System

Abstract

An object of a system according to an embodiment is to automatically detect and deal with a harassment action in a metaverse.SOLUTION: A system includes a chat analysis unit, a harassment detection unit, a warning generation unit, and a notification unit. The chat analysis unit analyzes a chat in the Metaverse using the generated AI. The harassment detection unit detects a harassment action from the chat analyzed by the chat analysis unit. The warning generation unit generates a warning message for the harassment action detected by the harassment detection unit. The notification unit notifies the user of the warning message generated by the warning generation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology does not adequately provide a mechanism 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 in the metaverse. [Means for solving the problem]

[0006] The system according to the embodiment includes a chat analysis unit, a harassment detection unit, a warning generation unit, and a notification unit. The chat analysis unit analyzes chats within the metaverse using a generation AI. The harassment detection unit detects harassment behavior from the chat analyzed by the chat analysis unit. The warning generation unit generates a warning message in response to harassment behavior detected by the harassment detection unit. The notification unit notifies the user of the warning message generated by the warning generation unit. [Effects of the Invention]

[0007] A system according to an embodiment can automatically detect and address 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) The metaverse environment providing system according to an embodiment of the present invention is a system that uses a generation AI to automatically detect and deal with slander and impersonation within the metaverse, allowing users to use the metaverse with peace of mind.

[0029] A metaverse environment providing system according to an embodiment includes a chat analysis unit, an image analysis unit, a voice analysis unit, and a response unit. The chat analysis unit analyzes chats within the metaverse. For example, the generation AI analyzes chat content in real time to detect slander and impersonation. The generation AI can also analyze the context of the chat content to detect offensive words and phrases. The generation AI can also analyze the emotions in the chat content and issue a warning if negative emotions are elevated. The image analysis unit analyzes images shared within the metaverse. For example, the generation AI can use facial recognition technology within images to detect whether a specific user's avatar is being used fraudulently. The generation AI can also analyze the background and object context within an image to detect inappropriate content. The generation AI can also analyze facial expressions and gestures within an image to estimate a user's emotions. The voice analysis unit analyzes voice communication within the metaverse. For example, the generation AI can analyze the tone and pitch of voice data to detect offensive remarks. The generation AI can also analyze background and environmental sounds in the voice data to understand the context of the harassment. The generation AI can also estimate the user's emotions from the voice data and issue a warning if negative emotions increase. The response unit automatically responds to detected harassment. For example, if the generation AI detects slander, it can send a warning message to the user and temporarily restrict access as necessary. If the generation AI detects impersonation, it can temporarily disable the user's avatar and notify the legitimate user. This allows the metaverse environment providing system according to the embodiment to allow users to use the metaverse with peace of mind.

[0030] The chat analysis unit can learn harassment patterns based on the dialogue history between specific users. For example, the generation AI collects past dialogue history between specific users and analyzes the context. For example, it extracts offensive words and phrases from past chat content and learns harassment patterns. The generation AI also analyzes the frequency of use of specific phrases and words based on the dialogue history between users. For example, it detects offensive words frequently used by specific users and learns those patterns. The generation AI also analyzes the dialogue history and tracks changes in emotions between specific users. For example, it learns patterns of increasing negative emotions during dialogue and predicts harassment behavior. This enables highly accurate detection of harassment behavior between specific users.

[0031] The chat analysis unit can predict harassment based on a user's past behavioral history and speech tendencies. In the chat analysis unit, for example, the generation AI analyzes a user's past behavioral history to predict harassment. For example, it analyzes the behavioral patterns of users who have made offensive comments in the past to predict future harassment. The generation AI also analyzes a user's speech tendencies to predict harassment. For example, it detects offensive words and phrases frequently used by a specific user and predicts harassment based on those tendencies. The generation AI also predicts harassment based on an integrated analysis of a user's past behavioral history and speech tendencies. For example, it evaluates the risk of future harassment based on the user's past behavioral history and speech tendencies. This makes it possible to predict future harassment based on the user's past behavioral history and speech tendencies.

[0032] The chat analysis unit can be equipped with a multilingual analysis function that can handle different languages ​​or dialects. For example, the chat analysis unit is equipped with a multilingual analysis function that enables the generation AI to analyze different languages ​​and dialects. For example, it can handle multiple languages ​​such as English, Japanese, and Chinese and analyze chat content. The generation AI can also add a function to analyze different dialects and regional words. For example, it can analyze dialects and slang used in specific regions to detect harassment. The generation AI can also use the multilingual analysis function to analyze chat content in different languages ​​and dialects in real time. For example, it can detect harassment across different languages. This makes it possible to analyze chat content in different languages ​​and dialects and detect harassment.

[0033] The chat analysis unit can analyze a user's input speed or typing pattern to detect abnormal behavior. In the chat analysis unit, for example, the generation AI analyzes a user's input speed to detect abnormal behavior. For example, it issues a warning if there is a sudden change in input speed. The generation AI also analyzes a user's typing pattern to detect abnormal behavior. For example, it issues a warning if a specific pattern is repeated. The generation AI also detects abnormal behavior by comprehensively analyzing chat content, input speed, and typing pattern. For example, it issues a warning if offensive language and an abnormal input pattern are detected simultaneously. In this way, it is possible to analyze a user's input speed and typing pattern to detect abnormal behavior.

[0034] The image analysis unit can use facial recognition technology to detect whether a user's avatar in an image is being used fraudulently. For example, the generation AI uses facial recognition technology in an image to detect whether a specific user's avatar is being used fraudulently. For example, it issues a warning if another user is using the same avatar. The generation AI also uses facial recognition technology to compare the avatar in the image with the user's profile image. For example, if there is a mismatch, it detects fraudulent use. The generation AI also uses facial recognition technology in an image to detect whether a specific user's avatar is being used in multiple locations simultaneously. For example, it issues a warning if the same avatar is being used in different locations. This allows for highly accurate detection of whether a user's avatar is being used fraudulently.

[0035] The image analysis unit can detect inappropriate content with high accuracy based on the context of the background or object. For example, the image analysis unit's generation AI takes into account the context of the background and object when analyzing an image. For example, it issues a warning if inappropriate content is included in the background. The generation AI also analyzes objects within an image and detects inappropriate content based on that context. For example, it detects offensive symbols and gestures. The generation AI also comprehensively analyzes the context of the background and object to detect inappropriate content with high accuracy. For example, it issues a warning if the combination of the background and object is inappropriate. This allows for high-accuracy detection of inappropriate content by taking the context of the background and object into account.

[0036] The image analysis unit also includes 3D models and animations in its analysis when analyzing images, enabling it to cover a wider range of metaverse content. For example, the image analysis unit includes 3D models in its analysis when the generation AI analyzes images. For example, it detects unauthorized use of 3D avatars. The generation AI also includes animations in its analysis and analyzes dynamic content. For example, it detects inappropriate actions within animations. The generation AI also analyzes 3D models and animations in an integrated manner, enabling it to cover a wider range of metaverse content. For example, it issues a warning if the combination of a 3D avatar and animation is inappropriate. This allows it to cover a wider range of metaverse content by including 3D models and animations in its analysis.

[0037] The image analysis unit can automatically generate appropriate feedback and improvement suggestions for users based on the image analysis results. For example, the generation AI in the image analysis unit automatically generates appropriate feedback for users based on the image analysis results. For example, it makes improvement suggestions when inappropriate content is detected. The generation AI also makes specific improvement suggestions to users based on the image analysis results. For example, it makes suggestions to remove offensive symbols. The generation AI also provides integrated feedback and improvement suggestions to users based on the image analysis results. For example, it makes specific suggestions on how to correct inappropriate content. This makes it possible to automatically generate appropriate feedback and improvement suggestions for users based on the image analysis results.

[0038] The voice analysis unit can detect aggressive remarks by analyzing the tone and pitch of the voice data. In the voice analysis unit, for example, the generation AI analyzes the tone of the voice data to detect aggressive remarks. For example, it issues a warning if the tone becomes higher. The generation AI also analyzes the pitch of the voice data to detect aggressive remarks. For example, it issues a warning if the pitch changes suddenly. The generation AI also performs an integrated analysis of tone and pitch to detect aggressive remarks with high accuracy. For example, it issues a warning if the tone and pitch change simultaneously. In this way, by analyzing the tone and pitch of the voice data, aggressive remarks can be detected with high accuracy.

[0039] The audio analysis unit can understand the context of harassment based on background or environmental sounds in the audio analysis. For example, the generation AI takes background sounds into account in the audio analysis to understand the context of harassment. For example, if the background sounds are noisy, it evaluates the likelihood of offensive remarks. The generation AI also analyzes environmental sounds to understand the context of harassment. For example, it evaluates the risk of harassment when specific environmental sounds are included. The generation AI also analyzes background sounds and environmental sounds in an integrated manner to understand the context of harassment with high accuracy. For example, it issues a warning if the background sounds and environmental sounds show a specific pattern. In this way, by taking background sounds and environmental sounds into account, the context of harassment can be understood with high accuracy.

[0040] The speech analysis unit can add a multilingual speech analysis function that can handle different languages ​​and accents during speech analysis. The speech analysis unit, for example, is equipped with a multilingual speech analysis function that enables the generation AI to analyze different languages ​​and accents. For example, it can handle multiple languages ​​such as English, Japanese, and Chinese and analyze speech content. The generation AI also adds a function for analyzing different accents and regional pronunciation. For example, it can analyze accents and pronunciations used in specific regions to detect harassment. The generation AI also uses the multilingual speech analysis function to analyze speech content in different languages ​​and accents in real time. For example, it can detect harassment across different languages. This makes it possible to analyze speech content in different languages ​​and accents and detect harassment.

[0041] The voice analysis unit not only analyzes voice data, but also analyzes the user's speech rate or rhythm to detect abnormal behavior. In the voice analysis unit, for example, the generation AI analyzes the user's speech rate to detect abnormal behavior. For example, it issues a warning if the speech rate changes suddenly. The generation AI also analyzes the user's speech rhythm to detect abnormal behavior. For example, it issues a warning if a specific rhythm is repeated. The generation AI also detects abnormal behavior by comprehensively analyzing the voice content, speech rate, and rhythm. For example, it issues a warning if aggressive language and an abnormal speech pattern are detected simultaneously. This makes it possible to analyze the user's speech rate and rhythm and detect abnormal behavior.

[0042] The response unit can automatically select and execute a response method according to the type and severity of the harassment. For example, the response unit analyzes the type and severity of the harassment detected by the generation AI and automatically selects an appropriate response method. For example, it sends a warning message for mild harassment and temporarily restricts access in serious cases. The generation AI also executes different response methods depending on the type of harassment. For example, it sends a warning message for slander and disables the avatar for impersonation. The generation AI also evaluates the severity of the harassment and selects an appropriate response method. For example, it immediately restricts access for serious harassment and sends a support message to the victim. This makes it possible to automatically select and execute a response method according to the type and severity of harassment.

[0043] When harassment is detected, the countermeasure unit can send an educational message to the user in question to encourage behavioral improvement. For example, when the generation AI detects harassment, the countermeasure unit sends an educational message to the user in question. For example, it sends a message urging the user to be careful not to use offensive language. Furthermore, when harassment is detected, the generation AI sends a message urging the user in question to improve their behavior. For example, it sends a message urging the user to treat other users with respect. Furthermore, when harassment is detected, the generation AI makes specific suggestions to the user to improve their behavior. For example, it suggests using positive language instead of using offensive language. In this way, when harassment is detected, an educational message can be sent to the user in question to encourage behavioral improvement.

[0044] The response unit can provide a customized response method based on the behavioral history of the user in question. For example, the generation AI analyzes the behavioral history of the user in question and provides a customized response method. For example, a stricter response method can be applied to a user who has engaged in similar harassing behavior in the past. The generation AI also provides an individually customized response method based on the behavioral history of the user in question. For example, a message encouraging behavioral improvement can be sent to a user with a specific behavioral pattern. The generation AI also takes into account the behavioral history of the user in question and selects the optimal response method. For example, an appropriate warning message or access restriction can be displayed based on the past behavioral history. This makes it possible to provide a customized response method based on the behavioral history of the user in question.

[0045] The response unit notifies other users when harassment is detected, thereby facilitating a community-wide response. For example, when the generation AI detects harassment, the response unit notifies other users. For example, it sends a warning message to the entire community to warn them. Furthermore, when harassment is detected, the generation AI suggests ways to deal with it to other users. For example, it suggests specific actions to take to support the victim. Furthermore, when harassment is detected, the generation AI sends a message to promote a community-wide response. For example, it provides instructions on how to report harassment and how to provide support. In this way, when harassment is detected, other users are notified, thereby facilitating a community-wide response.

[0046] The generative AI can analyze overall communication patterns within the metaverse and predict potential harassment risks. For example, the generative AI can analyze overall communication patterns within the metaverse and predict potential harassment risks. For example, it can analyze the frequency of use of offensive language between specific users. The generative AI can also evaluate harassment risks based on communication patterns within the metaverse. For example, it can predict the risk of harassment occurring at specific times or locations. The generative AI can also analyze overall communication patterns and detect potential harassment risks early. For example, it can issue a warning if a specific pattern is repeated. This makes it possible to analyze overall communication patterns within the metaverse and predict potential harassment risks.

[0047] The generation AI can monitor user behavior in the metaverse in real time and take immediate action if abnormal behavior occurs. The generation AI can, for example, monitor user behavior in the metaverse in real time and take immediate action if abnormal behavior occurs. For example, it can issue a warning if aggressive behavior is detected. The generation AI can also analyze user behavior in real time and take appropriate action if abnormal behavior occurs. For example, it can temporarily restrict access if abnormal behavior is detected. The generation AI can also continuously monitor user behavior in the metaverse and take immediate action if abnormal behavior occurs. For example, it can send a warning message to the user in question if abnormal behavior is detected. This allows the generation AI to monitor user behavior in real time and take immediate action if abnormal behavior occurs.

[0048] The generative AI can periodically provide positive messages and content to users in order to provide a safe environment within the metaverse. For example, the generative AI can periodically send positive messages to users in order to provide a safe environment within the metaverse. For example, it can periodically send messages of encouragement or words of gratitude. The generative AI can also provide positive content to users. For example, it can periodically share positive news or success stories. The generative AI can also periodically provide positive messages and content to users in order to maintain a safe environment within the metaverse. For example, sending positive messages improves the user's emotional state. This allows the user to regularly receive positive messages and content, thereby providing an environment in which they can feel safe.

[0049] The generative AI can collect feedback from users to evaluate the safe environment in the metaverse and improve the environment based on that feedback. For example, the generative AI collects feedback from users to evaluate the safe environment in the metaverse. For example, it may collect feedback using a survey or comment function. The generative AI also analyzes the feedback from users and improves the environment in the metaverse. For example, it may make specific improvement suggestions based on the feedback. The generative AI also continuously improves the safe environment in the metaverse based on user feedback. For example, it may analyze feedback in real time and respond immediately. This allows the safe environment in the metaverse to be continuously improved based on user feedback.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The metaverse environment provision system can also provide customized measures based on a user's behavioral history. For example, it can apply more severe measures to users who have engaged in similar harassing behavior in the past. It can also send messages encouraging users with specific behavioral patterns to improve their behavior. This allows it to provide individually customized measures based on a user's behavioral history.

[0052] The metaverse environment provision system can also add a multilingual analysis function that can handle different languages ​​and dialects. For example, it can analyze chat content in multiple languages, such as English, Japanese, and Chinese. It can also analyze dialects and slang used in specific regions to detect harassment. This makes it possible to analyze chat content in different languages ​​and dialects and detect harassment.

[0053] The metaverse environment provision system can also analyze a user's input speed and typing patterns to detect abnormal behavior. For example, it can issue a warning if there is a sudden change in input speed. It can also issue a warning if a specific pattern is repeated. This allows the system to analyze a user's input speed and typing patterns and detect abnormal behavior.

[0054] The Metaverse Environment Provision System can also analyze 3D models and animations during image analysis, enabling it to cover a wider range of Metaverse content. For example, it can detect unauthorized use of 3D avatars. It can also detect inappropriate behavior within animations. By including 3D models and animations in its analysis, it can cover a wider range of Metaverse content.

[0055] The metaverse environment provision system not only analyzes voice data, but also analyzes the user's speech rate and rhythm to detect abnormal behavior. For example, it can issue a warning if there is a sudden change in speech rate. It can also issue a warning if a specific rhythm is repeated. This allows the system to analyze the user's speech rate and rhythm to detect abnormal behavior.

[0056] Furthermore, if harassment is detected, the metaverse environment providing system can send an educational message to the user in question to encourage behavioral improvement. For example, a message can be sent to warn the user not to use offensive language. It can also send a message encouraging the user to treat other users with respect. In this way, if harassment is detected, an educational message can be sent to the user in question to encourage behavioral improvement.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The chat analysis unit analyzes chats within the metaverse. The generation AI analyzes the chat content in real time to detect slander and impersonation. The generation AI can also analyze the context of the chat content to detect offensive words and phrases. Furthermore, the generation AI can analyze the sentiment of the chat content and issue a warning if negative sentiment increases. Step 2: The harassment detection unit detects harassing behavior from the chat analyzed by the chat analysis unit. The generation AI detects abusive and offensive words and phrases and identifies harassing behavior. Step 3: The warning generation unit generates a warning message for the harassment detected by the harassment detection unit. The generation AI creates an appropriate warning message based on the detected harassment. Step 4: The notification unit notifies the user of the warning message generated by the warning generation unit. The generation AI sends the warning message to the user in real time and temporarily restricts access if necessary.

[0059] (Example 2) The metaverse environment providing system according to an embodiment of the present invention is a system that uses a generation AI to automatically detect and deal with slander and impersonation within the metaverse, allowing users to use the metaverse with peace of mind.

[0060] A metaverse environment providing system according to an embodiment includes a chat analysis unit, an image analysis unit, a voice analysis unit, and a response unit. The chat analysis unit analyzes chats within the metaverse. For example, the generation AI analyzes chat content in real time to detect slander and impersonation. The generation AI can also analyze the context of the chat content to detect offensive words and phrases. The generation AI can also analyze the emotions in the chat content and issue a warning if negative emotions are elevated. The image analysis unit analyzes images shared within the metaverse. For example, the generation AI can use facial recognition technology within images to detect whether a specific user's avatar is being used fraudulently. The generation AI can also analyze the background and object context within an image to detect inappropriate content. The generation AI can also analyze facial expressions and gestures within an image to estimate a user's emotions. The voice analysis unit analyzes voice communication within the metaverse. For example, the generation AI can analyze the tone and pitch of voice data to detect offensive remarks. The generation AI can also analyze background and environmental sounds in the voice data to understand the context of the harassment. The generation AI can also estimate the user's emotions from the voice data and issue a warning if negative emotions increase. The response unit automatically responds to detected harassment. For example, if the generation AI detects slander, it can send a warning message to the user and temporarily restrict access as necessary. If the generation AI detects impersonation, it can temporarily disable the user's avatar and notify the legitimate user. This allows the metaverse environment providing system according to the embodiment to allow users to use the metaverse with peace of mind.

[0061] The chat analysis unit can learn harassment patterns based on the dialogue history between specific users. For example, the generation AI collects past dialogue history between specific users and analyzes the context. For example, it extracts offensive words and phrases from past chat content and learns harassment patterns. The generation AI also analyzes the frequency of use of specific phrases and words based on the dialogue history between users. For example, it detects offensive words frequently used by specific users and learns those patterns. The generation AI also analyzes the dialogue history and tracks changes in emotions between specific users. For example, it learns patterns of increasing negative emotions during dialogue and predicts harassment behavior. This enables highly accurate detection of harassment behavior between specific users.

[0062] The chat analysis unit can predict harassment based on a user's past behavioral history and speech tendencies. In the chat analysis unit, for example, the generation AI analyzes a user's past behavioral history to predict harassment. For example, it analyzes the behavioral patterns of users who have made offensive comments in the past to predict future harassment. The generation AI also analyzes a user's speech tendencies to predict harassment. For example, it detects offensive words and phrases frequently used by a specific user and predicts harassment based on those tendencies. The generation AI also predicts harassment based on an integrated analysis of a user's past behavioral history and speech tendencies. For example, it evaluates the risk of future harassment based on the user's past behavioral history and speech tendencies. This makes it possible to predict future harassment based on the user's past behavioral history and speech tendencies.

[0063] The chat analysis unit uses an emotion estimation function to estimate a user's emotions from the chat content and can issue a warning if negative emotions increase. In the chat analysis unit, for example, the generation AI analyzes the chat content and estimates the user's emotions. For example, it detects offensive words and phrases and issues a warning if negative emotions increase. The generation AI also analyzes the context of the chat content and tracks changes in the user's emotions. For example, it detects patterns of increasing negative emotions in the conversation and issues a warning. The generation AI also uses the emotion estimation function to analyze the user's emotions from the chat content in real time. For example, it immediately issues a warning if negative emotions increase. This makes it possible to analyze a user's emotions in real time and immediately issue a warning if negative emotions increase.

[0064] The chat analysis unit can be equipped with a multilingual analysis function that can handle different languages ​​or dialects. For example, the chat analysis unit is equipped with a multilingual analysis function that enables the generation AI to analyze different languages ​​and dialects. For example, it can handle multiple languages ​​such as English, Japanese, and Chinese and analyze chat content. The generation AI can also add a function to analyze different dialects and regional words. For example, it can analyze dialects and slang used in specific regions to detect harassment. The generation AI can also use the multilingual analysis function to analyze chat content in different languages ​​and dialects in real time. For example, it can detect harassment across different languages. This makes it possible to analyze chat content in different languages ​​and dialects and detect harassment.

[0065] The chat analysis unit can analyze a user's input speed or typing pattern to detect abnormal behavior. In the chat analysis unit, for example, the generation AI analyzes a user's input speed to detect abnormal behavior. For example, it issues a warning if there is a sudden change in input speed. The generation AI also analyzes a user's typing pattern to detect abnormal behavior. For example, it issues a warning if a specific pattern is repeated. The generation AI also detects abnormal behavior by comprehensively analyzing chat content, input speed, and typing pattern. For example, it issues a warning if offensive language and an abnormal input pattern are detected simultaneously. In this way, it is possible to analyze a user's input speed and typing pattern to detect abnormal behavior.

[0066] The chat analysis unit uses the emotion estimation function to monitor other users' emotional reactions to chat content in real time, facilitating the early detection of harassment behavior. In the chat analysis unit, for example, the generation AI monitors other users' emotional reactions to chat content in real time. For example, it issues a warning if there are many negative emotional reactions. The generation AI also uses the emotion estimation function to analyze other users' emotional scores for the chat content. For example, it detects harassment behavior if the emotional score is low. The generation AI also evaluates the harassment risk of the chat content based on the emotional reactions of other users. For example, it takes early action if there are many negative emotional reactions. This allows for early detection of harassment behavior based on the emotional reactions of other users.

[0067] The image analysis unit can use facial recognition technology to detect whether a user's avatar in an image is being used fraudulently. For example, the generation AI uses facial recognition technology in an image to detect whether a specific user's avatar is being used fraudulently. For example, it issues a warning if another user is using the same avatar. The generation AI also uses facial recognition technology to compare the avatar in the image with the user's profile image. For example, if there is a mismatch, it detects fraudulent use. The generation AI also uses facial recognition technology in an image to detect whether a specific user's avatar is being used in multiple locations simultaneously. For example, it issues a warning if the same avatar is being used in different locations. This allows for highly accurate detection of whether a user's avatar is being used fraudulently.

[0068] The image analysis unit can detect inappropriate content with high accuracy based on the context of the background or object. For example, the image analysis unit's generation AI takes into account the context of the background and object when analyzing an image. For example, it issues a warning if inappropriate content is included in the background. The generation AI also analyzes objects within an image and detects inappropriate content based on that context. For example, it detects offensive symbols and gestures. The generation AI also comprehensively analyzes the context of the background and object to detect inappropriate content with high accuracy. For example, it issues a warning if the combination of the background and object is inappropriate. This allows for high-accuracy detection of inappropriate content by taking the context of the background and object into account.

[0069] The image analysis unit uses the emotion estimation function to estimate the user's emotion from facial expressions and gestures in an image, and can issue a warning if a negative emotion is expressed. In the image analysis unit, for example, the generation AI analyzes facial expressions in an image to estimate the user's emotion. For example, it issues a warning if an angry or sad expression is detected. The generation AI also analyzes gestures in an image to estimate the user's emotion. For example, it issues a warning if an aggressive gesture is detected. The generation AI also analyzes facial expressions and gestures in an integrated manner to estimate the user's emotion with high accuracy. For example, it issues a warning if a negative emotion is expressed. This makes it possible to estimate the user's emotion from facial expressions and gestures in an image, and issue a warning if a negative emotion is expressed.

[0070] The image analysis unit also includes 3D models and animations in its analysis when analyzing images, enabling it to cover a wider range of metaverse content. For example, the image analysis unit includes 3D models in its analysis when the generation AI analyzes images. For example, it detects unauthorized use of 3D avatars. The generation AI also includes animations in its analysis and analyzes dynamic content. For example, it detects inappropriate actions within animations. The generation AI also analyzes 3D models and animations in an integrated manner, enabling it to cover a wider range of metaverse content. For example, it issues a warning if the combination of a 3D avatar and animation is inappropriate. This allows it to cover a wider range of metaverse content by including 3D models and animations in its analysis.

[0071] The image analysis unit can automatically generate appropriate feedback and improvement suggestions for users based on the image analysis results. For example, the generation AI in the image analysis unit automatically generates appropriate feedback for users based on the image analysis results. For example, it makes improvement suggestions when inappropriate content is detected. The generation AI also makes specific improvement suggestions to users based on the image analysis results. For example, it makes suggestions to remove offensive symbols. The generation AI also provides integrated feedback and improvement suggestions to users based on the image analysis results. For example, it makes specific suggestions on how to correct inappropriate content. This makes it possible to automatically generate appropriate feedback and improvement suggestions for users based on the image analysis results.

[0072] The image analysis unit uses the emotion estimation function to monitor other users' emotional reactions to images in real time, facilitating the early detection of inappropriate images. In the image analysis unit, for example, the generation AI monitors other users' emotional reactions to images in real time. For example, it issues a warning if there are many negative emotional reactions. The generation AI also uses the emotion estimation function to analyze other users' emotional scores for an image. For example, it detects an inappropriate image if the emotional score is low. The generation AI also quickly detects inappropriate content in an image based on the emotional reactions of other users. For example, it takes early action if there are many negative emotional reactions. This makes it possible to quickly detect inappropriate images based on the emotional reactions of other users.

[0073] The voice analysis unit can detect aggressive remarks by analyzing the tone and pitch of the voice data. In the voice analysis unit, for example, the generation AI analyzes the tone of the voice data to detect aggressive remarks. For example, it issues a warning if the tone becomes higher. The generation AI also analyzes the pitch of the voice data to detect aggressive remarks. For example, it issues a warning if the pitch changes suddenly. The generation AI also performs an integrated analysis of tone and pitch to detect aggressive remarks with high accuracy. For example, it issues a warning if the tone and pitch change simultaneously. In this way, by analyzing the tone and pitch of the voice data, aggressive remarks can be detected with high accuracy.

[0074] The audio analysis unit can understand the context of harassment based on background or environmental sounds in the audio analysis. For example, the generation AI takes background sounds into account in the audio analysis to understand the context of harassment. For example, if the background sounds are noisy, it evaluates the likelihood of offensive remarks. The generation AI also analyzes environmental sounds to understand the context of harassment. For example, it evaluates the risk of harassment when specific environmental sounds are included. The generation AI also analyzes background sounds and environmental sounds in an integrated manner to understand the context of harassment with high accuracy. For example, it issues a warning if the background sounds and environmental sounds show a specific pattern. In this way, by taking background sounds and environmental sounds into account, the context of harassment can be understood with high accuracy.

[0075] The voice analysis unit uses an emotion estimation function to estimate the user's emotions from the voice and can issue a warning if negative emotions increase. In the voice analysis unit, for example, the generation AI analyzes voice data and estimates the user's emotions. For example, it detects emotions such as anger or sadness from the tone and pitch of the voice and issues a warning if negative emotions increase. The generation AI also analyzes the context of the voice and tracks changes in the user's emotions. For example, it detects patterns of increasing negative emotions in the conversation and issues a warning. The generation AI also uses the emotion estimation function to analyze the user's emotions from the voice in real time. For example, it immediately issues a warning if negative emotions increase. This makes it possible to estimate the user's emotions from the voice and issue a warning if negative emotions increase.

[0076] The speech analysis unit can add a multilingual speech analysis function that can handle different languages ​​and accents during speech analysis. The speech analysis unit, for example, is equipped with a multilingual speech analysis function that enables the generation AI to analyze different languages ​​and accents. For example, it can handle multiple languages ​​such as English, Japanese, and Chinese and analyze speech content. The generation AI also adds a function for analyzing different accents and regional pronunciation. For example, it can analyze accents and pronunciations used in specific regions to detect harassment. The generation AI also uses the multilingual speech analysis function to analyze speech content in different languages ​​and accents in real time. For example, it can detect harassment across different languages. This makes it possible to analyze speech content in different languages ​​and accents and detect harassment.

[0077] The voice analysis unit not only analyzes voice data, but also analyzes the user's speech rate or rhythm to detect abnormal behavior. In the voice analysis unit, for example, the generation AI analyzes the user's speech rate to detect abnormal behavior. For example, it issues a warning if the speech rate changes suddenly. The generation AI also analyzes the user's speech rhythm to detect abnormal behavior. For example, it issues a warning if a specific rhythm is repeated. The generation AI also detects abnormal behavior by comprehensively analyzing the voice content, speech rate, and rhythm. For example, it issues a warning if aggressive language and an abnormal speech pattern are detected simultaneously. This makes it possible to analyze the user's speech rate and rhythm and detect abnormal behavior.

[0078] The voice analysis unit uses the emotion estimation function to monitor other users' emotional reactions to voice in real time, facilitating the early detection of harassment behavior. In the voice analysis unit, for example, the generation AI monitors other users' emotional reactions to voice in real time. For example, it issues a warning if there are many negative emotional reactions. The generation AI also uses the emotion estimation function to analyze other users' emotional scores to the voice. For example, it detects harassment behavior if the emotional score is low. The generation AI also evaluates the harassment risk of the voice content based on the emotional reactions of other users. For example, it takes early action if there are many negative emotional reactions. This makes it possible to detect harassment behavior early based on the emotional reactions of other users.

[0079] The response unit can automatically select and execute a response method according to the type and severity of the harassment. For example, the response unit analyzes the type and severity of the harassment detected by the generation AI and automatically selects an appropriate response method. For example, it sends a warning message for mild harassment and temporarily restricts access in serious cases. The generation AI also executes different response methods depending on the type of harassment. For example, it sends a warning message for slander and disables the avatar for impersonation. The generation AI also evaluates the severity of the harassment and selects an appropriate response method. For example, it immediately restricts access for serious harassment and sends a support message to the victim. This makes it possible to automatically select and execute a response method according to the type and severity of harassment.

[0080] When harassment is detected, the countermeasure unit can send an educational message to the user in question to encourage behavioral improvement. For example, when the generation AI detects harassment, the countermeasure unit sends an educational message to the user in question. For example, it sends a message urging the user to be careful not to use offensive language. Furthermore, when harassment is detected, the generation AI sends a message urging the user in question to improve their behavior. For example, it sends a message urging the user to treat other users with respect. Furthermore, when harassment is detected, the generation AI makes specific suggestions to the user to improve their behavior. For example, it suggests using positive language instead of using offensive language. In this way, when harassment is detected, an educational message can be sent to the user in question to encourage behavioral improvement.

[0081] The response unit can provide a customized response method based on the behavioral history of the user in question. For example, the generation AI analyzes the behavioral history of the user in question and provides a customized response method. For example, a stricter response method can be applied to a user who has engaged in similar harassing behavior in the past. The generation AI also provides an individually customized response method based on the behavioral history of the user in question. For example, a message encouraging behavioral improvement can be sent to a user with a specific behavioral pattern. The generation AI also takes into account the behavioral history of the user in question and selects the optimal response method. For example, an appropriate warning message or access restriction can be displayed based on the past behavioral history. This makes it possible to provide a customized response method based on the behavioral history of the user in question.

[0082] The response unit notifies other users when harassment is detected, thereby facilitating a community-wide response. For example, when the generation AI detects harassment, the response unit notifies other users. For example, it sends a warning message to the entire community to warn them. Furthermore, when harassment is detected, the generation AI suggests ways to deal with it to other users. For example, it suggests specific actions to take to support the victim. Furthermore, when harassment is detected, the generation AI sends a message to promote a community-wide response. For example, it provides instructions on how to report harassment and how to provide support. In this way, when harassment is detected, other users are notified, thereby facilitating a community-wide response.

[0083] The countermeasure unit can use the emotion estimation function to monitor the user's emotional reaction after dealing with the harassment and evaluate the effectiveness of the countermeasure. For example, the generation AI in the countermeasure unit uses the emotion estimation function to monitor the user's emotional reaction after dealing with the harassment. For example, it evaluates whether the victim's emotions have improved after the countermeasure. The generation AI also analyzes the user's emotional reaction after the countermeasure and evaluates the effectiveness of the countermeasure. For example, it determines that the countermeasure was effective if negative emotions have decreased. The generation AI also uses the emotion estimation function to monitor the user's emotional state after the countermeasure in real time and continuously evaluate the effectiveness of the countermeasure. For example, if emotions do not improve after the countermeasure, it takes additional measures. In this way, the user's emotional reaction can be monitored after dealing with the harassment and the effectiveness of the countermeasure can be evaluated.

[0084] The generative AI can analyze overall communication patterns within the metaverse and predict potential harassment risks. For example, the generative AI can analyze overall communication patterns within the metaverse and predict potential harassment risks. For example, it can analyze the frequency of use of offensive language between specific users. The generative AI can also evaluate harassment risks based on communication patterns within the metaverse. For example, it can predict the risk of harassment occurring at specific times or locations. The generative AI can also analyze overall communication patterns and detect potential harassment risks early. For example, it can issue a warning if a specific pattern is repeated. This makes it possible to analyze overall communication patterns within the metaverse and predict potential harassment risks.

[0085] The generation AI can monitor user behavior in the metaverse in real time and take immediate action if abnormal behavior occurs. The generation AI can, for example, monitor user behavior in the metaverse in real time and take immediate action if abnormal behavior occurs. For example, it can issue a warning if aggressive behavior is detected. The generation AI can also analyze user behavior in real time and take appropriate action if abnormal behavior occurs. For example, it can temporarily restrict access if abnormal behavior is detected. The generation AI can also continuously monitor user behavior in the metaverse and take immediate action if abnormal behavior occurs. For example, it can send a warning message to the user in question if abnormal behavior is detected. This allows the generation AI to monitor user behavior in real time and take immediate action if abnormal behavior occurs.

[0086] The generation AI uses the emotion estimation function to monitor the emotional state of all users in the metaverse and can take measures before negative emotions spread. For example, the generation AI uses the emotion estimation function to monitor the emotional state of all users in the metaverse. For example, it issues a warning before negative emotions spread. The generation AI also analyzes the emotional state of all users in real time and takes measures before negative emotions spread. For example, it sends a positive message when negative emotions increase. The generation AI also uses the emotion estimation function to continuously monitor the emotional state in the metaverse and take appropriate measures before negative emotions spread. For example, it responds immediately when negative emotions are detected. This makes it possible to monitor the emotional state of all users in the metaverse and take measures before negative emotions spread.

[0087] The generative AI can periodically provide positive messages and content to users in order to provide a safe environment within the metaverse. For example, the generative AI can periodically send positive messages to users in order to provide a safe environment within the metaverse. For example, it can periodically send messages of encouragement or words of gratitude. The generative AI can also provide positive content to users. For example, it can periodically share positive news or success stories. The generative AI can also periodically provide positive messages and content to users in order to maintain a safe environment within the metaverse. For example, sending positive messages improves the user's emotional state. This allows the user to regularly receive positive messages and content, thereby providing an environment in which they can feel safe.

[0088] The generative AI can collect feedback from users to evaluate the safe environment in the metaverse and improve the environment based on that feedback. For example, the generative AI collects feedback from users to evaluate the safe environment in the metaverse. For example, it may collect feedback using a survey or comment function. The generative AI also analyzes the feedback from users and improves the environment in the metaverse. For example, it may make specific improvement suggestions based on the feedback. The generative AI also continuously improves the safe environment in the metaverse based on user feedback. For example, it may analyze feedback in real time and respond immediately. This allows the safe environment in the metaverse to be continuously improved based on user feedback.

[0089] The generation AI uses the emotion estimation function to monitor users' emotional reactions to events and activities in the metaverse, allowing it to provide content that users can enjoy with peace of mind. For example, the generation AI uses the emotion estimation function to monitor users' emotional reactions to events and activities in the metaverse. For example, it improves the event content if there are a lot of negative emotional reactions. The generation AI also provides content that users can enjoy with peace of mind based on the user's emotional reactions. For example, it prioritizes providing content with a lot of positive emotional reactions. The generation AI also uses the emotion estimation function to monitor emotional reactions to events and activities in the metaverse in real time, providing an environment that users can enjoy with peace of mind. For example, it responds immediately if negative emotions are detected. This allows it to monitor users' emotional reactions to events and activities and provide content that users can enjoy with peace of mind.

[0090] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0091] The metaverse environment provision system can also provide customized measures based on a user's behavioral history. For example, it can apply more severe measures to users who have engaged in similar harassing behavior in the past. It can also send messages encouraging users with specific behavioral patterns to improve their behavior. This allows it to provide individually customized measures based on a user's behavioral history.

[0092] The metaverse environment provision system can also add a multilingual analysis function that can handle different languages ​​and dialects. For example, it can analyze chat content in multiple languages, such as English, Japanese, and Chinese. It can also analyze dialects and slang used in specific regions to detect harassment. This makes it possible to analyze chat content in different languages ​​and dialects and detect harassment.

[0093] The metaverse environment provision system can also analyze a user's input speed and typing patterns to detect abnormal behavior. For example, it can issue a warning if there is a sudden change in input speed. It can also issue a warning if a specific pattern is repeated. This allows the system to analyze a user's input speed and typing patterns and detect abnormal behavior.

[0094] The metaverse environment provision system also uses an emotion estimation function to monitor other users' emotional reactions to chat content in real time, facilitating the early detection of harassment. For example, it can issue a warning if there are many negative emotional reactions. It can also detect harassment if the emotion score is low. This allows for early detection of harassment based on the emotional reactions of other users.

[0095] The Metaverse Environment Provision System can also analyze 3D models and animations during image analysis, enabling it to cover a wider range of Metaverse content. For example, it can detect unauthorized use of 3D avatars. It can also detect inappropriate behavior within animations. By including 3D models and animations in its analysis, it can cover a wider range of Metaverse content.

[0096] The metaverse environment providing system further uses an emotion estimation function to estimate a user's emotion from facial expressions and gestures in an image, and can issue a warning if a negative emotion is expressed. For example, an alert is issued if an angry or sad expression is detected. It can also issue a warning if an aggressive gesture is detected. This allows the system to estimate a user's emotion from facial expressions and gestures in an image, and can issue a warning if a negative emotion is expressed.

[0097] The metaverse environment provision system not only analyzes voice data, but also analyzes the user's speech rate and rhythm to detect abnormal behavior. For example, it can issue a warning if there is a sudden change in speech rate. It can also issue a warning if a specific rhythm is repeated. This allows the system to analyze the user's speech rate and rhythm to detect abnormal behavior.

[0098] The metaverse environment provision system also uses an emotion estimation function to monitor other users' emotional reactions to voice in real time, facilitating the early detection of harassment. For example, it can issue a warning if there are many negative emotional reactions. It can also detect harassment if the emotion score is low. This allows for early detection of harassment based on the emotional reactions of other users.

[0099] Furthermore, if harassment is detected, the metaverse environment providing system can send an educational message to the user in question to encourage behavioral improvement. For example, a message can be sent to warn the user not to use offensive language. It can also send a message encouraging the user to treat other users with respect. In this way, if harassment is detected, an educational message can be sent to the user in question to encourage behavioral improvement.

[0100] The metaverse environment providing system can further use its emotion estimation function to monitor the user's emotional response after dealing with harassment and evaluate the effectiveness of the response method. For example, it can evaluate whether the victim's emotions have improved after the response. It can also analyze the user's emotional response after the response and evaluate the effectiveness of the response method. This makes it possible to monitor the user's emotional response after dealing with harassment and evaluate the effectiveness of the response method.

[0101] The processing flow of the second embodiment will be briefly explained below.

[0102] Step 1: The chat analysis unit analyzes chats within the metaverse. The generation AI analyzes the chat content in real time to detect slander and impersonation. The generation AI can also analyze the context of the chat content to detect offensive words and phrases. Furthermore, the generation AI can analyze the sentiment of the chat content and issue a warning if negative sentiment increases. Step 2: The harassment detection unit detects harassing behavior from the chat analyzed by the chat analysis unit. The generation AI detects abusive and offensive words and phrases and identifies harassing behavior. Step 3: The warning generation unit generates a warning message for the harassment detected by the harassment detection unit. The generation AI creates an appropriate warning message based on the detected harassment. Step 4: The notification unit notifies the user of the warning message generated by the warning generation unit. The generation AI sends the warning message to the user in real time and temporarily restricts access if necessary.

[0103] 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.

[0104] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0105] 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.

[0106] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0107] 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.

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

[0109] The 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.

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

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

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

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0120] 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.

[0121] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0122] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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).

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0132] 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.

[0133] 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.

[0134] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0135] 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.

[0136] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0137] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 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 processing similar to that of the specific processing unit 290 using these models.

[0148] 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.

[0149] 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.

[0150] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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).

[0156] 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.

[0157] 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."

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0169] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0170] 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. Using generative AI, a chat analysis unit that analyzes chats within the metaverse; a harassment detection unit that detects harassment behavior from the chat analyzed by the chat analysis unit; a warning generation unit that generates a warning message in response to the harassment behavior detected by the harassment detection unit; a notification unit that notifies the user of the warning message generated by the warning generation unit. A system characterized by:

2. The chat analysis unit Learn harassment patterns based on interaction history between specific users 2. The system of claim 1.

3. The chat analysis unit Predict the above-mentioned harassment behavior based on the user's past behavior history and speech tendencies 2. The system of claim 1.

4. The chat analysis unit Inferring user emotions from chat content and issuing a warning when negative emotions increase 2. The system of claim 1.

5. The chat analysis unit Add multilingual analysis capabilities for different languages ​​or dialects 2. The system of claim 1.

Images