system

Abstract

The system according to the embodiment aims to automatically detect and deal with harassment behavior within the metaverse. [Solution] A system according to an embodiment includes a monitoring unit, a response unit, and a learning unit. The monitoring unit monitors chat, image, and audio data at regular intervals. The response unit automatically responds to harassment detected by the monitoring unit. The learning unit learns patterns of harassment based on data from the monitoring unit and the response unit.

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 does not have sufficient mechanisms for automatically detecting and dealing with harassment within the metaverse, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically detect and deal with harassment behavior within the metaverse. [Means for solving the problem]

[0006] The system according to the embodiment includes a monitoring unit, a response unit, and a learning unit. The monitoring unit monitors chat, image, and audio data at regular intervals. The response unit automatically responds to harassment detected by the monitoring unit. The learning unit learns patterns of harassment based on data from the monitoring unit and the response unit. [Effects of the Invention]

[0007] The system according to the embodiment can automatically detect and deal with harassment behavior within the metaverse. [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 metaverse environment monitoring system according to an embodiment of the present invention utilizes a generation AI to automatically detect and respond to harassment, such as slander and impersonation, within the metaverse. This system monitors chat, image, and audio data within the metaverse in real time to detect harassment. The generation AI then automatically responds to the harassment detected. Furthermore, the generation AI learns patterns of harassment to enable more accurate detection and response. This mechanism enables automatic detection and response to harassment within the metaverse, providing a metaverse environment in which users can feel safe. For example, if a defamatory message is sent while a user is chatting within the metaverse, the generation AI can immediately detect the message and send a warning message, thereby preventing harassment. Similarly, the generation AI can detect and respond to inappropriate content and comments in image and audio data. This allows the metaverse environment monitoring system to provide a metaverse environment in which users can feel safe.

[0029] A metaverse environment monitoring system according to an embodiment includes a monitoring unit, a response unit, and a learning unit. The monitoring unit monitors chat, image, and audio data at regular intervals. For example, the monitoring unit monitors chat data in the metaverse in real time to detect slander and impersonation. The monitoring unit can also analyze image data to detect inappropriate content. The monitoring unit can also analyze audio data to detect inappropriate comments. For example, the monitoring unit uses a generation AI to analyze chat data and detect slanderous messages. The monitoring unit can also use a generation AI to analyze image data to detect inappropriate content. The monitoring unit can also use a generation AI to analyze audio data to detect inappropriate comments. The response unit automatically responds to harassment detected by the monitoring unit. For example, the response unit prevents harassment by sending a warning message. The response unit can also suppress harassment by temporarily restricting access. For example, the response unit can immediately send a warning message when it detects an abusive message using the generation AI. The response unit can also immediately send a warning message when it detects inappropriate content using the generation AI. The response unit can also immediately send a warning message when it detects inappropriate remarks using the generation AI. The learning unit learns patterns of harassment based on data from the monitoring unit and the response unit. For example, the learning unit can use the generation AI to learn data on past harassment acts to more accurately detect and respond to them. The learning unit can also use the generation AI to learn patterns of harassment and detect new harassment acts. For example, the learning unit can use the generation AI to learn past abusive messages and detect similar messages. The learning unit can also use the generation AI to learn past inappropriate content and detect similar content. The learning unit can also use the generation AI to learn past inappropriate remarks and detect similar remarks. This allows the metaverse environment monitoring system according to the embodiment to provide a metaverse environment in which users can feel safe.

[0030] The chat analysis unit can analyze chat data. The chat analysis unit analyzes the chat data using, for example, a generation AI. For example, the chat analysis unit can analyze the chat data using natural language processing technology to detect abusive messages. The chat analysis unit can also analyze the chat data using keyword extraction technology to detect inappropriate messages. For example, the chat analysis unit can analyze the chat data using a generation AI to detect messages containing specific keywords. The chat analysis unit can also analyze the chat data using a generation AI to detect messages containing specific phrases. The chat analysis unit can also analyze the chat data using a generation AI to detect messages containing specific contexts. This improves the accuracy of detecting harassment behaviors through analysis of the chat data. Some or all of the above-described processing in the chat analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the chat analysis unit can input chat data to a generation AI, which then analyzes the chat data to detect abusive messages.

[0031] The image analysis unit can analyze image data. The image analysis unit analyzes the image data using, for example, a generation AI. For example, the image analysis unit can analyze the image data using image recognition technology to detect inappropriate content. The image analysis unit can also analyze the image data using feature extraction technology to detect inappropriate images. For example, the image analysis unit can analyze the image data using a generation AI to detect images with specific characteristics. The image analysis unit can also analyze the image data using a generation AI to detect images with specific patterns. Furthermore, the image analysis unit can analyze the image data using a generation AI to detect images with specific colors or shapes. This improves the accuracy of detecting harassment behavior through image data analysis. Some or all of the above-mentioned processing in the image analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the image analysis unit can input image data into a generation AI, which then analyzes the image data and detects inappropriate content.

[0032] The voice analysis unit can analyze voice data. The voice analysis unit analyzes the voice data using, for example, a generation AI. For example, the voice analysis unit can analyze the voice data using voice recognition technology to detect inappropriate remarks. The voice analysis unit can also analyze the voice data using phoneme analysis technology to detect inappropriate voices. For example, the voice analysis unit can analyze the voice data using a generation AI to detect voices containing specific phonemes. The voice analysis unit can also analyze the voice data using a generation AI to detect voices with specific rhythms or tones. Furthermore, the voice analysis unit can analyze the voice data using a generation AI to detect voices containing specific words or phrases. This improves the accuracy of detecting harassment behaviors through analysis of the voice data. Some or all of the above-described processing in the voice analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the voice analysis unit can input voice data to a generation AI, which then analyzes the voice data to detect inappropriate remarks.

[0033] The countermeasure unit may include a warning unit that promptly transmits a warning message. The warning unit, for example, uses a generation AI to immediately transmit a warning message when it detects a harassing act. For example, the warning unit may prevent the harassing act by sending a text message. The warning unit may also suppress the harassing act by sending a pop-up notification. For example, the warning unit may use a generation AI to immediately transmit a text message when it detects a defamatory message. The warning unit may also use a generation AI to immediately transmit a pop-up notification when it detects inappropriate content. Furthermore, the warning unit may use a generation AI to immediately transmit a warning message when it detects inappropriate remarks. In this way, by immediately transmitting a warning message against a harassing act, the act can be prevented before it occurs. Some or all of the above-described processing in the warning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the warning unit may input data indicating the detected harassing act into a generation AI, which may then generate and transmit a warning message.

[0034] The countermeasure unit may include a restriction unit that applies temporary access restrictions. For example, the restriction unit may apply temporary access restrictions when detecting harassment using a generation AI. For example, the restriction unit may suppress harassment by restricting access to a specific user. The restriction unit may also prevent harassment by restricting access to a specific function. For example, the restriction unit may use the generation AI to detect a defamatory message and apply access restrictions to a specific user. The restriction unit may also use the generation AI to detect inappropriate content and apply access restrictions to a specific function. Furthermore, the restriction unit may use the generation AI to detect inappropriate remarks and apply access restrictions to a specific user. In this way, harassment can be suppressed by temporarily restricting access to a user who has committed the harassment. Some or all of the above-described processing in the restriction unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the restriction unit may input data indicating the detection of harassment into the generation AI, which may then generate and apply access restrictions.

[0035] The learning unit may include a pattern learning unit that learns patterns of harassment. The pattern learning unit may use, for example, a generation AI to learn patterns of harassment. For example, the pattern learning unit may use a machine learning algorithm to learn data on past harassment behaviors to perform more accurate detection and response. The pattern learning unit may also use a generation AI to learn new patterns of harassment behaviors to improve detection accuracy. For example, the pattern learning unit may use a generation AI to learn past abusive messages and detect similar messages. The pattern learning unit may also use a generation AI to learn past inappropriate content and detect similar content. Furthermore, the pattern learning unit may use a generation AI to learn past inappropriate comments and detect similar comments. In this way, by learning patterns of harassment, the accuracy of detection and response is improved. Some or all of the above-described processing in the pattern learning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the pattern learning unit can input data on harassment behavior into the generation AI, allowing the generation AI to learn the patterns and improve detection accuracy.

[0036] The monitoring unit can analyze the user's past behavioral history and strengthen monitoring based on specific behavioral patterns. The monitoring unit can, for example, use a generation AI to analyze the user's past behavioral history. For example, the monitoring unit can analyze behavioral history data and strengthen monitoring based on specific behavioral patterns. For example, if a user has a history of being subjected to harassment in the past, the monitoring unit can strengthen monitoring of the user. Furthermore, if a user is more likely to be subjected to harassment during a specific time period, the monitoring unit can strengthen monitoring during that time period. Furthermore, if a user is more likely to be subjected to harassment in a specific location, the monitoring unit can strengthen monitoring at that location. In this way, strengthening monitoring based on the user's past behavioral history enables early detection of harassment. Some or all of the above-described processing in the monitoring unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the monitoring unit can input behavioral history data into a generation AI, which can analyze the behavioral patterns and strengthen monitoring.

[0037] The monitoring unit can adjust the monitoring frequency based on specific time periods or events. The monitoring unit can adjust the monitoring frequency based on specific time periods or events, for example, using a generation AI. For example, the monitoring unit can increase the monitoring frequency during times when harassment increases, such as at night or on weekends. The monitoring unit can also increase the monitoring frequency when a large-scale event is held within the metaverse. Furthermore, the monitoring unit can adjust the monitoring frequency when a specific user logs in. This improves the accuracy of detecting harassment by adjusting the monitoring frequency based on specific time periods or events. Some or all of the above-mentioned processing in the monitoring unit can be performed using, or without, a generation AI. For example, the monitoring unit can input time period and event data into the generation AI, which can then adjust the monitoring frequency.

[0038] The monitoring unit can adjust the monitoring range based on the user's geographical location information. The monitoring unit, for example, uses a generation AI to adjust the monitoring range taking the user's geographical location information into consideration. For example, when the user is in a specific area, the monitoring unit expands the monitoring range of that area. Furthermore, when the user is moving, the monitoring unit can also adjust the monitoring range of the user's destination. Furthermore, when the user is inside a specific building, the monitoring unit can adjust the monitoring range within that building. This enables more appropriate monitoring by adjusting the monitoring range based on the user's geographical location information. Some or all of the above-described processing in the monitoring unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the monitoring unit can input geographical location information to the generation AI, which can then adjust the monitoring range.

[0039] The monitoring unit can analyze the user's social media activity and monitor related behavior. The monitoring unit can analyze the user's social media activity using, for example, a generation AI. For example, the monitoring unit can analyze social media activity data and monitor related behavior. For example, if a user is subjected to harassment on social media, the monitoring unit can monitor the behavior. The monitoring unit can also monitor the behavior of a user who uses a specific keyword on social media. Furthermore, the monitoring unit can monitor the behavior of a user who joins a specific group on social media. This improves the accuracy of detecting harassment by monitoring related behavior based on social media activity. Some or all of the above-described processing in the monitoring unit can be performed using, or without, the generation AI. For example, the monitoring unit can input social media activity data into the generation AI, which can monitor related behavior.

[0040] The countermeasure unit can apply different countermeasures depending on the type of harassment. The countermeasure unit can apply different countermeasures depending on the type of harassment, for example, using a generation AI. For example, the countermeasure unit can send a warning message in the case of slander. The countermeasure unit can also suspend an account in the case of impersonation. Furthermore, the countermeasure unit can restrict the sending of messages in the case of spam. In this way, by applying appropriate countermeasures depending on the type of harassment, the behavior can be effectively suppressed. Some or all of the above-mentioned processing in the countermeasure unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the countermeasure unit can input data on harassment behavior into a generation AI, which can determine the type of behavior and apply appropriate countermeasures.

[0041] The response unit can select an appropriate response method by referring to past response history. The response unit, for example, uses a generation AI to refer to past response history. For example, the response unit preferentially applies response methods that were effective in the past. The response unit can also select an optimal response method for a similar case from past response history. Furthermore, the response unit can analyze past response history and select the most effective response method. In this way, the effectiveness of the response is improved by selecting an optimal response method based on past response history. Some or all of the above-mentioned processing in the response unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the response unit can input past response history data into the generation AI, which can select the optimal response method.

[0042] The response unit can adjust response measures based on the location of the harassment. The response unit adjusts response measures based on the location of the harassment, for example, using a generation AI. For example, the response unit can send an immediate warning message for harassment in a public place. The response unit can also provide individual response measures for harassment in a private place. Furthermore, the response unit can notify the event organizer for harassment during a specific event. This allows for more appropriate response by adjusting response measures based on the location of the harassment. Some or all of the above-described processing in the response unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the response unit can input location data into the generation AI, which can then adjust the response measures.

[0043] The handling unit can select a handling method by referring to relevant legal information. The handling unit can, for example, use a generation AI to refer to relevant legal information. For example, the handling unit can consider legal action if the harassment is legally prohibited. The handling unit can also send a warning message if the harassment is minor. Furthermore, the handling unit can suspend the account if the harassment is serious. In this way, selecting a handling method based on legal information enables legally appropriate handling. Some or all of the above-mentioned processing in the handling unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the handling unit can input legal information data into a generation AI, which can select a handling method.

[0044] The learning unit can improve the learning algorithm by referring to past learning data. The learning unit, for example, uses a generation AI to refer to past learning data. For example, the learning unit selects an optimal learning algorithm based on the past learning data. The learning unit can also analyze past learning data and adjust algorithm parameters. Furthermore, the learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning algorithm is optimized based on the past learning data, thereby improving the accuracy of learning. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input past learning data into the generation AI, which then optimizes the algorithm.

[0045] The learning unit can focus on learning specific patterns of harassment behavior. The learning unit, for example, uses a generation AI to focus on learning specific patterns of harassment behavior. For example, the learning unit can focus on learning patterns of slander. The learning unit can also focus on learning patterns of impersonation behavior. Furthermore, the learning unit can focus on learning patterns of spam behavior. In this way, by focusing on learning specific patterns of harassment behavior, the accuracy of detection and response is improved. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the learning unit can input data of specific harassment behavior into the generation AI, which can learn the pattern.

[0046] The learning unit can weight the learning data based on the time when the harassment occurred. The learning unit, for example, uses a generation AI to weight the learning data based on the time when the harassment occurred. For example, the learning unit weights data from time periods when harassment frequently occurs. The learning unit can also weight data from harassment during specific events. Furthermore, the learning unit can weight data from seasons when harassment increases. In this way, weighting the learning data based on the time when the harassment occurred improves the accuracy of the learning. Some or all of the above-described processing in the learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the learning unit can input occurrence time data into the generation AI, and the generation AI can weight the learning data.

[0047] The learning unit can adjust the learning content by referring to relevant social trends. The learning unit, for example, uses a generation AI to refer to relevant social trends. For example, the learning unit adjusts the learning content based on current social trends. The learning unit can also prioritize learning data related to specific social issues. Furthermore, the learning unit can update the learning content in accordance with changes in social trends. This enables more appropriate learning by adjusting the learning content based on social trends. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input social trend data into the generation AI, which can then adjust the learning content.

[0048] The chat analysis unit can enhance the analysis based on specific keywords or phrases. The chat analysis unit can enhance the analysis based on specific keywords or phrases, for example, using a generation AI. For example, the chat analysis unit can focus its analysis on keywords related to slander. The chat analysis unit can also focus its analysis on phrases related to impersonation. Furthermore, the chat analysis unit can also focus its analysis on keywords related to spam. By enhancing the analysis based on specific keywords or phrases, the accuracy of detecting harassment acts is improved. Some or all of the above-mentioned processing in the chat analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chat analysis unit can input specific keywords or phrases into the generation AI, which can enhance the analysis.

[0049] The chat analysis unit can optimize the analysis algorithm by referring to past chat history. The chat analysis unit, for example, uses a generation AI to refer to past chat history. For example, the chat analysis unit selects an optimal analysis algorithm based on the past chat history. The chat analysis unit can also analyze the past chat history and adjust the parameters of the algorithm. Furthermore, the chat analysis unit can improve the accuracy of the analysis algorithm by referring to the past chat history. In this way, optimizing the analysis algorithm based on the past chat history improves the accuracy of the analysis. Some or all of the above-mentioned processing in the chat analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the chat analysis unit can input past chat history data into the generation AI, which then optimizes the algorithm.

[0050] The chat analysis unit can adjust the analysis range based on the location of the chat. The chat analysis unit adjusts the analysis range based on the location of the chat, for example, using a generation AI. For example, the chat analysis unit performs a broad analysis on chats in public places. The chat analysis unit can also perform a limited analysis on chats in private places. Furthermore, the chat analysis unit can perform an analysis related to the event on chats during a specific event. This allows for more appropriate analysis by adjusting the analysis range based on the location of the chat. Some or all of the above-described processing in the chat analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the chat analysis unit can input location data to the generation AI, which can then adjust the analysis range.

[0051] The chat analysis unit can adjust the analysis content by referring to relevant legal information. The chat analysis unit can, for example, use a generation AI to refer to relevant legal information. For example, if a harassment behavior is legally prohibited, the chat analysis unit can strengthen the analysis related to that behavior. The chat analysis unit can also perform normal analysis for legally acceptable behavior. Furthermore, the chat analysis unit can also perform careful analysis for behavior in a legally gray area. This enables legally appropriate analysis by adjusting the analysis content based on legal information. Some or all of the above-mentioned processing in the chat analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chat analysis unit can input legal information data into the generation AI, which can then adjust the analysis content.

[0052] The image analysis unit can enhance analysis based on a specific visual pattern. The image analysis unit can enhance analysis based on a specific visual pattern, for example, using a generative AI. For example, the image analysis unit can focus its analysis on visual patterns associated with slander. The image analysis unit can also focus its analysis on visual patterns associated with impersonation. Furthermore, the image analysis unit can also focus its analysis on visual patterns associated with spam. By enhancing analysis based on a specific visual pattern, the accuracy of detecting harassment acts is improved. Some or all of the above-described processing in the image analysis unit can be performed using, or without, a generative AI. For example, the image analysis unit can input a specific visual pattern into the generative AI, which can enhance the analysis.

[0053] The image analysis unit can optimize the analysis algorithm by referring to past image data. The image analysis unit, for example, uses a generation AI to refer to past image data. For example, the image analysis unit selects an optimal analysis algorithm based on the past image data. The image analysis unit can also analyze past image data and adjust algorithm parameters. Furthermore, the image analysis unit can also improve the accuracy of the analysis algorithm by referring to past image data. In this way, optimizing the analysis algorithm based on past image data improves the accuracy of the analysis. Some or all of the above-mentioned processing in the image analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the image analysis unit can input past image data into a generation AI, which then optimizes the algorithm.

[0054] The image analysis unit can adjust the analysis range based on the location where the image was taken. The image analysis unit adjusts the analysis range based on the location where the image was taken, for example, using a generation AI. For example, the image analysis unit performs a broad analysis on images taken in public places. The image analysis unit can also perform a limited analysis on images taken in private places. Furthermore, the image analysis unit can perform an analysis related to the event on images taken during a specific event. This allows for more appropriate analysis by adjusting the analysis range based on the location where the image was taken. Some or all of the above-described processing in the image analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the image analysis unit can input shooting location data into the generation AI, which can then adjust the analysis range.

[0055] The image analysis unit can adjust the analysis content by referring to relevant legal information. The image analysis unit can, for example, use a generation AI to refer to relevant legal information. For example, if a harassment act is legally prohibited, the image analysis unit can strengthen the analysis related to that act. The image analysis unit can also perform a normal analysis for legally acceptable acts. Furthermore, the image analysis unit can also perform a careful analysis for acts in a legally gray area. This enables legally appropriate analysis by adjusting the analysis content based on legal information. Some or all of the above-mentioned processing in the image analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the image analysis unit can input legal information data into the generation AI, which can then adjust the analysis content.

[0056] The voice analysis unit can enhance analysis based on specific voice patterns. The voice analysis unit can enhance analysis based on specific voice patterns, for example, using a generation AI. For example, the voice analysis unit can focus its analysis on voice patterns related to slander. The voice analysis unit can also focus its analysis on voice patterns related to impersonation. Furthermore, the voice analysis unit can also focus its analysis on voice patterns related to spam. By enhancing analysis based on specific voice patterns, the accuracy of detecting harassment acts is improved. Some or all of the above-mentioned processing in the voice analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the voice analysis unit can input specific voice patterns into a generation AI, which can enhance the analysis.

[0057] The voice analysis unit can optimize the analysis algorithm by referring to past voice data. The voice analysis unit, for example, uses a generation AI to refer to past voice data. For example, the voice analysis unit selects an optimal analysis algorithm based on the past voice data. The voice analysis unit can also analyze past voice data and adjust algorithm parameters. Furthermore, the voice analysis unit can also improve the accuracy of the analysis algorithm by referring to past voice data. In this way, optimizing the analysis algorithm based on past voice data improves the accuracy of the analysis. Some or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the voice analysis unit can input past voice data into a generation AI, which then optimizes the algorithm.

[0058] The audio analysis unit can adjust the analysis range based on the location where the audio was generated. The audio analysis unit adjusts the analysis range based on the location where the audio was generated, for example, using a generation AI. For example, the audio analysis unit performs a broad analysis on audio generated in a public place. The audio analysis unit can also perform a limited analysis on audio generated in a private place. Furthermore, the audio analysis unit can perform an analysis related to the event on audio generated during a specific event. This allows for more appropriate analysis by adjusting the analysis range based on the location where the audio was generated. Some or all of the above-described processing in the audio analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the audio analysis unit can input location data to the generation AI, which can then adjust the analysis range.

[0059] The voice analysis unit can adjust the analysis content by referring to relevant legal information. The voice analysis unit can, for example, use a generation AI to refer to relevant legal information. For example, if a harassment act is legally prohibited, the voice analysis unit can strengthen the analysis related to that act. The voice analysis unit can also perform normal analysis for legally acceptable acts. Furthermore, the voice analysis unit can also perform careful analysis for acts in a legally gray area. This enables legally appropriate analysis by adjusting the analysis content based on legal information. Some or all of the above-mentioned processing in the voice analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the voice analysis unit can input legal information data into the generation AI, which can then adjust the analysis content.

[0060] When sending a warning message, the warning unit can refer to past warning history and select an appropriate message. The warning unit, for example, uses a generation AI to refer to past warning history. For example, the warning unit prioritizes sending warning messages that have been effective in the past. The warning unit can also select the optimal message for a similar case from the past warning history. Furthermore, the warning unit can analyze past warning history and select the most effective message. This improves the effectiveness of the warning by selecting the optimal message based on the past warning history. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the warning unit can input past warning history data into the generation AI, which can select the optimal message.

[0061] When transmitting a warning message, the warning unit can select an appropriate transmission method by taking into account the user's device information. The warning unit can, for example, use a generation AI to consider the user's device information. For example, if the user is using a smartphone, the warning unit can send the warning message via a push notification. Also, if the user is using a tablet, the warning unit can send the warning message via an in-app notification. Furthermore, if the user is using a PC, the warning unit can send the warning message via a pop-up notification. This improves the effectiveness of the warning by selecting the optimal transmission method based on the user's device information. Some or all of the above-described processing in the warning unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the warning unit can input the user's device information into the generation AI, which can then select the optimal transmission method.

[0062] When restricting access, the restriction unit can select an appropriate restriction method by referring to past restriction history. The restriction unit, for example, uses a generation AI to refer to the past restriction history. For example, the restriction unit preferentially applies restriction methods that were effective in the past. The restriction unit can also select the optimal restriction method for a similar case from the past restriction history. Furthermore, the restriction unit can analyze the past restriction history and select the most effective restriction method. This improves the effectiveness of the restriction by selecting the optimal restriction method based on the past restriction history. Some or all of the above-mentioned processing in the restriction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the restriction unit can input past restriction history data into the generation AI, which then selects the optimal restriction method.

[0063] When restricting access, the restriction unit can select an appropriate restriction method by taking into account the user's behavioral history. The restriction unit can, for example, use a generation AI to consider the user's behavioral history. For example, the restriction unit can apply a high level of restriction if the user has a history of harassing behavior. The restriction unit can also apply a medium level of restriction if the user has a history of minor violations. Furthermore, the restriction unit can also apply a light level of restriction if the user has no history of problematic behavior. This improves the effectiveness of the restriction by selecting an optimal restriction method based on the user's behavioral history. Some or all of the above-mentioned processing in the restriction unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the restriction unit can input the user's behavioral history data into the generation AI, which can then select the optimal restriction method.

[0064] The pattern learning unit can focus on learning specific patterns of harassment. The pattern learning unit, for example, uses a generation AI to focus on learning specific patterns of harassment. For example, the pattern learning unit can focus on learning patterns of slander. The pattern learning unit can also focus on learning patterns of impersonation. Furthermore, the pattern learning unit can also focus on learning patterns of spam. In this way, by focusing on learning specific patterns of harassment, the accuracy of detection and response is improved. Some or all of the above-mentioned processing in the pattern learning unit may be performed using, or without, the generation AI. For example, the pattern learning unit can input data of specific harassment into the generation AI, which then learns the pattern.

[0065] The pattern learning unit can weight the learning data based on the time when the harassment occurred. The pattern learning unit, for example, uses a generation AI to weight the learning data based on the time when the harassment occurred. For example, the pattern learning unit weights data from time periods when harassment frequently occurs. The pattern learning unit can also weight data from harassment during specific events. Furthermore, the pattern learning unit can weight data from seasons when harassment increases. In this way, weighting the learning data based on the time when the harassment occurred improves the accuracy of the learning. Some or all of the above-described processing in the pattern learning unit may be performed using, or without, the generation AI. For example, the pattern learning unit can input occurrence time data into the generation AI, which then weights the learning data.

[0066] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0067] The monitoring unit can analyze a user's behavioral patterns and adjust the intensity of monitoring based on specific behavioral patterns. For example, if a user has a history of committing harassment in the past, the monitoring unit can intensify monitoring of that user. In addition, if a user is more likely to commit harassment during a specific time period, the monitoring unit can also increase the intensity of monitoring during that time period. Furthermore, if a user is more likely to commit harassment in a specific location, the monitoring unit can also intensify monitoring in that location. In this way, adjusting the intensity of monitoring based on past behavioral patterns enables early detection of harassment.

[0068] The image analysis unit can strengthen the analysis based on a specific visual pattern. For example, the image analysis unit can focus on analyzing visual patterns related to slander. The image analysis unit can also focus on analyzing visual patterns related to impersonation. Furthermore, the image analysis unit can also focus on analyzing visual patterns related to spam. In this way, by strengthening the analysis based on a specific visual pattern, the accuracy of detecting harassment acts can be improved.

[0069] The countermeasures unit can apply different countermeasures depending on the type of harassment. For example, the countermeasures unit can send a warning message in the case of slander. The countermeasures unit can also suspend an account in the case of impersonation. Furthermore, the countermeasures unit can restrict the sending of messages in the case of spam. In this way, by applying appropriate countermeasures depending on the type of harassment, it is possible to effectively suppress the behavior.

[0070] The learning unit can improve the learning algorithm by referring to past learning data. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and adjust algorithm parameters. Furthermore, the learning unit can improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning algorithm is optimized based on past learning data, thereby improving the accuracy of learning.

[0071] When restricting access, the restriction unit can select an appropriate restriction method taking into account the user's behavioral history. For example, if the user has a history of harassing behavior in the past, the restriction unit can apply a strong restriction. In addition, if the user has a history of minor violations in the past, the restriction unit can also apply a moderate restriction. Furthermore, if the user has no history of problematic behavior in the past, the restriction unit can also apply a mild restriction. In this way, the effectiveness of the restriction is improved by selecting the optimal restriction method based on the user's behavioral history.

[0072] The processing flow of the first embodiment will be briefly explained below.

[0073] Step 1: The monitoring unit monitors chat, image, and audio data at regular intervals. For example, the monitoring unit monitors chat data in the metaverse in real time to detect abusive comments and impersonation. It can also analyze image data to detect inappropriate content. It can also analyze audio data to detect inappropriate remarks. The monitoring unit uses generative AI to analyze this data and detect abusive messages, inappropriate content, and inappropriate remarks. Step 2: The response unit automatically responds to harassment detected by the monitoring unit. For example, the response unit can prevent harassment by sending a warning message. It can also suppress harassment by temporarily restricting access. Using generative AI, the response unit immediately sends a warning message when it detects abusive messages, inappropriate content, or inappropriate remarks. Step 3: The learning unit learns patterns of harassment based on data from the monitoring and response units. For example, the learning unit uses generative AI to learn data on past harassment behaviors, enabling more accurate detection and response. The learning unit can also use generative AI to learn patterns of harassment behaviors and detect new harassment behaviors. It learns from past abusive messages, inappropriate content, and inappropriate remarks, and detects similar messages, content, and remarks.

[0074] (Example 2) A metaverse environment monitoring system according to an embodiment of the present invention utilizes a generation AI to automatically detect and respond to harassment, such as slander and impersonation, within the metaverse. This system monitors chat, image, and audio data within the metaverse in real time to detect harassment. The generation AI then automatically responds to the harassment detected. Furthermore, the generation AI learns patterns of harassment to enable more accurate detection and response. This mechanism enables automatic detection and response to harassment within the metaverse, providing a metaverse environment in which users can feel safe. For example, if a defamatory message is sent while a user is chatting within the metaverse, the generation AI can immediately detect the message and send a warning message, thereby preventing harassment. Similarly, the generation AI can detect and respond to inappropriate content and comments in image and audio data. This allows the metaverse environment monitoring system to provide a metaverse environment in which users can feel safe.

[0075] A metaverse environment monitoring system according to an embodiment includes a monitoring unit, a response unit, and a learning unit. The monitoring unit monitors chat, image, and audio data at regular intervals. For example, the monitoring unit monitors chat data in the metaverse in real time to detect slander and impersonation. The monitoring unit can also analyze image data to detect inappropriate content. The monitoring unit can also analyze audio data to detect inappropriate comments. For example, the monitoring unit uses a generation AI to analyze chat data and detect slanderous messages. The monitoring unit can also use a generation AI to analyze image data to detect inappropriate content. The monitoring unit can also use a generation AI to analyze audio data to detect inappropriate comments. The response unit automatically responds to harassment detected by the monitoring unit. For example, the response unit prevents harassment by sending a warning message. The response unit can also suppress harassment by temporarily restricting access. For example, the response unit can immediately send a warning message when it detects an abusive message using the generation AI. The response unit can also immediately send a warning message when it detects inappropriate content using the generation AI. The response unit can also immediately send a warning message when it detects inappropriate remarks using the generation AI. The learning unit learns patterns of harassment based on data from the monitoring unit and the response unit. For example, the learning unit can use the generation AI to learn data on past harassment acts to more accurately detect and respond to them. The learning unit can also use the generation AI to learn patterns of harassment and detect new harassment acts. For example, the learning unit can use the generation AI to learn past abusive messages and detect similar messages. The learning unit can also use the generation AI to learn past inappropriate content and detect similar content. The learning unit can also use the generation AI to learn past inappropriate remarks and detect similar remarks. This allows the metaverse environment monitoring system according to the embodiment to provide a metaverse environment in which users can feel safe.

[0076] The chat analysis unit can analyze chat data. The chat analysis unit analyzes the chat data using, for example, a generation AI. For example, the chat analysis unit can analyze the chat data using natural language processing technology to detect abusive messages. The chat analysis unit can also analyze the chat data using keyword extraction technology to detect inappropriate messages. For example, the chat analysis unit can analyze the chat data using a generation AI to detect messages containing specific keywords. The chat analysis unit can also analyze the chat data using a generation AI to detect messages containing specific phrases. The chat analysis unit can also analyze the chat data using a generation AI to detect messages containing specific contexts. This improves the accuracy of detecting harassment behaviors through analysis of the chat data. Some or all of the above-described processing in the chat analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the chat analysis unit can input chat data to a generation AI, which then analyzes the chat data to detect abusive messages.

[0077] The image analysis unit can analyze image data. The image analysis unit analyzes the image data using, for example, a generation AI. For example, the image analysis unit can analyze the image data using image recognition technology to detect inappropriate content. The image analysis unit can also analyze the image data using feature extraction technology to detect inappropriate images. For example, the image analysis unit can analyze the image data using a generation AI to detect images with specific characteristics. The image analysis unit can also analyze the image data using a generation AI to detect images with specific patterns. Furthermore, the image analysis unit can analyze the image data using a generation AI to detect images with specific colors or shapes. This improves the accuracy of detecting harassment behavior through image data analysis. Some or all of the above-mentioned processing in the image analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the image analysis unit can input image data into a generation AI, which then analyzes the image data and detects inappropriate content.

[0078] The voice analysis unit can analyze voice data. The voice analysis unit analyzes the voice data using, for example, a generation AI. For example, the voice analysis unit can analyze the voice data using voice recognition technology to detect inappropriate remarks. The voice analysis unit can also analyze the voice data using phoneme analysis technology to detect inappropriate voices. For example, the voice analysis unit can analyze the voice data using a generation AI to detect voices containing specific phonemes. The voice analysis unit can also analyze the voice data using a generation AI to detect voices with specific rhythms or tones. Furthermore, the voice analysis unit can analyze the voice data using a generation AI to detect voices containing specific words or phrases. This improves the accuracy of detecting harassment behaviors through analysis of the voice data. Some or all of the above-described processing in the voice analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the voice analysis unit can input voice data to a generation AI, which then analyzes the voice data to detect inappropriate remarks.

[0079] The countermeasure unit may include a warning unit that promptly transmits a warning message. The warning unit, for example, uses a generation AI to immediately transmit a warning message when it detects a harassing act. For example, the warning unit may prevent the harassing act by sending a text message. The warning unit may also suppress the harassing act by sending a pop-up notification. For example, the warning unit may use a generation AI to immediately transmit a text message when it detects a defamatory message. The warning unit may also use a generation AI to immediately transmit a pop-up notification when it detects inappropriate content. Furthermore, the warning unit may use a generation AI to immediately transmit a warning message when it detects inappropriate remarks. In this way, by immediately transmitting a warning message against a harassing act, the act can be prevented before it occurs. Some or all of the above-described processing in the warning unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the warning unit may input data indicating the detected harassing act into a generation AI, which may then generate and transmit a warning message.

[0080] The countermeasure unit may include a restriction unit that applies temporary access restrictions. For example, the restriction unit may apply temporary access restrictions when detecting harassment using a generation AI. For example, the restriction unit may suppress harassment by restricting access to a specific user. The restriction unit may also prevent harassment by restricting access to a specific function. For example, the restriction unit may use the generation AI to detect a defamatory message and apply access restrictions to a specific user. The restriction unit may also use the generation AI to detect inappropriate content and apply access restrictions to a specific function. Furthermore, the restriction unit may use the generation AI to detect inappropriate remarks and apply access restrictions to a specific user. In this way, harassment can be suppressed by temporarily restricting access to a user who has committed the harassment. Some or all of the above-described processing in the restriction unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the restriction unit may input data indicating the detection of harassment into the generation AI, which may then generate and apply access restrictions.

[0081] The learning unit may include a pattern learning unit that learns patterns of harassment. The pattern learning unit may use, for example, a generation AI to learn patterns of harassment. For example, the pattern learning unit may use a machine learning algorithm to learn data on past harassment behaviors and perform more accurate detection and response. The pattern learning unit may also use the generation AI to learn new patterns of harassment behaviors and improve detection accuracy. For example, the pattern learning unit may use the generation AI to learn past abusive messages and detect similar messages. The pattern learning unit may also use the generation AI to learn past inappropriate content and detect similar content. Furthermore, the pattern learning unit may use the generation AI to learn past inappropriate comments and detect similar comments. In this way, by learning patterns of harassment, the accuracy of detection and response is improved. Some or all of the above-described processing in the pattern learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the pattern learning unit can input data on harassment behavior into the generation AI, allowing the generation AI to learn the patterns and improve detection accuracy.

[0082] The monitoring unit can estimate the user's emotions and adjust the monitoring frequency based on the estimated user emotions. The monitoring unit, for example, uses a generation AI to estimate the user's emotions. For example, the monitoring unit can estimate the user's emotions using emotion analysis technology and adjust the monitoring frequency based on the estimated emotions. For example, the monitoring unit can increase the monitoring frequency when the user is stressed to detect harassment early. The monitoring unit can also maintain the monitoring frequency at a normal level when the user is relaxed to avoid excessive monitoring. Furthermore, the monitoring unit can adjust the monitoring frequency to a moderate level when the user is excited to maintain an appropriate balance. This enables more appropriate monitoring by adjusting the monitoring frequency according to the user's emotions. Some or all of the above-mentioned processing in the monitoring unit can be performed using, or without, a generation AI. For example, the monitoring unit can input the user's emotion data into a generation AI, which can estimate the emotion and adjust the monitoring frequency.

[0083] The monitoring unit can analyze the user's past behavioral history and strengthen monitoring based on specific behavioral patterns. The monitoring unit can, for example, use a generation AI to analyze the user's past behavioral history. For example, the monitoring unit can analyze behavioral history data and strengthen monitoring based on specific behavioral patterns. For example, if a user has a history of being subjected to harassment in the past, the monitoring unit can strengthen monitoring of the user. Furthermore, if a user is more likely to be subjected to harassment during a specific time period, the monitoring unit can strengthen monitoring during that time period. Furthermore, if a user is more likely to be subjected to harassment in a specific location, the monitoring unit can strengthen monitoring at that location. In this way, strengthening monitoring based on the user's past behavioral history enables early detection of harassment. Some or all of the above-described processing in the monitoring unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the monitoring unit can input behavioral history data into a generation AI, which can analyze the behavioral patterns and strengthen monitoring.

[0084] The monitoring unit can adjust the monitoring frequency based on specific time periods or events. The monitoring unit can adjust the monitoring frequency based on specific time periods or events, for example, using a generation AI. For example, the monitoring unit can increase the monitoring frequency during times when harassment increases, such as at night or on weekends. The monitoring unit can also increase the monitoring frequency when a large-scale event is held within the metaverse. Furthermore, the monitoring unit can adjust the monitoring frequency when a specific user logs in. This improves the accuracy of detecting harassment by adjusting the monitoring frequency based on specific time periods or events. Some or all of the above-mentioned processing in the monitoring unit can be performed using, or without, a generation AI. For example, the monitoring unit can input time period and event data into the generation AI, which can then adjust the monitoring frequency.

[0085] The monitoring unit can estimate the user's emotions and determine the priority of monitoring targets based on the estimated user emotions. The monitoring unit, for example, uses a generation AI to estimate the user's emotions. For example, the monitoring unit can estimate the user's emotions using emotion analysis technology and determine the priority of monitoring targets based on the estimated emotions. For example, the monitoring unit can prioritize monitoring of a user who is feeling anxious. The monitoring unit can also prioritize monitoring of a user who is feeling angry. Furthermore, the monitoring unit can prioritize monitoring of a user who is feeling sad. This enables more effective monitoring by determining the priority of monitoring targets according to the user's emotions. Some or all of the above-described processing in the monitoring unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the monitoring unit can input user emotion data into a generation AI, which can estimate the emotions and determine the priority of monitoring targets.

[0086] The monitoring unit can adjust the monitoring range based on the user's geographical location information. The monitoring unit, for example, uses a generation AI to adjust the monitoring range taking the user's geographical location information into consideration. For example, when the user is in a specific area, the monitoring unit expands the monitoring range of that area. Furthermore, when the user is moving, the monitoring unit can also adjust the monitoring range of the user's destination. Furthermore, when the user is inside a specific building, the monitoring unit can adjust the monitoring range within that building. This enables more appropriate monitoring by adjusting the monitoring range based on the user's geographical location information. Some or all of the above-described processing in the monitoring unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the monitoring unit can input geographical location information to the generation AI, which can then adjust the monitoring range.

[0087] The monitoring unit can analyze the user's social media activity and monitor related behavior. The monitoring unit can analyze the user's social media activity using, for example, a generation AI. For example, the monitoring unit can analyze social media activity data and monitor related behavior. For example, if a user is subjected to harassment on social media, the monitoring unit can monitor the behavior. The monitoring unit can also monitor the behavior of a user who uses a specific keyword on social media. Furthermore, the monitoring unit can monitor the behavior of a user who joins a specific group on social media. This improves the accuracy of detecting harassment by monitoring related behavior based on social media activity. Some or all of the above-described processing in the monitoring unit can be performed using, or without, the generation AI. For example, the monitoring unit can input social media activity data into the generation AI, which can monitor related behavior.

[0088] The coping unit can estimate the user's emotions and select a coping method based on the estimated user's emotions. The coping unit, for example, uses a generation AI to estimate the user's emotions. For example, the coping unit can estimate the user's emotions using emotion analysis technology and select a coping method based on the estimated emotions. For example, the coping unit can provide a calm coping method if the user is feeling angry. The coping unit can also provide a comforting coping method if the user is feeling sad. Furthermore, the coping unit can also provide a reassuring coping method if the user is feeling anxious. This enables more appropriate coping by adjusting the coping method according to the user's emotions. Some or all of the above-described processing in the coping unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the coping unit can input the user's emotion data into the generation AI, which can estimate the emotion and select a coping method.

[0089] The countermeasure unit can apply different countermeasures depending on the type of harassment. The countermeasure unit can apply different countermeasures depending on the type of harassment, for example, using a generation AI. For example, the countermeasure unit can send a warning message in the case of slander. The countermeasure unit can also suspend an account in the case of impersonation. Furthermore, the countermeasure unit can restrict the sending of messages in the case of spam. In this way, by applying appropriate countermeasures depending on the type of harassment, the behavior can be effectively suppressed. Some or all of the above-mentioned processing in the countermeasure unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the countermeasure unit can input data on harassment behavior into a generation AI, which can determine the type of behavior and apply appropriate countermeasures.

[0090] The response unit can select an appropriate response method by referring to past response history. The response unit, for example, uses a generation AI to refer to past response history. For example, the response unit preferentially applies response methods that were effective in the past. The response unit can also select an optimal response method for a similar case from past response history. Furthermore, the response unit can analyze past response history and select the most effective response method. In this way, the effectiveness of the response is improved by selecting an optimal response method based on past response history. Some or all of the above-mentioned processing in the response unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the response unit can input past response history data into the generation AI, which can select the optimal response method.

[0091] The handling unit can estimate the user's emotions and determine the priority of responses based on the estimated user emotions. The handling unit, for example, uses a generation AI to estimate the user's emotions. For example, the handling unit can estimate the user's emotions using emotion analysis technology and determine the priority of responses based on the estimated emotions. For example, the handling unit can prioritize responses when the user is feeling strong anger. The handling unit can also prioritize responses when the user is feeling deep sadness. Furthermore, the handling unit can prioritize responses when the user is feeling strong anxiety. This enables more effective responses by determining the priority of responses according to the user's emotions. Some or all of the above-described processing in the handling unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the handling unit can input the user's emotion data into the generation AI, which can estimate the emotions and determine the priority of responses.

[0092] The response unit can adjust response measures based on the location of the harassment. The response unit adjusts response measures based on the location of the harassment, for example, using a generation AI. For example, the response unit can send an immediate warning message for harassment in a public place. The response unit can also provide individual response measures for harassment in a private place. Furthermore, the response unit can notify the event organizer for harassment during a specific event. This allows for more appropriate response by adjusting response measures based on the location of the harassment. Some or all of the above-described processing in the response unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the response unit can input location data into the generation AI, which can then adjust the response measures.

[0093] The handling unit can select a handling method by referring to relevant legal information. The handling unit can, for example, use a generation AI to refer to relevant legal information. For example, the handling unit can consider legal action if the harassment is legally prohibited. The handling unit can also send a warning message if the harassment is minor. Furthermore, the handling unit can suspend the account if the harassment is serious. In this way, selecting a handling method based on legal information enables legally appropriate handling. Some or all of the above-mentioned processing in the handling unit can be performed, for example, using a generation AI, or can be performed without using a generation AI. For example, the handling unit can input legal information data into a generation AI, which can select a handling method.

[0094] The learning unit can estimate the user's emotions and select training data based on the estimated user emotions. The learning unit, for example, uses a generation AI to estimate the user's emotions. For example, the learning unit can estimate the user's emotions using emotion analysis technology and select training data based on the estimated emotions. For example, if the user is feeling angry, the learning unit can prioritize learning data related to that emotion. Also, if the user is feeling sad, the learning unit can prioritize learning data related to that emotion. Furthermore, if the user is feeling anxious, the learning unit can prioritize learning data related to that emotion. In this way, by selecting training data based on the user's emotions, the accuracy of learning is improved. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the learning unit can input the user's emotion data into the generation AI, which can estimate the emotions and select training data.

[0095] The learning unit can improve the learning algorithm by referring to past learning data. The learning unit, for example, uses a generation AI to refer to past learning data. For example, the learning unit selects an optimal learning algorithm based on the past learning data. The learning unit can also analyze past learning data and adjust algorithm parameters. Furthermore, the learning unit can also improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning algorithm is optimized based on the past learning data, thereby improving the accuracy of learning. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input past learning data into the generation AI, which then optimizes the algorithm.

[0096] The learning unit can focus on learning specific patterns of harassment behavior. The learning unit, for example, uses a generation AI to focus on learning specific patterns of harassment behavior. For example, the learning unit can focus on learning patterns of slander. The learning unit can also focus on learning patterns of impersonation behavior. Furthermore, the learning unit can focus on learning patterns of spam behavior. In this way, by focusing on learning specific patterns of harassment behavior, the accuracy of detection and response is improved. Some or all of the above-mentioned processing in the learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the learning unit can input data of specific harassment behavior into the generation AI, which can learn the pattern.

[0097] The learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The learning unit, for example, uses a generation AI to estimate the user's emotions. For example, the learning unit can estimate the user's emotions using emotion analysis technology and adjust the frequency of learning based on the estimated emotions. For example, the learning unit can increase the frequency of learning if the user frequently feels angry. The learning unit can also increase the frequency of learning if the user frequently feels sad. Furthermore, the learning unit can also increase the frequency of learning if the user frequently feels anxious. This enables more effective learning by adjusting the frequency of learning according to the user's emotions. Some or all of the above-mentioned processing in the learning unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the learning unit can input the user's emotion data into the generation AI, which can estimate the emotions and adjust the frequency of learning.

[0098] The learning unit can weight the learning data based on the time when the harassment occurred. The learning unit, for example, uses a generation AI to weight the learning data based on the time when the harassment occurred. For example, the learning unit weights data from time periods when harassment frequently occurs. The learning unit can also weight data from harassment during specific events. Furthermore, the learning unit can weight data from seasons when harassment increases. In this way, weighting the learning data based on the time when the harassment occurred improves the accuracy of the learning. Some or all of the above-described processing in the learning unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the learning unit can input occurrence time data into the generation AI, and the generation AI can weight the learning data.

[0099] The learning unit can adjust the learning content by referring to relevant social trends. The learning unit, for example, uses a generation AI to refer to relevant social trends. For example, the learning unit adjusts the learning content based on current social trends. The learning unit can also prioritize learning data related to specific social issues. Furthermore, the learning unit can update the learning content in accordance with changes in social trends. This enables more appropriate learning by adjusting the learning content based on social trends. Some or all of the above-mentioned processing in the learning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the learning unit can input social trend data into the generation AI, which can then adjust the learning content.

[0100] The chat analysis unit can estimate a user's emotions and adjust the chat analysis method based on the estimated user's emotions. The chat analysis unit, for example, uses a generation AI to estimate a user's emotions. For example, the chat analysis unit can estimate a user's emotions using emotion analysis technology and adjust the chat analysis method based on the estimated emotions. For example, the chat analysis unit can improve the accuracy of chat analysis when a user is feeling angry. The chat analysis unit can also improve the accuracy of chat analysis when a user is feeling sad. Furthermore, the chat analysis unit can also improve the accuracy of chat analysis when a user is feeling anxious. This allows for more accurate analysis by adjusting the accuracy of chat analysis according to the user's emotions. Some or all of the above-described processing in the chat analysis unit can be performed using, or without, the generation AI. For example, the chat analysis unit can input user emotion data into the generation AI, which can estimate the emotions and adjust the chat analysis method.

[0101] The chat analysis unit can enhance the analysis based on specific keywords or phrases. The chat analysis unit can enhance the analysis based on specific keywords or phrases, for example, using a generation AI. For example, the chat analysis unit can focus its analysis on keywords related to slander. The chat analysis unit can also focus its analysis on phrases related to impersonation. Furthermore, the chat analysis unit can also focus its analysis on keywords related to spam. By enhancing the analysis based on specific keywords or phrases, the accuracy of detecting harassment acts is improved. Some or all of the above-mentioned processing in the chat analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chat analysis unit can input specific keywords or phrases into the generation AI, which can enhance the analysis.

[0102] The chat analysis unit can optimize the analysis algorithm by referring to past chat history. The chat analysis unit, for example, uses a generation AI to refer to past chat history. For example, the chat analysis unit selects an optimal analysis algorithm based on the past chat history. The chat analysis unit can also analyze the past chat history and adjust the parameters of the algorithm. Furthermore, the chat analysis unit can improve the accuracy of the analysis algorithm by referring to the past chat history. In this way, optimizing the analysis algorithm based on the past chat history improves the accuracy of the analysis. Some or all of the above-mentioned processing in the chat analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the chat analysis unit can input past chat history data into the generation AI, which then optimizes the algorithm.

[0103] The chat analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The chat analysis unit can estimate the user's emotions using, for example, a generation AI. For example, the chat analysis unit can estimate the user's emotions using emotion analysis technology and adjust the display method of the analysis results based on the estimated emotions. For example, the chat analysis unit can provide a simple, highly visible display method when the user is nervous. The chat analysis unit can also provide a display method that includes detailed information when the user is relaxed. Furthermore, the chat analysis unit can provide a display method that focuses on the main points when the user is in a hurry. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-mentioned processing in the chat analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chat analysis unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the display method of the analysis results.

[0104] The chat analysis unit can adjust the analysis range based on the location of the chat. The chat analysis unit adjusts the analysis range based on the location of the chat, for example, using a generation AI. For example, the chat analysis unit performs a broad analysis on chats in public places. The chat analysis unit can also perform a limited analysis on chats in private places. Furthermore, the chat analysis unit can perform an analysis related to the event on chats during a specific event. This allows for more appropriate analysis by adjusting the analysis range based on the location of the chat. Some or all of the above-described processing in the chat analysis unit may be performed using, for example, the generation AI, or may be performed without using the generation AI. For example, the chat analysis unit can input location data to the generation AI, which can then adjust the analysis range.

[0105] The chat analysis unit can adjust the analysis content by referring to relevant legal information. The chat analysis unit can, for example, use a generation AI to refer to relevant legal information. For example, if a harassment behavior is legally prohibited, the chat analysis unit can strengthen the analysis related to that behavior. The chat analysis unit can also perform normal analysis for legally acceptable behavior. Furthermore, the chat analysis unit can also perform careful analysis for behavior in a legally gray area. This enables legally appropriate analysis by adjusting the analysis content based on legal information. Some or all of the above-mentioned processing in the chat analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the chat analysis unit can input legal information data into the generation AI, which can then adjust the analysis content.

[0106] The image analysis unit can estimate the user's emotion and adjust the image analysis method based on the estimated user's emotion. The image analysis unit, for example, uses a generation AI to estimate the user's emotion. For example, the image analysis unit can estimate the user's emotion using emotion analysis technology and adjust the image analysis method based on the estimated emotion. For example, the image analysis unit can increase the accuracy of image analysis when the user is feeling angry. The image analysis unit can also increase the accuracy of image analysis when the user is feeling sad. Furthermore, the image analysis unit can also increase the accuracy of image analysis when the user is feeling anxious. This allows for more appropriate analysis by adjusting the accuracy of image analysis according to the user's emotion. Some or all of the above-described processing in the image analysis unit can be performed using, or without, the generation AI. For example, the image analysis unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the image analysis method.

[0107] The image analysis unit can enhance analysis based on a specific visual pattern. The image analysis unit can enhance analysis based on a specific visual pattern, for example, using a generative AI. For example, the image analysis unit can focus its analysis on visual patterns associated with slander. The image analysis unit can also focus its analysis on visual patterns associated with impersonation. Furthermore, the image analysis unit can also focus its analysis on visual patterns associated with spam. By enhancing analysis based on a specific visual pattern, the accuracy of detecting harassment acts is improved. Some or all of the above-described processing in the image analysis unit can be performed using, or without, a generative AI. For example, the image analysis unit can input a specific visual pattern into the generative AI, which can enhance the analysis.

[0108] The image analysis unit can optimize the analysis algorithm by referring to past image data. The image analysis unit, for example, uses a generation AI to refer to past image data. For example, the image analysis unit selects an optimal analysis algorithm based on the past image data. The image analysis unit can also analyze past image data and adjust algorithm parameters. Furthermore, the image analysis unit can also improve the accuracy of the analysis algorithm by referring to past image data. In this way, optimizing the analysis algorithm based on past image data improves the accuracy of the analysis. Some or all of the above-mentioned processing in the image analysis unit may be performed, for example, using a generation AI, or may be performed without using a generation AI. For example, the image analysis unit can input past image data into a generation AI, which then optimizes the algorithm.

[0109] The image analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The image analysis unit, for example, uses a generation AI to estimate the user's emotions. For example, the image analysis unit can estimate the user's emotions using emotion analysis technology and adjust the display method of the analysis results based on the estimated emotions. For example, the image analysis unit can provide a simple, highly visible display method when the user is nervous. The image analysis unit can also provide a display method that includes detailed information when the user is relaxed. Furthermore, the image analysis unit can provide a display method that focuses on the main points when the user is in a hurry. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-mentioned processing in the image analysis unit can be performed using, or without, the generation AI. For example, the image analysis unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the display method of the analysis results.

[0110] The image analysis unit can adjust the analysis range based on the location where the image was taken. The image analysis unit adjusts the analysis range based on the location where the image was taken, for example, using a generation AI. For example, the image analysis unit performs a broad analysis on images taken in public places. The image analysis unit can also perform a limited analysis on images taken in private places. Furthermore, the image analysis unit can perform an analysis related to the event on images taken during a specific event. This allows for more appropriate analysis by adjusting the analysis range based on the location where the image was taken. Some or all of the above-described processing in the image analysis unit may be performed using, for example, a generation AI, or may be performed without using the generation AI. For example, the image analysis unit can input shooting location data into the generation AI, which can then adjust the analysis range.

[0111] The image analysis unit can adjust the analysis content by referring to relevant legal information. The image analysis unit can, for example, use a generation AI to refer to relevant legal information. For example, if a harassment act is legally prohibited, the image analysis unit can strengthen the analysis related to that act. The image analysis unit can also perform a normal analysis for legally acceptable acts. Furthermore, the image analysis unit can also perform a careful analysis for acts in a legally gray area. This enables legally appropriate analysis by adjusting the analysis content based on legal information. Some or all of the above-mentioned processing in the image analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the image analysis unit can input legal information data into the generation AI, which can then adjust the analysis content.

[0112] The voice analysis unit can estimate the user's emotion and adjust the voice analysis method based on the estimated user's emotion. The voice analysis unit, for example, uses a generation AI to estimate the user's emotion. For example, the voice analysis unit can estimate the user's emotion using emotion analysis technology and adjust the voice analysis method based on the estimated emotion. For example, the voice analysis unit can increase the accuracy of voice analysis when the user is feeling angry. The voice analysis unit can also increase the accuracy of voice analysis when the user is feeling sad. Furthermore, the voice analysis unit can also increase the accuracy of voice analysis when the user is feeling anxious. This allows for more appropriate analysis by adjusting the accuracy of voice analysis according to the user's emotion. Some or all of the above-mentioned processing in the voice analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the voice analysis unit can input the user's emotion data into a generation AI, which can estimate the emotion and adjust the voice analysis method.

[0113] The voice analysis unit can enhance analysis based on specific voice patterns. The voice analysis unit can enhance analysis based on specific voice patterns, for example, using a generation AI. For example, the voice analysis unit can focus its analysis on voice patterns related to slander. The voice analysis unit can also focus its analysis on voice patterns related to impersonation. Furthermore, the voice analysis unit can also focus its analysis on voice patterns related to spam. By enhancing analysis based on specific voice patterns, the accuracy of detecting harassment acts is improved. Some or all of the above-mentioned processing in the voice analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the voice analysis unit can input specific voice patterns into a generation AI, which can enhance the analysis.

[0114] The voice analysis unit can optimize the analysis algorithm by referring to past voice data. The voice analysis unit, for example, uses a generation AI to refer to past voice data. For example, the voice analysis unit selects an optimal analysis algorithm based on the past voice data. The voice analysis unit can also analyze past voice data and adjust algorithm parameters. Furthermore, the voice analysis unit can also improve the accuracy of the analysis algorithm by referring to past voice data. In this way, optimizing the analysis algorithm based on past voice data improves the accuracy of the analysis. Some or all of the above-mentioned processing in the voice analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the voice analysis unit can input past voice data into a generation AI, which then optimizes the algorithm.

[0115] The voice analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The voice analysis unit, for example, uses a generation AI to estimate the user's emotions. For example, the voice analysis unit can estimate the user's emotions using emotion analysis technology and adjust the display method of the analysis results based on the estimated emotions. For example, the voice analysis unit can provide a simple, highly visible display method when the user is nervous. The voice analysis unit can also provide a display method that includes detailed information when the user is relaxed. Furthermore, the voice analysis unit can provide a display method that focuses on the main points when the user is in a hurry. This allows for more appropriate display by adjusting the display method of the analysis results according to the user's emotions. Some or all of the above-mentioned processing in the voice analysis unit may be performed using, or without, a generation AI. For example, the voice analysis unit can input the user's emotion data into a generation AI, which can estimate the emotion and adjust the display method of the analysis results.

[0116] The audio analysis unit can adjust the analysis range based on the location where the audio was generated. The audio analysis unit adjusts the analysis range based on the location where the audio was generated, for example, using a generation AI. For example, the audio analysis unit performs a broad analysis on audio generated in a public place. The audio analysis unit can also perform a limited analysis on audio generated in a private place. Furthermore, the audio analysis unit can perform an analysis related to the event on audio generated during a specific event. This allows for more appropriate analysis by adjusting the analysis range based on the location where the audio was generated. Some or all of the above-described processing in the audio analysis unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the audio analysis unit can input location data to the generation AI, which can then adjust the analysis range.

[0117] The voice analysis unit can adjust the analysis content by referring to relevant legal information. The voice analysis unit can, for example, use a generation AI to refer to relevant legal information. For example, if a harassment act is legally prohibited, the voice analysis unit can strengthen the analysis related to that act. The voice analysis unit can also perform normal analysis for legally acceptable acts. Furthermore, the voice analysis unit can also perform careful analysis for acts in a legally gray area. This enables legally appropriate analysis by adjusting the analysis content based on legal information. Some or all of the above-mentioned processing in the voice analysis unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the voice analysis unit can input legal information data into the generation AI, which can then adjust the analysis content.

[0118] The warning unit can estimate the user's emotion and adjust the format of the warning message based on the estimated user's emotion. The warning unit can estimate the user's emotion using, for example, a generation AI. For example, the warning unit can estimate the user's emotion using emotion analysis technology and adjust the format of the warning message based on the estimated emotion. For example, if the user is feeling angry, the warning unit can send a warning message in a calm tone. Also, if the user is feeling sad, the warning unit can send a warning message with comforting content. Furthermore, if the user is feeling anxious, the warning unit can send a warning message with reassuring content. This allows for more appropriate warnings by adjusting the content of the warning message according to the user's emotion. Some or all of the above-mentioned processing in the warning unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the warning unit can input user emotion data into the generation AI, which can estimate the emotion and adjust the format of the warning message.

[0119] When sending a warning message, the warning unit can refer to past warning history and select an appropriate message. The warning unit, for example, uses a generation AI to refer to past warning history. For example, the warning unit prioritizes sending warning messages that have been effective in the past. The warning unit can also select the optimal message for a similar case from the past warning history. Furthermore, the warning unit can analyze past warning history and select the most effective message. This improves the effectiveness of the warning by selecting the optimal message based on the past warning history. Some or all of the above-mentioned processing in the warning unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the warning unit can input past warning history data into the generation AI, which can select the optimal message.

[0120] The warning unit can estimate the user's emotion and adjust the timing of sending the warning message based on the estimated user's emotion. The warning unit can estimate the user's emotion using, for example, a generation AI. For example, the warning unit can estimate the user's emotion using emotion analysis technology and adjust the timing of sending the warning message based on the estimated emotion. For example, the warning unit can immediately send a warning message if the user is feeling angry. The warning unit can also send a warning message at an appropriate time if the user is feeling sad. Furthermore, the warning unit can send a warning message at a time that will reassure the user if the user is feeling anxious. This allows for more appropriate timing of the warning by adjusting the timing of sending the warning message according to the user's emotion. Some or all of the above-described processing in the warning unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the warning unit can input user emotion data into the generation AI, which can estimate the emotion and adjust the timing of sending the warning message.

[0121] When transmitting a warning message, the warning unit can select an appropriate transmission method by taking into account the user's device information. The warning unit can, for example, use a generation AI to consider the user's device information. For example, if the user is using a smartphone, the warning unit can send the warning message via a push notification. Also, if the user is using a tablet, the warning unit can send the warning message via an in-app notification. Furthermore, if the user is using a PC, the warning unit can send the warning message via a pop-up notification. This improves the effectiveness of the warning by selecting the optimal transmission method based on the user's device information. Some or all of the above-described processing in the warning unit can be performed, for example, using the generation AI, or can be performed without using the generation AI. For example, the warning unit can input the user's device information into the generation AI, which can then select the optimal transmission method.

[0122] The restriction unit can estimate the user's emotion and adjust the level of access restriction based on the estimated user's emotion. The restriction unit, for example, uses a generation AI to estimate the user's emotion. For example, the restriction unit can estimate the user's emotion using emotion analysis technology and adjust the level of access restriction based on the estimated emotion. For example, the restriction unit can apply a high level of access restriction when the user is feeling angry. The restriction unit can also apply a medium level of access restriction when the user is feeling sad. Furthermore, the restriction unit can apply a light level of access restriction when the user is feeling anxious. This allows for more appropriate restriction by adjusting the level of access restriction according to the user's emotion. Some or all of the above-described processing in the restriction unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the restriction unit can input the user's emotion data into the generation AI, which can then estimate the emotion and adjust the level of access restriction.

[0123] When restricting access, the restriction unit can select an appropriate restriction method by referring to past restriction history. The restriction unit, for example, uses a generation AI to refer to the past restriction history. For example, the restriction unit preferentially applies restriction methods that were effective in the past. The restriction unit can also select the optimal restriction method for a similar case from the past restriction history. Furthermore, the restriction unit can analyze the past restriction history and select the most effective restriction method. This improves the effectiveness of the restriction by selecting the optimal restriction method based on the past restriction history. Some or all of the above-mentioned processing in the restriction unit may be performed, for example, using the generation AI, or may be performed without using the generation AI. For example, the restriction unit can input past restriction history data into the generation AI, which then selects the optimal restriction method.

[0124] The restriction unit can estimate the user's emotions and adjust the period of access restriction based on the estimated user emotions. The restriction unit, for example, uses a generation AI to estimate the user's emotions. For example, the restriction unit can estimate the user's emotions using emotion analysis technology and adjust the period of access restriction based on the estimated emotions. For example, the restriction unit can apply a long-term access restriction if the user is feeling strong anger. The restriction unit can also apply a medium-term access restriction if the user is feeling deep sadness. Furthermore, the restriction unit can also apply a short-term access restriction if the user is feeling strong anxiety. This enables more appropriate restriction by adjusting the period of access restriction according to the user's emotions. Some or all of the above-mentioned processing in the restriction unit can be performed using, for example, a generation AI, or can be performed without using a generation AI. For example, the restriction unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the period of access restriction.

[0125] When restricting access, the restriction unit can select an appropriate restriction method by taking into account the user's behavioral history. The restriction unit can, for example, use a generation AI to consider the user's behavioral history. For example, the restriction unit can apply a high level of restriction if the user has a history of harassing behavior. The restriction unit can also apply a medium level of restriction if the user has a history of minor violations. Furthermore, the restriction unit can also apply a light level of restriction if the user has no history of problematic behavior. This improves the effectiveness of the restriction by selecting an optimal restriction method based on the user's behavioral history. Some or all of the above-mentioned processing in the restriction unit can be performed using, for example, the generation AI, or can be performed without using the generation AI. For example, the restriction unit can input the user's behavioral history data into the generation AI, which can then select the optimal restriction method.

[0126] The pattern learning unit can estimate a user's emotion and select training data based on the estimated user's emotion. The pattern learning unit, for example, uses a generation AI to estimate the user's emotion. For example, the pattern learning unit can estimate the user's emotion using emotion analysis technology and select training data based on the estimated emotion. For example, if the user is feeling angry, the pattern learning unit can prioritize learning data related to that emotion. Also, if the user is feeling sad, the pattern learning unit can prioritize learning data related to that emotion. Furthermore, if the user is feeling anxious, the pattern learning unit can prioritize learning data related to that emotion. This improves the accuracy of learning by selecting training data based on the user's emotion. Some or all of the above-described processing in the pattern learning unit may be performed using, for example, a generation AI, or may be performed without using a generation AI. For example, the pattern learning unit can input user emotion data into a generation AI, which can estimate the emotion and select training data.

[0127] The pattern learning unit can focus on learning specific patterns of harassment. The pattern learning unit, for example, uses a generation AI to focus on learning specific patterns of harassment. For example, the pattern learning unit can focus on learning patterns of slander. The pattern learning unit can also focus on learning patterns of impersonation. Furthermore, the pattern learning unit can also focus on learning patterns of spam. In this way, by focusing on learning specific patterns of harassment, the accuracy of detection and response is improved. Some or all of the above-mentioned processing in the pattern learning unit may be performed using, or without, the generation AI. For example, the pattern learning unit can input data of specific harassment into the generation AI, which then learns the pattern.

[0128] The pattern learning unit can estimate the user's emotions and adjust the frequency of learning based on the estimated user emotions. The pattern learning unit, for example, uses a generation AI to estimate the user's emotions. For example, the pattern learning unit can estimate the user's emotions using emotion analysis technology and adjust the frequency of learning based on the estimated emotions. For example, the pattern learning unit can increase the frequency of learning if the user frequently feels angry. The pattern learning unit can also increase the frequency of learning if the user frequently feels sad. Furthermore, the pattern learning unit can also increase the frequency of learning if the user frequently feels anxious. This enables more effective learning by adjusting the frequency of learning according to the user's emotions. Some or all of the above-described processing in the pattern learning unit can be performed using, or without, the generation AI. For example, the pattern learning unit can input the user's emotion data into the generation AI, which can estimate the emotion and adjust the frequency of learning.

[0129] The pattern learning unit can weight the learning data based on the time when the harassment occurred. The pattern learning unit, for example, uses a generation AI to weight the learning data based on the time when the harassment occurred. For example, the pattern learning unit weights data from time periods when harassment frequently occurs. The pattern learning unit can also weight data from harassment during specific events. Furthermore, the pattern learning unit can weight data from seasons when harassment increases. In this way, weighting the learning data based on the time when the harassment occurred improves the accuracy of the learning. Some or all of the above-described processing in the pattern learning unit may be performed using, or without, the generation AI. For example, the pattern learning unit can input occurrence time data into the generation AI, which then weights the learning data. === Hard Collateral 1-1 === Each of the multiple elements including the monitoring unit, the response unit, and the learning 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 monitoring unit monitors chat, image, and audio data in the metaverse using the camera 42 and microphone 38B of the smart device 14, and detects harassment behavior using the control unit 46A. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and sends a warning message in response to detected harassment behavior. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns data on past harassment behavior to improve detection accuracy. === Hard Collateral 1-2 === Each of the multiple elements, including the monitoring unit, response unit, and learning 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 monitoring unit monitors chat, image, and audio data in the metaverse using the camera 42 and microphone 238 of the smart glasses 214, and detects harassment behavior using the control unit 46A. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and sends a warning message in response to detected harassment behavior. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns data on past harassment behavior to improve detection accuracy. === Hard Collateral 1-3 === Each of the multiple elements including the monitoring unit, the response unit, and the learning 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 monitoring unit monitors chat, image, and audio data in the metaverse using the camera 42 and microphone 238 of the headset-type terminal 314, and detects harassment behavior using the control unit 46A. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and sends a warning message in response to detected harassment behavior. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns data on past harassment behavior to improve detection accuracy. === Hard Collateral 1-4 === Each of the multiple elements including the monitoring unit, the response unit, and the learning unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the monitoring unit monitors chat, image, and audio data in the metaverse using the camera 42 and microphone 238 of the robot 414, and detects harassment behavior using the control unit 46A. The response unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and sends a warning message in response to detected harassment behavior. The learning unit is realized, for example, by the specific processing unit 290 of the data processing device 12, and learns data on past harassment behavior to improve detection accuracy.

[0130] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0131] The monitoring unit can analyze a user's behavioral patterns and adjust the intensity of monitoring based on specific behavioral patterns. For example, if a user has a history of committing harassment in the past, the monitoring unit can intensify monitoring of that user. In addition, if a user is more likely to commit harassment during a specific time period, the monitoring unit can also increase the intensity of monitoring during that time period. Furthermore, if a user is more likely to commit harassment in a specific location, the monitoring unit can also intensify monitoring in that location. In this way, adjusting the intensity of monitoring based on past behavioral patterns enables early detection of harassment.

[0132] The chat analysis unit can estimate the user's emotions and adjust the accuracy of the chat analysis based on the estimated user's emotions. For example, the chat analysis unit can increase the accuracy of the chat analysis when the user is feeling angry. The chat analysis unit can also increase the accuracy of the chat analysis when the user is feeling sad. Furthermore, the chat analysis unit can also increase the accuracy of the chat analysis when the user is feeling anxious. This allows for more appropriate analysis by adjusting the accuracy of the chat analysis according to the user's emotions.

[0133] The image analysis unit can strengthen the analysis based on a specific visual pattern. For example, the image analysis unit can focus on analyzing visual patterns related to slander. The image analysis unit can also focus on analyzing visual patterns related to impersonation. Furthermore, the image analysis unit can also focus on analyzing visual patterns related to spam. In this way, by strengthening the analysis based on a specific visual pattern, the accuracy of detecting harassment acts can be improved.

[0134] The voice analysis unit can estimate the user's emotions and adjust the voice analysis method based on the estimated user's emotions. For example, the voice analysis unit can increase the accuracy of voice analysis when the user feels angry. The voice analysis unit can also increase the accuracy of voice analysis when the user feels sad. Furthermore, the voice analysis unit can also increase the accuracy of voice analysis when the user feels anxious. This allows for more appropriate analysis by adjusting the accuracy of voice analysis according to the user's emotions.

[0135] The countermeasures unit can apply different countermeasures depending on the type of harassment. For example, the countermeasures unit can send a warning message in the case of slander. The countermeasures unit can also suspend an account in the case of impersonation. Furthermore, the countermeasures unit can restrict the sending of messages in the case of spam. In this way, by applying appropriate countermeasures depending on the type of harassment, it is possible to effectively suppress the behavior.

[0136] The coping unit can estimate the user's emotions and select a coping method based on the estimated user's emotions. For example, if the user is feeling angry, the coping unit can provide a calm coping method. If the user is feeling sad, the coping unit can also provide a comforting coping method. Furthermore, if the user is feeling anxious, the coping unit can also provide a reassuring coping method. This allows for more appropriate coping by adjusting the coping method according to the user's emotions.

[0137] The learning unit can improve the learning algorithm by referring to past learning data. For example, the learning unit selects an optimal learning algorithm based on past learning data. The learning unit can also analyze past learning data and adjust algorithm parameters. Furthermore, the learning unit can improve the accuracy of the learning algorithm by referring to past learning data. In this way, the learning algorithm is optimized based on past learning data, thereby improving the accuracy of learning.

[0138] The learning unit can estimate the user's emotion and select learning data based on the estimated user's emotion. For example, if the user is feeling angry, the learning unit can prioritize learning data related to that emotion. Also, if the user is feeling sad, the learning unit can prioritize learning data related to that emotion. Furthermore, if the user is feeling anxious, the learning unit can prioritize learning data related to that emotion. In this way, by selecting learning data based on the user's emotion, the accuracy of learning is improved.

[0139] The warning unit can estimate the user's emotion and adjust the format of the warning message based on the estimated user's emotion. For example, if the user is feeling angry, the warning unit can send a warning message in a calm tone. If the user is feeling sad, the warning unit can also send a warning message with comforting content. Furthermore, if the user is feeling anxious, the warning unit can also send a warning message with reassuring content. This allows for more appropriate warnings by adjusting the content of the warning message according to the user's emotion.

[0140] When restricting access, the restriction unit can select an appropriate restriction method taking into account the user's behavioral history. For example, if the user has a history of harassing behavior in the past, the restriction unit can apply a strong restriction. In addition, if the user has a history of minor violations in the past, the restriction unit can also apply a moderate restriction. Furthermore, if the user has no history of problematic behavior in the past, the restriction unit can also apply a mild restriction. In this way, the effectiveness of the restriction is improved by selecting the optimal restriction method based on the user's behavioral history.

[0141] The processing flow of the second embodiment will be briefly explained below.

[0142] Step 1: The monitoring unit monitors chat, image, and audio data at regular intervals. For example, the monitoring unit monitors chat data in the metaverse in real time to detect abusive comments and impersonation. It can also analyze image data to detect inappropriate content. It can also analyze audio data to detect inappropriate remarks. The monitoring unit uses generative AI to analyze this data and detect abusive messages, inappropriate content, and inappropriate remarks. Step 2: The response unit automatically responds to harassment detected by the monitoring unit. For example, the response unit can prevent harassment by sending a warning message. It can also suppress harassment by temporarily restricting access. Using generative AI, the response unit immediately sends a warning message when it detects abusive messages, inappropriate content, or inappropriate remarks. Step 3: The learning unit learns patterns of harassment based on data from the monitoring and response units. For example, the learning unit uses generative AI to learn data on past harassment behaviors, enabling more accurate detection and response. The learning unit can also use generative AI to learn patterns of harassment behaviors and detect new harassment behaviors. It learns from past abusive messages, inappropriate content, and inappropriate remarks, and detects similar messages, content, and remarks.

[0143] 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.

[0144] 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 the generative AI include a neural network (NN) and a neural network (NN). 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 (e.g., still image data or video data). 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 one or more data formats of voice data, text data, image data, etc. 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 may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0145] 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.

[0146] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0147] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0161] 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.

[0162] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0163] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0177] 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.

[0178] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0179] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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).

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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 including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). 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 one or more data formats, such as audio data, text data, and image 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 models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0194] 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.

[0195] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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).

[0200] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0201] 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."

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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.

[0211] 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.

[0212] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0213] 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.

[0214] [Explanation of symbols]

[0215] 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 monitoring unit that monitors chat, image, and audio data at regular intervals; a countermeasure unit that automatically counters harassment behavior detected by the monitoring unit; a learning unit that learns patterns of harassment behavior based on data from the monitoring unit and the handling unit; Equipped with A system characterized by:

2. Equipped with a chat analysis unit that analyzes chat data The system of claim 1 .

3. Equipped with an image analysis unit that analyzes image data The system of claim 1 .

4. Equipped with a voice analysis unit that analyzes voice data The system of claim 1 .

5. The countermeasure unit Equipped with a warning unit that quickly sends warning messages The system of claim 1 .

6. The countermeasure unit Equipped with a restriction section that applies temporary access restrictions The system of claim 1 .

7. The learning unit Equipped with a pattern learning unit that learns patterns of harassment behavior The system of claim 1 .

8. The monitoring unit Estimate the user's emotions and adjust the monitoring frequency based on the estimated user emotions. The system of claim 1 .

9. The monitoring unit Analyze users' past behavioral history and strengthen monitoring based on specific behavioral patterns The system of claim 1 .

10. The monitoring unit Adjust monitoring frequency based on specific times or events The system of claim 1 .

Images