optimized for a large screen and provide detailed information. Furthermore, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification. For example, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification to encourage a prompt response. This makes it possible to provide the optimal notification method by taking into consideration device information of the notification target. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that inputs device information of the notification target and outputs the optimal notification method.

[0135] When notifying an occurrence of bullying, the notification unit can make the content of the notification multilingual. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. The notification unit can also automatically set the language of the notification based on the language setting of the user's device. For example, the notification unit can automatically set the language of the notification based on the language setting of the user's device. Furthermore, the notification unit can provide a language switching function when a user speaks multiple languages. For example, when a user speaks multiple languages, the notification unit can provide a language switching function and provide a notification in an appropriate language. This provides multilingual support to accommodate users who speak different languages. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can provide a notification using an AI model that inputs the content of the notification and translates it into multiple languages.

[0136] When notifying an occurrence of bullying, the notification unit can customize the content of the notification to provide information according to the recipient's attributes. For example, the notification unit can send a notification including detailed response procedures to faculty and staff. For example, the notification unit can send a notification including detailed response procedures to faculty and staff to encourage a prompt response. The notification unit can also send a concise, easy-to-understand notification to students. For example, the notification unit can send a concise, easy-to-understand notification to students to encourage an appropriate response. Furthermore, the notification unit can send a notification encouraging a prompt response to an unspecified number of people. For example, the notification unit can send a notification encouraging a prompt response to an unspecified number of people to encourage an appropriate response. This enables a more appropriate response by providing information according to the recipient's attributes. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can send a notification using an AI model that inputs the recipient's attribute data and customizes the content of the notification.

[0137] The analysis unit can analyze the tone and content of audio, as well as the movements and facial expressions of video. The analysis unit, for example, analyzes the tone of audio to detect changes in emotions. For example, the analysis unit can analyze changes in the tone of audio to detect emotions such as anger or sadness. The analysis unit can also analyze the content of audio to detect specific keywords. For example, the analysis unit can analyze the content of audio to detect keywords such as "help" or "stop." The analysis unit can also analyze the movements in video to detect specific behavioral patterns. For example, the analysis unit can analyze the movements in video to detect violent actions or fleeing actions. The analysis unit can also analyze facial expressions in video to detect changes in emotions. For example, the analysis unit can analyze facial expressions in video to detect emotions such as anger or sadness. This enables the detailed analysis of audio and video to detect signs of bullying with high accuracy. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can use a generative AI model that takes inputs such as the tone and content of audio, and the movements and facial expressions of video, and outputs signs of bullying.

[0138] The notification unit can use GPS information to send notifications to nearby others. The notification unit can, for example, use GPS information to send notifications to nearby others. For example, the notification unit can immediately notify the smartphone apps of others near the location where bullying was detected that bullying has been detected. The notification unit can also use GPS information to limit the scope of the notification. For example, the notification unit can send notifications only to others within a certain range from the location where bullying was detected. Furthermore, the notification unit can also use GPS information to set notification priorities. For example, the notification unit can prioritize notifications to others closest to the location where bullying was detected. In this way, using GPS information allows for quick and accurate notification. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can perform notifications using an AI model that inputs GPS information and outputs the notification destination.

[0139] The collection unit can collect audio and video from a microphone or camera of a smartphone or IoT device. The collection unit, for example, collects audio using a smartphone's microphone. For example, the collection unit can collect surrounding audio in real time using the smartphone's microphone. The collection unit can also collect video using the smartphone's camera. For example, the collection unit can collect surrounding video in real time using the smartphone's camera. The collection unit can also collect audio and video using the IoT device's microphone or camera. For example, the collection unit can collect audio within a specific area using the IoT device's microphone. The collection unit can also collect video within a specific area using the IoT device's camera. This allows audio and video to be collected over a wide area using a smartphone or IoT device. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can perform collection using an AI model that receives audio and video collected from the smartphone's or IoT device's microphone or camera and outputs collected data.

[0140] The detection unit can detect signs of bullying. The detection unit detects signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. The detection unit can also detect the occurrence of bullying when a specific behavioral pattern (e.g., violent behavior) is detected. Furthermore, the detection unit can analyze both audio and video and detect signs of bullying based on the comprehensive analysis results. For example, the detection unit can detect signs of bullying by analyzing the tone and content of audio and the movements and facial expressions of video. This enables highly accurate detection of signs of bullying and enables rapid response. Some or all of the above-mentioned processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can perform detection using a generative AI model that inputs the tone and content of audio and the movements and facial expressions of video and outputs signs of bullying.

[0141] The notification unit can enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. The notification unit can, for example, enable other people who receive the notification to rush to the scene or check from a distance and report it to the police. For example, the notification unit can notify other people who are near the location where bullying was detected that bullying has been detected and encourage them to rush to the scene. The notification unit can also enable other people who receive the notification to check from a distance and report it to the police. For example, the notification unit can encourage other people who are near the location where bullying was detected to report it to the police. This allows other people who receive the notification to respond quickly, thereby minimizing the damage caused by bullying. Some or all of the above-described processing by the notification unit can be performed, for example, using AI or without AI. For example, the notification unit can perform notification using an AI model that inputs the behavior of the notified other person and outputs a response method.

[0142] The collection unit can estimate the user's emotions and adjust the timing of collecting audio and video based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of collecting audio and video based on the estimated user emotions. For example, when the user is nervous, the collection unit can collect detailed data by increasing the collection timing. Furthermore, when the user is relaxed, the collection unit can also collect data at intervals to collect the minimum amount of data necessary. Furthermore, when the user is excited, the collection unit can also collect data immediately by increasing the collection timing to closer to real time. This allows for more appropriate data to be collected by adjusting the collection timing according to the user's emotions. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can adjust the collection timing using an AI model that inputs user emotion data and outputs the collection timing.

[0143] The collection unit can automatically filter ambient environmental sounds and background noise when collecting audio and video. For example, the collection unit can analyze ambient environmental sounds in real time and remove background noise when collecting audio. For example, the collection unit can automatically remove noise in a specific frequency band when collecting audio to collect clear data. The collection unit can also automatically filter areas with little movement in the video to highlight important movements when collecting video. For example, the collection unit can filter background areas with little movement and highlight areas with a lot of movement when collecting video. Furthermore, the collection unit can automatically remove specific noise when collecting audio and video to collect clear data. For example, the collection unit can remove noise in a specific frequency band when collecting audio and video to collect clear data. This allows clear data to be collected by removing ambient sounds and background noise. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can perform filtering using an AI model that receives audio and video data as input and outputs noise-removed data.

[0144] When collecting audio or video, the collection unit can start collection when a specific keyword or action is triggered. For example, the collection unit can start audio collection when a specific keyword (e.g., "help me") is detected. For example, the collection unit can start audio collection and collect detailed data when a specific keyword is detected. The collection unit can also start video collection when a specific action (e.g., waving one's hand) is detected. For example, the collection unit can start video collection and collect detailed data when a specific action is detected. Furthermore, the collection unit can simultaneously start collecting audio and video when a combination of a keyword and action (e.g., waving one's hand while shouting "help") is detected. For example, when a combination of a keyword and action is detected, the collection unit can simultaneously start collecting audio and video and collect detailed data. In this way, by starting collection when a specific keyword or action is triggered, important data can be collected without missing anything. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit can start collection using an AI model that receives a specific keyword or action as input and outputs a trigger to start collection.

[0145] The collection unit can automatically adjust the position and angle of the collection device when collecting audio and video. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. For example, the collection unit can automatically adjust the direction of a microphone when collecting audio to collect optimal audio. The collection unit can also automatically adjust the angle of a camera when collecting video to collect optimal video. For example, the collection unit can automatically adjust the angle of a camera when collecting video to collect optimal video. Furthermore, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. For example, the collection unit can automatically adjust the position of a device when collecting audio and video to collect optimal data. This allows optimal data to be collected by automatically adjusting the position and angle of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can make adjustments using an AI model that inputs the position and angle of the collection device and outputs the optimal position and angle.

[0146] The collection unit can estimate the user's emotions and determine the priority of the audio and video to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and determines the priority of the audio and video to be collected based on the estimated user emotions. For example, when the user is nervous, the collection unit can prioritize collecting audio and collect detailed conversation content. Furthermore, when the user is relaxed, the collection unit can prioritize collecting video and collect detailed information about the surrounding situation. Furthermore, when the user is excited, the collection unit can simultaneously collect both audio and video to collect comprehensive data. In this way, by determining the priority of the audio and video to be collected according to the user's emotions, important data can be collected preferentially. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can determine the priority using an AI model that inputs user emotion data and outputs the priority of the audio and video to be collected.

[0147] When collecting audio and video, the collection unit can customize the collection method by referring to the user's past behavioral history. The collection unit customizes the collection method by referring to, for example, the user's past behavioral history. For example, the collection unit can customize the collection method based on patterns of audio and video that the user frequently collected in the past. The collection unit can also determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. For example, the collection unit can determine the priority of audio and video to be collected during a specific time period based on the user's past behavioral history. Furthermore, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. For example, the collection unit can analyze the user's past behavioral history and suggest the optimal collection timing. In this way, the optimal collection method can be provided by referring to the user's past behavioral history. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can customize the collection method using an AI model that uses the user's past behavioral history data as input and customizes the collection method.

[0148] When collecting audio or video, the collection unit can adjust the collection frequency taking into account the remaining battery level of the collection device. For example, when the remaining battery level of the collection device is low, the collection unit reduces the collection frequency to conserve battery power. For example, when the remaining battery level of the collection device is low, the collection unit can reduce the collection frequency to conserve battery power. Furthermore, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. For example, when the remaining battery level of the collection device is sufficient, the collection unit can increase the collection frequency to collect detailed data. Furthermore, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. For example, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. This enables efficient data collection by taking the remaining battery level of the collection device into account. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can adjust the collection frequency using an AI model that inputs remaining battery level data of the collection device and outputs a collection frequency.

[0149] When collecting audio and video, the collection unit can limit the collection range based on the location information of the collection device. For example, the collection unit collects audio and video only within a specific area based on the location information of the collection device. For example, the collection unit can collect audio and video only within a specific area based on the location information of the collection device. The collection unit can also automatically adjust the collection range based on the location information of the collection device to collect optimal data. For example, the collection unit can automatically adjust the collection range based on the location information of the collection device to collect optimal data. Furthermore, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. For example, the collection unit can monitor the location information of the collection device in real time and dynamically change the collection range. This enables efficient data collection by limiting the collection range based on the location information of the collection device. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can limit the collection range using an AI model that inputs the location information of the collection device and outputs the collection range.

[0150] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. The analysis unit, for example, estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. For example, if the user is nervous, the analysis unit can use an algorithm that is sensitive to changes in emotions for analysis. Also, if the user is relaxed, the analysis unit can use an algorithm that is insensitive to changes in emotions for analysis. Furthermore, if the user is excited, the analysis unit can use an algorithm that is neutral to changes in emotions for analysis. This allows for more appropriate analysis by adjusting the analysis algorithm according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can adjust the algorithm using a generative AI model that inputs user emotion data and outputs an analysis algorithm.

[0151] The analysis unit can improve analysis accuracy by combining multiple analysis algorithms when analyzing audio or video. For example, the analysis unit can improve analysis accuracy by combining a voice recognition algorithm and an emotion analysis algorithm when analyzing audio. For example, the analysis unit can analyze audio data using a voice recognition algorithm and detect emotional changes using an emotion analysis algorithm. Furthermore, the analysis unit can improve analysis accuracy by combining a face recognition algorithm and a motion analysis algorithm when analyzing video. For example, the analysis unit can analyze video data using a face recognition algorithm and detect specific behavioral patterns using a motion analysis algorithm. Furthermore, the analysis unit can use multiple algorithms in parallel when analyzing audio and video to improve overall analysis accuracy. For example, the analysis unit can combine a voice recognition algorithm and an emotion analysis algorithm, or a face recognition algorithm and a motion analysis algorithm to improve overall analysis accuracy. Thus, combining multiple analysis algorithms improves analysis accuracy. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can perform analysis using multiple generative AI models that input audio or video data and output analysis results.

[0152] When analyzing audio or video, the analysis unit can optimize analysis parameters by referring to past analysis results. The analysis unit, for example, optimizes current analysis parameters based on past audio analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio analysis results. The analysis unit can also optimize current analysis parameters based on past video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past video analysis results. Furthermore, the analysis unit can optimize current analysis parameters by comprehensively referring to past audio and video analysis results. For example, the analysis unit can optimize current analysis parameters by referring to past audio and video analysis results. In this way, current analysis parameters can be optimized by referring to past analysis results. Some or all of the above-mentioned processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can optimize parameters using a generation AI model that inputs past analysis result data and outputs optimal analysis parameters.

[0153] The analysis unit can prioritize analysis of specific patterns or signals when analyzing audio or video. For example, the analysis unit prioritizes analysis of specific keywords or phrases when analyzing audio. For example, the analysis unit can prioritize analysis of specific keywords (e.g., "help me") or phrases to collect detailed data. The analysis unit can also prioritize analysis of specific actions or facial expressions when analyzing video. For example, the analysis unit can prioritize analysis of specific actions (e.g., waving one's hand) or facial expressions to collect detailed data. Furthermore, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. For example, the analysis unit can prioritize analysis of specific patterns or signals when analyzing audio and video to quickly provide results. By prioritizing analysis of specific patterns or signals, results can be quickly provided. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can perform analysis using a generative AI model that takes specific patterns or signals as input and outputs analysis results.

[0154] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, the analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is nervous, the analysis unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the analysis unit can provide a display method that includes detailed information. Furthermore, if the user is excited, the analysis unit can provide a visually stimulating display method. This allows for more appropriate information provision by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-described processing in the analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the analysis unit can adjust the display method using a generation AI model that inputs user emotion data and outputs a display method of the analysis results.

[0155] When analyzing audio or video, the analysis unit can determine the analysis priority according to the amount of data to be analyzed. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts. For example, when there is a large amount of audio data, the analysis unit can prioritize analyzing important parts and collect detailed data. Furthermore, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes. For example, when there is a large amount of video data, the analysis unit can prioritize analyzing important scenes and collect detailed data. Furthermore, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data. For example, the analysis unit can dynamically adjust the analysis priority according to the amount of audio and video data to perform efficient analysis. This enables efficient analysis by determining the priority according to the amount of data to be analyzed. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can determine the priority using a generative AI model that inputs the amount of data to be analyzed and outputs the analysis priority.

[0156] The analysis unit may be added with a function of feeding back analysis results in real time when analyzing audio or video. The analysis unit, for example, may feed back audio analysis results in real time, enabling immediate response. For example, the analysis unit may feed back audio analysis results in real time, enabling immediate response. The analysis unit may also feed back video analysis results in real time, enabling immediate response. For example, the analysis unit may feed back video analysis results in real time, enabling immediate response. The analysis unit may also feed back audio and video analysis results in real time, enabling comprehensive response. For example, the analysis unit may feed back audio and video analysis results in real time, enabling comprehensive response. As a result, real-time feedback enables immediate response. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit may provide feedback using a generative AI model that receives audio and video analysis results as input and provides feedback in real time.

[0157] When analyzing audio or video, the analysis unit can cooperate with other systems to share the analysis results. The analysis unit, for example, cooperates with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. The analysis unit can also cooperate with other systems to perform comprehensive data analysis. For example, the analysis unit can cooperate with other systems to perform comprehensive data analysis. This enables comprehensive data analysis by coordinating with other systems. Some or all of the above-described processing in the analysis unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the analysis unit can input audio or video analysis results and share the analysis results using a generative AI model that cooperates with other systems to share the analysis results.

[0158] The detection unit can estimate the user's emotions and adjust the detection threshold based on the estimated user's emotions. The detection unit, for example, estimates the user's emotions and adjusts the detection threshold based on the estimated user's emotions. For example, if the user is nervous, the detection unit can set the detection threshold low and respond sensitively. Furthermore, if the user is relaxed, the detection unit can set the detection threshold high and respond only to the minimum required level. Furthermore, if the user is excited, the detection unit can set the detection threshold neutrally and respond in a balanced manner. This enables more appropriate detection by adjusting the detection threshold according to the user's emotions. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can adjust the threshold using a generative AI model that inputs user emotion data and outputs a detection threshold.

[0159] When detecting signs of bullying, the detection unit can improve detection accuracy by integrating multiple data sources. The detection unit, for example, integrates audio data and video data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and video data to detect signs of bullying with high accuracy. The detection unit can also integrate audio data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate audio data and text data to detect signs of bullying with high accuracy. The detection unit can also integrate video data and text data to detect signs of bullying with high accuracy. For example, the detection unit can integrate video data and text data to detect signs of bullying with high accuracy. In this way, by integrating multiple data sources, detection accuracy is improved. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the detection unit can perform detection using a generative AI model that takes multiple data sources as input and outputs signs of bullying.

[0160] When detecting signs of bullying, the detection unit can optimize the detection algorithm by referring to past detection results. The detection unit, for example, optimizes the current detection algorithm based on the detection results of past audio data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio data. The detection unit can also optimize the current detection algorithm based on the detection results of past video data. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past video data. The detection unit can also optimize the current detection algorithm by comprehensively referring to past audio and video detection results. For example, the detection unit can optimize the current detection algorithm by referring to the detection results of past audio and video. In this way, the current detection algorithm can be optimized by referring to the past detection results. Some or all of the above-mentioned processing in the detection unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the detection unit can optimize the algorithm using a generative AI model that inputs past detection result data and outputs an optimal detection algorithm.

[0161] When detecting signs of bullying, the detection unit can strengthen detection by using specific actions or statements as triggers. For example, the detection unit strengthens detection when a specific action (e.g., violent behavior) is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific action is detected. The detection unit can also strengthen detection when a specific statement (e.g., offensive language such as "die") is detected. For example, the detection unit can strengthen detection and collect detailed data when a specific statement is detected. Furthermore, the detection unit can strengthen detection when a combination of action and statement (e.g., violent actions and offensive language) is detected. For example, the detection unit can strengthen detection and collect detailed data when a combination of action and statement is detected. This enables a rapid response by strengthening detection when specific actions or statements are triggered. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI. For example, the detection unit can strengthen detection by using a generative AI model that inputs specific actions or statements and outputs a trigger for strengthening detection.

[0162] The detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, the detection unit can estimate the user's emotion and adjust the display method of the detection result based on the estimated user's emotion. For example, if the user is nervous, the detection unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the detection unit can provide a display method including detailed information. Furthermore, if the user is excited, the detection unit can provide a visually stimulating display method. This enables more appropriate information provision by adjusting the display method of the detection result according to the user's emotion. Some or all of the above-described processing in the detection unit may be performed, for example, using a generative AI, or may be performed without using a generative AI. For example, the detection unit can adjust the display method using a generative AI model that inputs user emotion data and outputs a display method of the detection result.

[0163] When detecting signs of bullying, the detection unit can determine the detection priority according to the amount of data of the detection target. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts. For example, when there is a large amount of audio data, the detection unit can prioritize detecting important parts and collect detailed data. Furthermore, when there is a large amount of video data, the detection unit can prioritize detecting important scenes. For example, when there is a large amount of video data, the detection unit can prioritize detecting important scenes and collect detailed data. Furthermore, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data. For example, the detection unit can dynamically adjust the detection priority according to the amount of audio and video data to perform efficient detection. This enables efficient detection by determining the priority according to the amount of data of the detection target. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can determine the priority using a generative AI model that inputs the amount of data of the detection target and outputs the detection priority.

[0164] The detection unit may be added with a function for feeding back detection results in real time when detecting signs of bullying. The detection unit, for example, may feed back detection results of audio data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of audio data in real time, enabling an immediate response. The detection unit may also feed back detection results of video data in real time, enabling an immediate response. For example, the detection unit may feed back detection results of video data in real time, enabling an immediate response. The detection unit may also feed back detection results of audio and video in real time, enabling a comprehensive response. For example, the detection unit may feed back detection results of audio and video in real time, enabling a comprehensive response. As a result, real-time feedback enables an immediate response. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit may provide feedback using a generative AI model that receives detection results of audio and video and provides feedback in real time.

[0165] When detecting signs of bullying, the detection unit can cooperate with other systems to share the detection results. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of video data. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of video data. The detection unit can also cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. For example, the detection unit can cooperate with other systems to perform comprehensive data analysis of the detection results of audio and video. This enables comprehensive data analysis by cooperating with other systems. Some or all of the above-described processing in the detection unit may be performed using, for example, a generative AI, or may be performed without using a generative AI. For example, the detection unit can input the detection results of audio and video and share the detection results using a generative AI model that cooperates with other systems to share the detection results.

[0166] The notification unit can estimate the user's emotions and adjust the content and timing of notifications based on the estimated user emotions. The notification unit, for example, estimates the user's emotions and adjusts the content and timing of notifications based on the estimated user emotions. For example, if the user is nervous, the notification unit can immediately send a concise and clear notification. Furthermore, if the user is relaxed, the notification unit can also send a notification containing detailed information at an appropriate time. Furthermore, if the user is excited, the notification unit can also immediately send a visually stimulating notification. This allows for more appropriate notifications by adjusting the content and timing of notifications according to the user's emotions. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can adjust notifications using an AI model that inputs user emotion data and outputs the content and timing of notifications.

[0167] When notifying an occurrence of bullying, the notification unit can set a priority for the notification and provide a notification according to the level of importance. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority. For example, if a sign of serious bullying is detected, the notification unit can send a notification with the highest priority to encourage a prompt response. Furthermore, if a sign of minor bullying is detected, the notification unit can send a notification with normal priority to encourage a prompt response. Furthermore, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance. For example, if multiple signs of bullying are detected, the notification unit can dynamically adjust the priority of the notification according to the level of importance to encourage an optimal response. This enables a prompt and appropriate response by providing a notification according to the level of importance. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can make notifications using an AI model that inputs bullying symptom data and outputs notification priorities.

[0168] The notification unit can customize the format of the notification (text, audio, video, etc.) when notifying an occurrence of bullying. For example, the notification unit can send a text notification and provide detailed information. For example, the notification unit can send a text notification and provide detailed information. The notification unit can also send an audio notification to encourage a prompt response. For example, the notification unit can send an audio notification to encourage a prompt response. Furthermore, the notification unit can send a video notification to visually convey the situation at the scene. For example, the notification unit can send a video notification to visually convey the situation at the scene. In this way, customizing the notification format makes it possible to provide optimal information to the recipient. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can customize the notification using an AI model that inputs the content of the notification and outputs the format of the notification.

[0169] When notifying an occurrence of bullying, the notification unit can save the notification history so that it can be referenced later. For example, the notification unit can save the notification history and perform a detailed analysis later. For example, the notification unit can save the notification history and perform a detailed analysis later. The notification unit can also save the notification history and check past response statuses. For example, the notification unit can save the notification history and check past response statuses. Furthermore, the notification unit can save the notification history and use it for future improvements. For example, the notification unit can save the notification history and use it for future improvements. In this way, saving the notification history enables later detailed analysis and confirmation. Some or all of the above-mentioned processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can manage the history using an AI model that receives notification history data as input and stores and references it.

[0170] The notification unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. For example, the notification unit can estimate the user's emotion and adjust the notification display method based on the estimated user's emotion. For example, if the user is nervous, the notification unit can provide a simple, highly visible display method. Furthermore, if the user is relaxed, the notification unit can provide a display method including detailed information. Furthermore, if the user is excited, the notification unit can provide a visually stimulating display method. This allows for more appropriate information provision by adjusting the notification display method according to the user's emotion. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can adjust the display method using an AI model that inputs user emotion data and outputs a notification display method.

[0171] When notifying the user of an incident of bullying, the notification unit can select the optimal notification method by taking into consideration device information of the notification target. For example, if the user is using a smartphone, the notification unit sends a push notification. For example, if the user is using a smartphone, the notification unit can send a push notification to encourage a prompt response. Furthermore, if the user is using a tablet, the notification unit can send a notification optimized for a large screen. For example, if the user is using a tablet, the notification unit can send a notification optimized for a large screen and provide detailed information. Furthermore, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification. For example, if the user is using a smartwatch, the notification unit can send a concise, highly visible notification to encourage a prompt response. This makes it possible to provide the optimal notification method by taking into consideration device information of the notification target. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can perform notification using an AI model that inputs device information of the notification target and outputs the optimal notification method.

[0172] When notifying an occurrence of bullying, the notification unit can make the content of the notification multilingual. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. For example, the notification unit can translate the content of the notification into multiple languages ​​to accommodate users who speak different languages. The notification unit can also automatically set the language of the notification based on the language setting of the user's device. For example, the notification unit can automatically set the language of the notification based on the language setting of the user's device. Furthermore, the notification unit can provide a language switching function when a user speaks multiple languages. For example, when a user speaks multiple languages, the notification unit can provide a language switching function and provide a notification in an appropriate language. This provides multilingual support to accommodate users who speak different languages. Some or all of the above-described processing in the notification unit may be performed using, for example, AI, or may be performed without using AI. For example, the notification unit can provide a notification using an AI model that inputs the content of the notification and translates it into multiple languages.

[0173] When notifying an occurrence of bullying, the notification unit can customize the content of the notification to provide information according to the recipient's attributes. For example, the notification unit can send a notification including detailed response procedures to faculty and staff. For example, the notification unit can send a notification including detailed response procedures to faculty and staff to encourage a prompt response. The notification unit can also send a concise, easy-to-understand notification to students. For example, the notification unit can send a concise, easy-to-understand notification to students to encourage an appropriate response. Furthermore, the notification unit can send a notification encouraging a prompt response to an unspecified number of people. For example, the notification unit can send a notification encouraging a prompt response to an unspecified number of people to encourage an appropriate response. This enables a more appropriate response by providing information according to the recipient's attributes. Some or all of the above-described processing by the notification unit may be performed using, for example, AI, or may be performed without AI. For example, the notification unit can send a notification using an AI model that inputs the recipient's attribute data and customizes the content of the notification. === Hard Collateral 1-1 === Each of the multiple elements including the collection unit, analysis unit, detection unit, and notification unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit collects audio and video using a microphone or camera of the smart device 14. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected audio and video using a generative AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects the occurrence of bullying based on the analysis results. The notification unit is realized, for example, by the control unit 46A of the smart device 14 and sends a notification to the smartphone app of another person nearby when bullying is detected. === Hard Collateral 1-2 === Each of the multiple elements including the collection unit, analysis unit, detection unit, and notification unit described above is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit collects audio and video using a microphone and camera of the smart glasses 214. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the collected audio and video using a generative AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and detects the occurrence of bullying based on the analysis results. The notification unit is realized, for example, by the control unit 46A of the smart glasses 214 and sends a notification to the smartphone app of another person nearby when bullying is detected. === Hard Collateral 1-3 === Each of the multiple elements including the collection unit, analysis unit, detection unit, and notification unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit collects audio and video using a microphone or camera of the headset-type terminal 314. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected audio and video using a generative AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and detects the occurrence of bullying based on the analysis results. The notification unit is realized, for example, by the control unit 46A of the headset-type terminal 314, and sends a notification to the smartphone app of another person nearby when bullying is detected. === Hard Collateral 1-4 === Each of the multiple elements including the collection unit, analysis unit, detection unit, and notification unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit collects audio and video using a microphone or camera of the robot 414. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and analyzes the collected audio and video using a generative AI. The detection unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and detects the occurrence of bullying based on the analysis results. The notification unit is realized, for example, by the control unit 46A of the robot 414, and sends a notification to the smartphone app of another person nearby when bullying is detected.

[0174] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0175] When analyzing audio and video, the analysis unit can optimize the analysis algorithm by referring to the user's past behavioral history. For example, the analysis unit can adjust the current analysis algorithm based on the user's past behavior. This enables more accurate analysis based on the user's behavioral patterns. For example, if a specific behavioral pattern has been detected in the past as a sign of bullying, that pattern can be prioritized in the analysis. Furthermore, the analysis accuracy for specific time periods or situations can be improved based on the user's behavioral history. Furthermore, by referring to the user's behavioral history, the reliability of the analysis results can be improved.

[0176] The notification unit can estimate the user's emotions and adjust the content and format of the notification based on the estimated user's emotions. For example, if the user is nervous, a concise and clear notification can be sent. If the user is relaxed, a notification containing detailed information can be sent. Furthermore, if the user is excited, a visually stimulating notification can be sent. This enables optimal notification according to the user's emotions. For example, in an emergency, a voice notification can be prioritized, and if detailed information is required, a text notification can be sent. The timing of notifications can also be adjusted according to the user's emotions.

[0177] When collecting audio or video, the collection unit can adjust the collection frequency taking into account the remaining battery level of the collection device. For example, if the battery level of the collection device is low, the collection frequency can be reduced to conserve battery power. Alternatively, if the battery level is sufficient, the collection frequency can be increased to collect more detailed data. Furthermore, the collection unit can monitor the remaining battery level of the collection device in real time and automatically adjust the optimal collection frequency. This enables efficient data collection taking into account the remaining battery level. For example, the collection frequency can be halved when the battery level is 50% or less, and maximized when the battery level is 80% or more.

[0178] The analysis unit can prioritize specific patterns and signals when analyzing audio and video. For example, when analyzing audio, it can prioritize the analysis of specific keywords and phrases to collect detailed data. It can also prioritize the analysis of specific actions and facial expressions when analyzing video. Furthermore, when analyzing audio and video, it can prioritize the analysis of specific patterns and signals to quickly produce results. This makes it possible to analyze without missing important data. For example, if the keyword "help" or violent actions are detected, it can prioritize analysis.

[0179] When detecting signs of bullying, the detection unit can improve detection accuracy by integrating multiple data sources. For example, signs of bullying can be detected with high accuracy by integrating audio data and video data. Detection accuracy can also be improved by integrating audio data and text data. Furthermore, signs of bullying can be detected with high accuracy by integrating video data and text data. In this way, by integrating multiple data sources, detection accuracy is improved and more reliable detection is possible. For example, if the keyword "help" is detected in audio data and violent behavior is simultaneously detected in video data, it can be detected with a high probability as a sign of bullying.

[0180] When notifying an occurrence of bullying, the notification unit can save the notification history so that it can be referenced later. For example, the notification history can be saved and a detailed analysis can be performed later. The notification history can also be saved and past response status can be checked. Furthermore, the notification history can be saved and used to help with future improvements. In this way, by saving the notification history, detailed analysis and checking can be performed later. For example, based on the past notification history, it is possible to analyze which responses were effective and use this information in future responses. Furthermore, by referring to the notification history, it is possible to check past response status and respond quickly to similar situations.

[0181] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated user emotions. For example, if the user is nervous, an algorithm that is sensitive to changes in emotions can be used for analysis. On the other hand, if the user is relaxed, an algorithm that is insensitive to changes in emotions can be used for analysis. Furthermore, if the user is excited, an algorithm that is neutral to changes in emotions can be used for analysis. This allows for more appropriate analysis by adjusting the analysis algorithm according to the user's emotions. For example, an algorithm that is sensitive to changes in emotions can be used for a nervous user, and an algorithm that is insensitive to changes in emotions can be used for a relaxed user.

[0182] When collecting audio or video, the collection unit can start collection using a specific keyword or action as a trigger. For example, if a specific keyword (e.g., "help me") is detected, audio collection can be started. Also, if a specific action (e.g., waving one's hand) is detected, video collection can be started. Furthermore, if a combination of a keyword and action (e.g., waving one's hand while shouting "help me") is detected, audio and video collection can be started simultaneously. In this way, by starting collection using a specific keyword or action as a trigger, it is possible to collect important data without missing anything. For example, if the keyword "help me" is detected, audio collection can be started immediately, and if the action of waving one's hand is detected, video collection can be started immediately.

[0183] When notifying an occurrence of bullying, the notification unit can make the content of the notification multilingual. For example, the content of the notification can be translated into multiple languages ​​to accommodate users who speak different languages. The notification language can also be automatically set based on the language setting of the user's device. Furthermore, if a user speaks multiple languages, a language switching function can be provided. This makes it possible to support multiple languages ​​and accommodate users who speak different languages. For example, a notification can be sent in English to an English-speaking user, and in Japanese to a Japanese-speaking user. Furthermore, if a user speaks multiple languages, a language switching function can be provided to send the notification in the appropriate language.

[0184] The collection unit can estimate the user's emotions and determine the priority of the audio and video to be collected based on the estimated user's emotions. For example, if the user is nervous, audio collection can be prioritized to collect detailed conversation content. Also, if the user is relaxed, video collection can be prioritized to collect detailed information about the surrounding situation. Furthermore, if the user is excited, both audio and video can be collected simultaneously to collect comprehensive data. In this way, by determining the priority of the audio and video to be collected according to the user's emotions, important data can be collected preferentially. For example, audio collection can be prioritized for a nervous user, and video collection can be prioritized for a relaxed user.

[0185] The processing flow of the second embodiment will be briefly explained below.

[0186] Step 1: The collection unit collects audio or video. The collection unit collects audio or video, for example, from the microphone or camera of a smartphone or IoT device. The collection unit can also automatically filter surrounding environmental sounds and background noise when collecting audio or video. For example, the collection unit can analyze surrounding environmental sounds in real time and remove background noise when collecting audio or video. Furthermore, the collection unit can start collection when a specific keyword or action is triggered when collecting audio or video. For example, the collection unit can start collecting audio when a specific keyword (e.g., "help") is detected. Step 2: The analysis unit uses the generation AI to analyze the audio and video collected by the collection unit. The analysis unit analyzes, for example, the tone and content of the audio, and the movements and facial expressions of the video. For example, the analysis unit can analyze the tone of the audio to detect changes in emotions. The analysis unit can also analyze the movements of the video to detect specific behavioral patterns. Furthermore, the analysis unit can analyze both the audio and video and output comprehensive analysis results. Step 3: The detection unit detects the occurrence of bullying based on the information analyzed by the analysis unit. The detection unit can detect signs of bullying based on, for example, specific keywords or behavioral patterns. For example, the detection unit can detect the occurrence of bullying when a specific keyword (e.g., "die") is detected. Step 4: The notification unit notifies the occurrence of bullying detected by the detection unit. The notification unit can send a notification to other people nearby using GPS information, for example. For example, the notification unit can immediately notify the smartphone apps of other people near the location where the bullying was detected that bullying has been detected.

[0187] 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.

[0188] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<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.

[0189] 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.

[0190] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0191] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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).

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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 AI 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.

[0205] 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.

[0206] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0207] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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).

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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 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 identification processing unit 290 using these models.

[0218] 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.

[0219] 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.

[0220] 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 AI 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.

[0221] 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.

[0222] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0223] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0224] 7, a 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.

[0225] 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.

[0226] 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.

[0227] 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.

[0228] 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).

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. 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 the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also 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 perform the same process as the identification processing unit 290 using these models.

[0235] 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.

[0236] 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.

[0237] 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 AI 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.

[0238] 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.

[0239] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] 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).

[0244] 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 "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0245] 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."

[0246] 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.

[0247] 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.

[0248] 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.

[0249] 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.

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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.

[0256] 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.

[0257] 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.

[0258] [Explanation of symbols]

[0259] 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 system comprising a collection unit that collects audio or video, an analysis unit that analyzes the audio or video collected by the collection unit, a detection unit that detects the occurrence of bullying based on the information analyzed by the analysis unit, and a notification unit that notifies the occurrence of bullying detected by the detection unit.

2. The system according to claim 1 , wherein the analysis unit analyzes tone or content of voice, and movement or facial expression of video.

3. The notification unit Use GPS information to send notifications to others nearby 2. The system of claim 1.

4. The system according to claim 1 , wherein the collection unit collects audio or video from a microphone or camera of a smartphone or IoT device.

5. The detection unit Detecting signs of bullying 2. The system of claim 1.

6. The notification unit It allows others who receive the notification to rush to the scene or check it from a distance and report it to the police.

2. The system of claim 1.

7. The collecting unit Estimate the user's emotions and adjust the timing of audio and video collection based on the estimated user emotions.

2. The system of claim 1.

8. The collecting unit Automatically filters out ambient and background noise when collecting audio and video 2. The system of claim 1.

Images