system

Abstract

An object of the system according to the embodiment is to provide personalized and prompt support to a patient having a mental symptom.SOLUTION: A system includes an emotion note interpretation part, a feedback provision part, a biological data analysis part, a rest promotion part, a virtual environment provision part, and a social support part. The emotional note interpretation unit interprets an emotional note. The feedback provider may provide feedback based on a result of the interpretation by the emotion note interpreter. The biological data analysis unit analyzes biological data obtained using the smart glasses. The rest prompting unit prompts a rest on the basis of the result analyzed by the biological data analyzing unit. The virtual environment providing unit may provide a virtual environment using AR or VR technology. The social support unit facilitates connection between users.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] Current technologies do not adequately provide personalized and immediate support for patients with mental health conditions, and there is room for improvement.

[0005] The system according to the embodiment aims to provide personalized and immediate support to patients with mental health conditions. [Means for solving the problem]

[0006] The system according to the embodiment includes an emotion note interpretation unit, a feedback provision unit, a biometric data analysis unit, a rest promotion unit, a virtual environment provision unit, and a social support unit. The emotion note interpretation unit interprets the emotion note. The feedback provision unit provides feedback based on the results of the interpretation by the emotion note interpretation unit. The biometric data analysis unit analyzes biometric data obtained using smart glasses. The rest promotion unit encourages rest based on the results of the analysis by the biometric data analysis unit. The virtual environment provision unit provides a virtual environment using AR or VR technology. The social support unit facilitates connections between users. [Effects of the Invention]

[0007] The system according to the embodiment can provide personalized and immediate support to patients with psychological symptoms. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

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

[0028] (Example 1) A support system according to an embodiment of the present invention integrates emotional note interpretation, feedback provision, biometric data analysis, rest promotion, virtual environment provision, and social support. This system integrates a generative AI model with smart glasses to provide more personalized and prompt support services. For example, the generative AI interprets emotional notes entered manually by a user on a smartphone or via voice input using smart glasses in natural language and provides feedback based on the results. This allows users to better understand emotional changes and monitor their progress. Furthermore, the generative AI analyzes biometric data obtained using smart glasses and prompts rest if the user's emotional state declines over a long period of time. This allows users to understand their emotional state in real time and take appropriate measures. Furthermore, the system uses AR and VR technologies to provide users with a comfortable virtual environment, allowing them to monitor emotional changes in a relaxed state. Furthermore, the system enhances existing social support functions, facilitating connections between users and providing anonymous and safe sharing areas. This allows users to share information and receive support from other users. This allows the support system to provide enhanced support for patients with depression and other mental health conditions. For example, users can quickly and accurately grasp changes in their emotions and receive appropriate feedback. Users can also monitor their emotional state in real time and take a break as needed. Furthermore, by providing a comfortable virtual environment, users can monitor changes in their emotions in a relaxed state. This facilitates connections between users and ensures an anonymous and safe sharing area.

[0029] The support system according to the embodiment includes an emotion note interpretation unit, a feedback provision unit, a biometric data analysis unit, a rest promotion unit, a virtual environment provision unit, and a social support unit. The emotion note interpretation unit interprets an emotion note entered manually by a user on a smartphone or via voice input using the smart glasses. The emotion note may be in a text format, an audio format, or an image format, but is not limited to these examples. The emotion note interpretation unit interprets the emotion note in natural language using, for example, a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the content of the emotion note to grasp changes in emotions. The feedback provision unit provides feedback based on the results of the interpretation by the emotion note interpretation unit. Examples of feedback include, but are not limited to, text messages, audio messages, and visual feedback. The feedback provision unit uses the generation AI to provide appropriate feedback to the user. The biometric data analysis unit analyzes biometric data obtained using the smart glasses. Examples of biometric data include, but are not limited to, heart rate, body temperature, and blood pressure. The biometric data analysis unit uses a generating AI to analyze biometric data and understand the user's emotional state. The rest promotion unit encourages rest based on the results of the analysis by the biometric data analysis unit. Examples of rest include, but are not limited to, rest time, rest quality, and rest environment. The rest promotion unit uses a generating AI to encourage the user to take appropriate rest. The virtual environment provision unit provides a virtual environment using AR or VR technology. Examples of virtual environments include, but are not limited to, relaxation environments, concentration environments, and entertainment environments. The virtual environment provision unit uses a generating AI to provide an appropriate virtual environment for the user. The social support unit facilitates connections between users and provides an anonymous and safe sharing area. Examples of social support include, but are not limited to, anonymous support, group support, and individual support. The social support unit uses a generating AI to support connections between users.As a result, the support system according to the embodiment can provide a system that integrates interpretation of emotional notes, provision of feedback, analysis of biometric data, promotion of rest, provision of a virtual environment, and social support.

[0030] The emotion note interpretation unit can interpret, in natural language, emotion notes that a user has manually entered on a smartphone or via voice input on smart glasses. The emotion note interpretation unit uses, for example, a generation AI to interpret, in natural language, emotion notes that a user has manually entered on a smartphone or via voice input on smart glasses. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the content of the emotion note to grasp changes in emotion. For example, the generation AI analyzes the text of the emotion note and extracts changes in emotion. The generation AI can also convert emotion notes entered via voice input into text using voice recognition technology and analyze that text. The generation AI can also convert emotion notes entered via image input into text using image recognition technology and analyze that text. This makes it possible to interpret emotion notes according to the user's input method.

[0031] The feedback providing unit can provide feedback based on the results of interpretation by the emotion note interpretation unit. The feedback providing unit provides feedback based on the results of interpretation by the emotion note interpretation unit, for example, using a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and provides appropriate feedback to the user. For example, the generation AI sends a text message to the user based on the results of interpretation of the emotion note. The generation AI can also generate an audio message and provide it to the user. Furthermore, the generation AI can generate visual feedback and provide it to the user. This makes it possible to provide feedback based on the interpretation results.

[0032] The biometric data analysis unit can analyze biometric data obtained using the smart glasses. The biometric data analysis unit analyzes the biometric data obtained using the smart glasses, for example, using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the biometric data to understand the user's emotional state. The biometric data may include, but is not limited to, heart rate, body temperature, blood pressure, etc. For example, the generation AI may analyze heart rate data to evaluate the user's stress level. The generation AI may also analyze body temperature data to evaluate the user's health condition. Furthermore, the generation AI may analyze blood pressure data to evaluate the user's cardiovascular health condition. This enables the analysis of biometric data using smart glasses.

[0033] The rest promotion unit can encourage rest based on the results of analysis by the biometric data analysis unit. The rest promotion unit, for example, uses a generation AI to encourage rest based on the results of analysis by the biometric data analysis unit. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and encourages the user to take appropriate rest. Rest includes, for example, rest time, rest quality, and rest environment, but is not limited to these examples. For example, the generation AI analyzes the user's biometric data and suggests an appropriate rest time. The generation AI can also provide advice to improve the quality of rest based on the user's biometric data. Furthermore, the generation AI can also suggest an appropriate rest environment based on the user's biometric data. This makes it possible to promote rest based on the results of biometric data analysis.

[0034] The virtual environment providing unit can provide a virtual environment using AR or VR technology. The virtual environment providing unit can provide a virtual environment using AR or VR technology, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and can provide an appropriate virtual environment for the user. Examples of virtual environments include, but are not limited to, a relaxation environment, a concentration environment, and an entertainment environment. For example, when providing a relaxation environment, the generation AI can provide a virtual environment that includes calming music and scenery. When providing a concentration environment, the generation AI can also eliminate noise to provide an environment that is easy to concentrate in. Furthermore, when providing an entertainment environment, the generation AI can also provide content tailored to the user's preferences. This makes it possible to provide a virtual environment using AR or VR technology.

[0035] The social support unit can facilitate connections between users and provide an anonymous and safe shared area. The social support unit can facilitate connections between users and provide an anonymous and safe shared area, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and supports connections between users. Social support can include, but is not limited to, anonymous support, group support, individual support, etc. For example, when providing anonymous support, the generation AI can provide support while protecting the user's privacy. Furthermore, when providing group support, the generation AI can also provide support that promotes communication within the group. Furthermore, when providing individual support, the generation AI can also provide support that meets the user's individual needs. This makes it possible for users to connect with each other and provide a safe shared area.

[0036] The emotion note interpretation unit can improve the accuracy of the interpretation when interpreting the emotion note by referring to the user's past emotion note history. The emotion note interpretation unit, for example, uses a generation AI to improve the accuracy of the interpretation when interpreting the emotion note by referring to the user's past emotion note history. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past emotion note history to improve the accuracy of the interpretation. For example, the generation AI refers to the user's past emotion note history, identifies similar emotion patterns, and reflects them in the interpretation. The generation AI can also extract specific trigger events from the user's past emotion note history and use them in the interpretation. Furthermore, the generation AI can analyze the user's past emotion note history, grasp trends in emotional changes, and reflect them in the interpretation. In this way, the accuracy of the interpretation is improved by referring to the past emotion note history.

[0037] The emotion note interpretation unit can take into account the user's current living situation and environment when interpreting the emotion note. The emotion note interpretation unit, for example, uses a generation AI to take into account the user's current living situation and environment when interpreting the emotion note. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects this in the interpretation of the emotion note. For example, the generation AI interprets the emotion note taking into account the user's current living situation (work, family, health, etc.). The generation AI can also interpret the emotion note taking into account the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the interpretation of the emotion note based on the user's current living situation and environment. This enables interpretation that takes into account the user's current living situation and environment.

[0038] The emotion note interpretation unit can optimize the interpretation algorithm according to different input methods when interpreting emotion notes. The emotion note interpretation unit, for example, uses a generation AI to optimize the interpretation algorithm according to different input methods (voice, text, image, etc.) when interpreting emotion notes. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and applies an interpretation algorithm according to the input method. For example, the generation AI converts emotion notes input by voice into text using voice recognition technology and interprets them. The generation AI can also interpret emotion notes input by text using natural language processing technology. Furthermore, the generation AI can convert emotion notes input by image into text using image recognition technology and interpret them. This makes it possible to optimize the interpretation algorithm according to different input methods.

[0039] The emotion note interpretation unit can take into account the user's geographical location information when interpreting the emotion note. The emotion note interpretation unit, for example, uses a generation AI to take into account the user's geographical location information when interpreting the emotion note. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes geographical location information and reflects it in the interpretation of the emotion note. For example, the generation AI obtains the user's current location and reflects emotion triggers related to that location in the interpretation. Furthermore, when the user is in a specific location, the generation AI can also refer to past emotion notes related to that location to perform the interpretation. Furthermore, the generation AI can customize the interpretation of the emotion note based on the user's geographical location information. This makes it possible to perform an interpretation that takes geographical location information into account.

[0040] The emotion note interpretation unit can analyze the user's social media activity when interpreting the emotion note and reflect related information in the interpretation. The emotion note interpretation unit can, for example, use a generation AI to analyze the user's social media activity when interpreting the emotion note and reflect related information in the interpretation. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activity and reflects it in the interpretation of the emotion note. For example, the generation AI can analyze the content of the user's social media posts and reflect this in the interpretation of the emotion note. The generation AI can also refer to the activity of the user's friends on social media and reflect this in the interpretation of the emotion note. Furthermore, the generation AI can refer to the user's social media check-in information and reflect this in the interpretation of the emotion note. This makes it possible to make an interpretation that reflects social media activity.

[0041] The emotion note interpretation unit can customize the interpretation method when interpreting emotion notes by reflecting the user's past feedback. The emotion note interpretation unit, for example, uses a generation AI to customize the interpretation method when interpreting emotion notes by reflecting the user's past feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the interpretation method. For example, the generation AI can refer to feedback provided by the user in the past and adjust the interpretation method. Furthermore, if the generation AI determines from the user's past feedback that a specific interpretation method is effective, it can preferentially use that method. Furthermore, the generation AI can customize the interpretation method based on the user's past feedback. This makes it possible to customize the interpretation method by reflecting past feedback.

[0042] The feedback providing unit can adjust the level of detail of the feedback based on the importance of the emotion notes when providing feedback. The feedback providing unit, for example, uses a generation AI to adjust the level of detail of the feedback based on the importance of the emotion notes when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of the emotion notes and adjusts the level of detail of the feedback. For example, the generation AI provides detailed feedback when the importance of the emotion notes is high. The generation AI can also provide brief feedback when the importance of the emotion notes is low. Furthermore, the generation AI can adjust the level of detail of the feedback according to the importance of the emotion notes. This makes it possible to adjust the level of detail of the feedback according to the importance of the emotion notes.

[0043] The feedback providing unit can apply different feedback algorithms depending on the category of the emotion note when providing feedback. The feedback providing unit, for example, uses a generation AI to apply different feedback algorithms depending on the category of the emotion note when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the category of the emotion note and applies an appropriate feedback algorithm. For example, if the emotion note is related to stress, the generation AI can provide feedback to reduce stress. Also, if the emotion note is related to joy, the generation AI can provide feedback to maintain that emotion. Furthermore, if the emotion note is related to sadness, the generation AI can provide comforting feedback. This makes it possible to apply feedback algorithms depending on the category of the emotion note.

[0044] The feedback providing unit can improve the accuracy of the feedback when providing feedback by referring to the user's past feedback history. The feedback providing unit, for example, uses a generation AI to improve the accuracy of the feedback when providing feedback by referring to the user's past feedback history. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past feedback history to improve the accuracy of the feedback. For example, the generation AI refers to the user's past feedback history to provide optimal feedback. Furthermore, if the generation AI finds that a specific feedback is effective from the user's past feedback history, it can preferentially use that method. Furthermore, the generation AI can improve the accuracy of the feedback based on the user's past feedback history. This makes it possible to improve the accuracy of feedback by referring to the past feedback history.

[0045] The feedback providing unit can determine the priority of feedback based on the time when the emotion note was submitted when providing feedback. The feedback providing unit, for example, uses a generation AI to determine the priority of feedback based on the time when the emotion note was submitted when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the time of submission to determine the priority of feedback. For example, the generation AI provides feedback preferentially if the emotion note was submitted recently. Furthermore, the generation AI can also provide feedback later if the emotion note was submitted in the past. Furthermore, the generation AI can adjust the priority of feedback depending on the time when the emotion note was submitted. This makes it possible to determine the priority of feedback depending on the time when the emotion note was submitted.

[0046] The feedback providing unit can adjust the order of feedback based on the relevance of the emotion notes when providing feedback. The feedback providing unit, for example, uses a generation AI to adjust the order of feedback based on the relevance of the emotion notes when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of the emotion notes and adjusts the order of feedback. For example, the generation AI provides feedback preferentially when the emotion notes are highly relevant. Furthermore, the generation AI can also provide feedback later when the emotion notes are less relevant. Furthermore, the generation AI can adjust the order of feedback according to the relevance of the emotion notes. This makes it possible to adjust the order of feedback according to the relevance of the emotion notes.

[0047] The feedback providing unit can adjust the use of technical terms in the feedback according to the user's level of expertise when providing feedback. The feedback providing unit, for example, uses a generation AI to adjust the use of technical terms in the feedback according to the user's level of expertise when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's level of expertise and adjusts the use of technical terms in the feedback. For example, if the user has technical knowledge, the generation AI provides feedback using technical terms. Also, if the user does not have technical knowledge, the generation AI can provide feedback in simple language. Furthermore, the generation AI can adjust the use of technical terms in the feedback according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the feedback according to the user's level of expertise.

[0048] The biometric data analysis unit can improve the accuracy of the analysis by referring to the user's past biometric data history when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to improve the accuracy of the analysis by referring to the user's past biometric data history when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past biometric data history to improve the accuracy of the analysis. For example, the generation AI refers to the user's past biometric data history, identifies similar patterns, and reflects them in the analysis. The generation AI can also extract specific trigger events from the user's past biometric data history and use them in the analysis. Furthermore, the generation AI can analyze the user's past biometric data history to understand trends in health status and reflect them in the analysis. In this way, the accuracy of the analysis is improved by referring to the past biometric data history.

[0049] The biometric data analysis unit can perform the analysis by taking into account the user's current living situation and environment when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to perform the analysis by taking into account the user's current living situation and environment when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects this in the analysis of the biometric data. For example, the generation AI analyzes the biometric data by taking into account the user's current living situation (work, family, health, etc.). The generation AI can also analyze the biometric data by taking into account the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the analysis of the biometric data based on the user's current living situation and environment. This enables analysis that takes into account the user's current living situation and environment.

[0050] The biometric data analysis unit can optimize the analysis algorithm according to different types of biometric data when analyzing the biometric data. For example, the biometric data analysis unit uses a generation AI to optimize the analysis algorithm according to different types of biometric data (heart rate, body temperature, blood pressure, etc.) when analyzing the biometric data. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the type of biometric data and applies an appropriate analysis algorithm. For example, the generation AI may analyze heart rate data and evaluate stress levels. The generation AI may also analyze body temperature data and evaluate health conditions. Furthermore, the generation AI may analyze blood pressure data and evaluate cardiovascular health conditions. This makes it possible to optimize the analysis algorithm according to different types of biometric data.

[0051] The biometric data analysis unit can perform analysis taking into account the user's geographical location information when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to perform analysis taking into account the user's geographical location information when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information and reflects it in the analysis of the biometric data. For example, the generation AI obtains the user's current location and reflects health risks associated with that location in the analysis. Furthermore, when the user is in a specific location, the generation AI can also perform analysis by referring to past biometric data related to that location. Furthermore, the generation AI can customize the analysis of the biometric data based on the user's geographical location information. This makes it possible to perform analysis taking into account geographical location information.

[0052] The biometric data analysis unit can analyze the user's social media activities during biometric data analysis and reflect related information in the analysis. The biometric data analysis unit can, for example, use a generation AI to analyze the user's social media activities during biometric data analysis and reflect related information in the analysis. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activities and reflects them in the analysis of the biometric data. For example, the generation AI can analyze the content of the user's social media posts and reflect them in the analysis of the biometric data. The generation AI can also refer to the activities of the user's friends on social media and reflect them in the analysis of the biometric data. Furthermore, the generation AI can refer to the user's check-in information on social media and reflect them in the analysis of the biometric data. This makes it possible to perform an analysis that reflects social media activities.

[0053] The biometric data analysis unit can customize the analysis method by reflecting the user's past feedback when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to customize the analysis method by reflecting the user's past feedback when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the analysis method. For example, the generation AI refers to feedback provided by the user in the past and adjusts the analysis method. Furthermore, if the user's past feedback indicates that a specific analysis method is effective, the generation AI can preferentially use that method. Furthermore, the generation AI can customize the analysis method based on the user's past feedback. This makes it possible to customize the analysis method by reflecting past feedback.

[0054] The rest promotion unit can adjust the level of detail of rest based on the importance of biometric data when promoting rest. The rest promotion unit, for example, uses a generation AI to adjust the level of detail of rest based on the importance of biometric data when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of biometric data and adjusts the level of detail of rest. For example, the generation AI may suggest a detailed rest method when the importance of biometric data is high. The generation AI may also suggest a simple rest method when the importance of biometric data is low. Furthermore, the generation AI can adjust the level of detail of rest according to the importance of biometric data. This makes it possible to adjust the level of detail of rest according to the importance of biometric data.

[0055] The rest promotion unit can apply different rest promotion algorithms depending on the category of biometric data when promoting rest. The rest promotion unit, for example, uses a generation AI to apply different rest promotion algorithms depending on the category of biometric data when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the category of biometric data and applies an appropriate rest promotion algorithm. For example, if the biometric data is related to stress, the generation AI can suggest a rest method to reduce stress. Also, if the biometric data is related to fatigue, the generation AI can suggest a rest method to recover from fatigue. Furthermore, if the biometric data is related to maintaining health, the generation AI can suggest a rest method to maintain health. This makes it possible to apply a rest promotion algorithm depending on the category of biometric data.

[0056] The rest promotion unit can improve the accuracy of rest by referring to the user's past rest history when promoting rest. The rest promotion unit, for example, uses a generation AI to improve the accuracy of rest by referring to the user's past rest history when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past rest history to improve the accuracy of rest. For example, the generation AI can refer to the user's past rest history and suggest an optimal rest method. Furthermore, if a specific rest method is found to be effective based on the user's past rest history, the generation AI can preferentially use that method. Furthermore, the generation AI can improve the accuracy of rest based on the user's past rest history. This makes it possible to improve the accuracy of rest by referring to the past rest history.

[0057] The rest promotion unit can determine rest priorities based on the time of submission of biometric data when promoting rest. The rest promotion unit, for example, uses a generation AI to determine rest priorities based on the time of submission of biometric data when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the time of submission and determines rest priorities. For example, the generation AI may preferentially suggest rest methods if biometric data was submitted recently. Furthermore, the generation AI may postpone suggesting rest methods if biometric data was submitted in the past. Furthermore, the generation AI can adjust rest priorities based on the time of submission of biometric data. This makes it possible to determine rest priorities based on the time of submission of biometric data.

[0058] The rest promotion unit can adjust the order of rest based on the relevance of the biometric data when promoting rest. The rest promotion unit adjusts the order of rest based on the relevance of the biometric data when promoting rest, for example, using a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of the biometric data to adjust the order of rest. For example, if the biometric data is highly relevant, the generation AI can prioritize suggesting a rest method. Also, if the biometric data is less relevant, the generation AI can postpone suggesting a rest method. Furthermore, the generation AI can adjust the order of rest based on the relevance of the biometric data. This makes it possible to adjust the order of rest based on the relevance of the biometric data.

[0059] The rest promotion unit can adjust the use of rest terminology according to the user's level of expertise when promoting rest. The rest promotion unit, for example, uses a generation AI to adjust the use of rest terminology according to the user's level of expertise when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's level of expertise and adjusts the use of rest terminology. For example, if the user has expertise, the generation AI can suggest a rest method using technical terminology. Also, if the user does not have expertise, the generation AI can suggest a rest method in simple terms. Furthermore, the generation AI can adjust the use of rest terminology according to the user's level of expertise. This makes it possible to adjust the use of rest terminology according to the user's level of expertise.

[0060] The virtual environment providing unit can improve the accuracy of the virtual environment provision by referring to the user's past virtual environment usage history when providing the virtual environment. The virtual environment providing unit, for example, uses a generation AI to improve the accuracy of the virtual environment provision by referring to the user's past virtual environment usage history when providing the virtual environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past virtual environment usage history to improve the accuracy of the provision. For example, the generation AI can provide the optimal virtual environment by referring to the user's past virtual environment usage history. Furthermore, if a specific virtual environment is found to be effective based on the user's past virtual environment usage history, the generation AI can also preferentially provide that environment. Furthermore, the generation AI can improve the accuracy of the virtual environment provision based on the user's past virtual environment usage history. In this way, the accuracy of the provision is improved by referring to the past virtual environment usage history.

[0061] The virtual environment providing unit can provide the virtual environment while taking into consideration the user's current living situation and environment. The virtual environment providing unit, for example, uses a generation AI to provide the virtual environment while taking into consideration the user's current living situation and environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects them in the provision of the virtual environment. For example, the generation AI provides the virtual environment while taking into consideration the user's current living situation (work, family, health, etc.). The generation AI can also provide the virtual environment while taking into consideration the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the provision of the virtual environment based on the user's current living situation and environment. This makes it possible to provide a virtual environment that takes into consideration the user's current living situation and environment.

[0062] The virtual environment providing unit can optimize the provision algorithm according to different types of virtual environments when providing a virtual environment. For example, the virtual environment providing unit uses a generation AI to optimize the provision algorithm according to different types of virtual environments (relaxation, concentration, entertainment, etc.) when providing a virtual environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the type of virtual environment and applies an appropriate provision algorithm. For example, when providing a relaxation environment, the generation AI provides a virtual environment including calming music and scenery. Furthermore, when providing a concentration environment, the generation AI can eliminate noise to provide an environment that is easy to concentrate in. Furthermore, when providing an entertainment environment, the generation AI can provide content tailored to the user's preferences. This enables the provision algorithm to be optimized according to different types of virtual environments.

[0063] The virtual environment providing unit can provide the virtual environment taking into account the user's geographical location information. The virtual environment providing unit, for example, uses a generation AI to provide the virtual environment taking into account the user's geographical location information. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information and reflects it in the provision of the virtual environment. For example, the generation AI obtains the user's current location and provides a virtual environment related to that location. Furthermore, if the user is in a specific location, the generation AI can also provide a virtual environment related to that location. Furthermore, the generation AI can customize the provision of the virtual environment based on the user's geographical location information. This makes it possible to provide a virtual environment that takes geographical location information into account.

[0064] The virtual environment providing unit can analyze the user's social media activity when providing the virtual environment and reflect related information in the provided environment. The virtual environment providing unit can, for example, use a generation AI to analyze the user's social media activity when providing the virtual environment and reflect related information in the provided environment. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activity and reflects it in the provided virtual environment. For example, the generation AI can analyze the content of the user's social media posts and reflect it in the provided virtual environment. The generation AI can also refer to the activity of the user's friends on social media and reflect it in the provided virtual environment. Furthermore, the generation AI can refer to the user's check-in information on social media and reflect it in the provided virtual environment. This makes it possible to provide a virtual environment that reflects social media activity.

[0065] The virtual environment providing unit can customize the method of providing a virtual environment by reflecting the user's past feedback when providing the virtual environment. The virtual environment providing unit, for example, uses a generation AI to customize the method of providing a virtual environment by reflecting the user's past feedback when providing the virtual environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the method of providing the virtual environment. For example, the generation AI refers to feedback provided by the user in the past and adjusts the method of providing the virtual environment. Furthermore, if the user's past feedback indicates that a specific virtual environment is effective, the generation AI can preferentially provide that environment. Furthermore, the generation AI can customize the method of providing the virtual environment based on the user's past feedback. This makes it possible to customize the method of providing a virtual environment by reflecting past feedback.

[0066] The social support unit can improve the accuracy of social support provision by referring to the user's past social support usage history when providing social support. The social support unit, for example, uses a generation AI to improve the accuracy of social support provision by referring to the user's past social support usage history when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past social support usage history to improve the accuracy of provision. For example, the generation AI can provide optimal social support by referring to the user's past social support usage history. Furthermore, if a specific support method is found to be effective based on the user's past social support usage history, the generation AI can preferentially provide that method. Furthermore, the generation AI can improve the accuracy of social support provision based on the user's past social support usage history. In this way, the accuracy of provision is improved by referring to the past social support usage history.

[0067] The social support unit can provide social support while taking into account the user's current living situation and environment. The social support unit, for example, uses a generation AI to provide social support while taking into account the user's current living situation and environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects this in the provision of social support. For example, the generation AI provides social support while taking into account the user's current living situation (work, family, health, etc.). The generation AI can also provide social support while taking into account the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the provision of social support based on the user's current living situation and environment. This makes it possible to provide social support while taking into account the user's current living situation and environment.

[0068] The social support unit can optimize the provision algorithm according to different types of social support when providing social support. For example, the social support unit uses a generation AI to optimize the provision algorithm according to different types of social support (anonymous, group, individual, etc.) when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the type of social support and applies an appropriate provision algorithm. For example, when providing anonymous support, the generation AI provides support while protecting the user's privacy. Furthermore, when providing group support, the generation AI can also provide support that promotes communication within the group. Furthermore, when providing individual support, the generation AI can also provide support that meets the user's individual needs. This makes it possible to optimize the provision algorithm according to different types of social support.

[0069] The social support unit can provide social support while taking into account the user's geographical location information. The social support unit, for example, uses a generation AI to provide social support while taking into account the user's geographical location information. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information and reflects it in the provision of social support. For example, the generation AI obtains the user's current location and provides social support related to that location. Furthermore, if the user is in a specific location, the generation AI can also provide social support related to that location. Furthermore, the generation AI can customize the provision of social support based on the user's geographical location information. This makes it possible to provide social support while taking into account the geographical location information.

[0070] The social support unit can analyze the user's social media activities and reflect related information in the social support provided when providing social support. The social support unit, for example, uses a generation AI to analyze the user's social media activities and reflect related information in the social support provided when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activities and reflects them in the social support provided. For example, the generation AI analyzes the content of the user's social media posts and reflects them in the social support provided. The generation AI can also refer to the activities of the user's friends on social media and reflect them in the social support provided. Furthermore, the generation AI can refer to the user's social media check-in information and reflect them in the social support provided. This makes it possible to provide social support that reflects social media activities.

[0071] The social support unit can customize the method of providing social support by reflecting the user's past feedback when providing social support. The social support unit, for example, uses a generation AI to customize the method of providing social support by reflecting the user's past feedback when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the method of providing social support. For example, the generation AI refers to feedback provided by the user in the past and adjusts the method of providing social support. Furthermore, if a specific method of social support is found to be effective based on the user's past feedback, the generation AI can provide that method preferentially. Furthermore, the generation AI can customize the method of providing social support based on the user's past feedback. This makes it possible to customize the method of providing social support by reflecting past feedback.

[0072] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0073] When interpreting a user's emotion note, the emotion note interpretation unit can improve the accuracy of the interpretation by referring to the user's past behavioral patterns. For example, it can analyze what emotions the user has expressed in specific situations in the past and reflect this in the interpretation of the current emotion note. It can also take into account what emotions the user tends to express at specific times or places when making an interpretation. Furthermore, it can extract specific trigger events from the user's past behavioral patterns and use them in the interpretation. In this way, by referring to past behavioral patterns, the accuracy of the interpretation can be improved.

[0074] The emotion note interpretation unit can support input in different languages ​​when interpreting a user's emotion notes. For example, if a user inputs emotion notes in different languages, such as English, Spanish, and French, it will provide an interpretation that corresponds to each language. It can also use generative AI to translate between different languages ​​and provide interpretation results. Furthermore, if a user uses multiple languages, it can provide an interpretation that corresponds to each language and provide an integrated interpretation result. This improves the accuracy of interpretation by supporting input in different languages.

[0075] The feedback providing unit can refer to the user's feedback history and customize new feedback based on the content of past feedback. For example, it can analyze the content of feedback the user has received in the past and provide feedback in similar situations. It can also evaluate the effectiveness of feedback the user has received in the past and provide effective feedback preferentially. Furthermore, it can extract specific feedback patterns from the user's feedback history and reflect them in new feedback. In this way, the accuracy of feedback can be improved by referring to the past feedback history.

[0076] When analyzing a user's biometric data, the biometric data analysis unit can integrate data from different devices. For example, it can integrate biometric data collected from different devices, such as smart glasses, smart watches, and smartphones, to perform a comprehensive analysis. It can also synchronize data between different devices to provide consistent data. It can also compare data from different devices and detect outliers. This improves the accuracy of the analysis by integrating data from different devices.

[0077] The rest promotion unit can refer to the user's rest history and suggest new rest methods based on past rest methods. For example, it can evaluate the effectiveness of the user's past rest methods and prioritize suggesting effective rest methods. It can also extract specific rest patterns from the user's rest history and reflect them in new rest methods. It can also suggest individually customized rest methods based on the user's rest history. This improves the accuracy of rest methods by referring to past rest history.

[0078] The virtual environment providing unit can refer to the user's virtual environment usage history and provide a new virtual environment based on past usage. For example, it can evaluate the effectiveness of virtual environments used by the user in the past and provide effective virtual environments preferentially. It can also extract specific usage patterns from the user's virtual environment usage history and reflect them in a new virtual environment. Furthermore, it can provide an individually customized virtual environment based on the user's virtual environment usage history. This improves the accuracy of the virtual environment provided by referring to past usage history.

[0079] The processing flow of the first embodiment will be briefly explained below.

[0080] Step 1: The emotion note interpretation unit interprets the emotion note entered by the user manually on a smartphone or by voice on the smart glasses. Emotion notes can be in text, audio, or image format. The emotion note interpretation unit uses generative AI to interpret the emotion note in natural language and grasp changes in emotions. Step 2: The feedback providing unit provides feedback based on the results interpreted by the emotion note interpretation unit. The feedback may be a text message, a voice message, or visual feedback. The feedback providing unit uses a generation AI to provide appropriate feedback to the user. Step 3: The biometric data analysis unit analyzes the biometric data obtained using the smart glasses. The biometric data includes heart rate, body temperature, blood pressure, etc. The biometric data analysis unit uses generative AI to analyze the biometric data and understand the user's emotional state. Step 4: The rest promotion unit encourages the user to take a rest based on the results of the analysis by the biometric data analysis unit. Rest includes rest time, quality of rest, and rest environment. The rest promotion unit uses generation AI to encourage the user to take an appropriate rest. Step 5: The virtual environment providing unit provides a virtual environment using AR or VR technology. The virtual environment can be a relaxation environment, a concentration environment, an entertainment environment, etc. The virtual environment providing unit uses a generating AI to provide an appropriate virtual environment for the user. Step 6: The social support section facilitates connections between users and provides an anonymous and safe sharing area. Social support includes anonymous support, group support, and individual support. The social support section uses generative AI to help users connect with each other.

[0081] (Example 2) A support system according to an embodiment of the present invention integrates emotional note interpretation, feedback provision, biometric data analysis, rest promotion, virtual environment provision, and social support. This system integrates a generative AI model with smart glasses to provide more personalized and prompt support services. For example, the generative AI interprets emotional notes entered manually by a user on a smartphone or via voice input using smart glasses in natural language and provides feedback based on the results. This allows users to better understand emotional changes and monitor their progress. Furthermore, the generative AI analyzes biometric data obtained using smart glasses and prompts rest if the user's emotional state declines over a long period of time. This allows users to understand their emotional state in real time and take appropriate measures. Furthermore, the system uses AR and VR technologies to provide users with a comfortable virtual environment, allowing them to monitor emotional changes in a relaxed state. Furthermore, the system enhances existing social support functions, facilitating connections between users and providing anonymous and safe sharing areas. This allows users to share information and receive support from other users. This allows the support system to provide enhanced support for patients with depression and other mental health conditions. For example, users can quickly and accurately grasp changes in their emotions and receive appropriate feedback. Users can also monitor their emotional state in real time and take a break as needed. Furthermore, by providing a comfortable virtual environment, users can monitor changes in their emotions in a relaxed state. This facilitates connections between users and ensures an anonymous and safe sharing area.

[0082] The support system according to the embodiment includes an emotion note interpretation unit, a feedback provision unit, a biometric data analysis unit, a rest promotion unit, a virtual environment provision unit, and a social support unit. The emotion note interpretation unit interprets an emotion note entered manually by a user on a smartphone or via voice input using the smart glasses. The emotion note may be in a text format, an audio format, or an image format, but is not limited to these examples. The emotion note interpretation unit interprets the emotion note in natural language using, for example, a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the content of the emotion note to grasp changes in emotions. The feedback provision unit provides feedback based on the results of the interpretation by the emotion note interpretation unit. Examples of feedback include, but are not limited to, text messages, audio messages, and visual feedback. The feedback provision unit uses the generation AI to provide appropriate feedback to the user. The biometric data analysis unit analyzes biometric data obtained using the smart glasses. Examples of biometric data include, but are not limited to, heart rate, body temperature, and blood pressure. The biometric data analysis unit uses a generating AI to analyze biometric data and understand the user's emotional state. The rest promotion unit encourages rest based on the results of the analysis by the biometric data analysis unit. Examples of rest include, but are not limited to, rest time, rest quality, and rest environment. The rest promotion unit uses a generating AI to encourage the user to take appropriate rest. The virtual environment provision unit provides a virtual environment using AR or VR technology. Examples of virtual environments include, but are not limited to, relaxation environments, concentration environments, and entertainment environments. The virtual environment provision unit uses a generating AI to provide an appropriate virtual environment for the user. The social support unit facilitates connections between users and provides an anonymous and safe sharing area. Examples of social support include, but are not limited to, anonymous support, group support, and individual support. The social support unit uses a generating AI to support connections between users.As a result, the support system according to the embodiment can provide a system that integrates interpretation of emotional notes, provision of feedback, analysis of biometric data, promotion of rest, provision of a virtual environment, and social support.

[0083] The emotion note interpretation unit can interpret, in natural language, emotion notes that a user has manually entered on a smartphone or via voice input on smart glasses. The emotion note interpretation unit uses, for example, a generation AI to interpret, in natural language, emotion notes that a user has manually entered on a smartphone or via voice input on smart glasses. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the content of the emotion note to grasp changes in emotion. For example, the generation AI analyzes the text of the emotion note and extracts changes in emotion. The generation AI can also convert emotion notes entered via voice input into text using voice recognition technology and analyze that text. The generation AI can also convert emotion notes entered via image input into text using image recognition technology and analyze that text. This makes it possible to interpret emotion notes according to the user's input method.

[0084] The feedback providing unit can provide feedback based on the results of interpretation by the emotion note interpretation unit. The feedback providing unit provides feedback based on the results of interpretation by the emotion note interpretation unit, for example, using a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and provides appropriate feedback to the user. For example, the generation AI sends a text message to the user based on the results of interpretation of the emotion note. The generation AI can also generate an audio message and provide it to the user. Furthermore, the generation AI can generate visual feedback and provide it to the user. This makes it possible to provide feedback based on the interpretation results.

[0085] The biometric data analysis unit can analyze biometric data obtained using the smart glasses. The biometric data analysis unit analyzes the biometric data obtained using the smart glasses, for example, using a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the biometric data to understand the user's emotional state. The biometric data may include, but is not limited to, heart rate, body temperature, blood pressure, etc. For example, the generation AI may analyze heart rate data to evaluate the user's stress level. The generation AI may also analyze body temperature data to evaluate the user's health condition. Furthermore, the generation AI may analyze blood pressure data to evaluate the user's cardiovascular health condition. This enables the analysis of biometric data using smart glasses.

[0086] The rest promotion unit can encourage rest based on the results of analysis by the biometric data analysis unit. The rest promotion unit, for example, uses a generation AI to encourage rest based on the results of analysis by the biometric data analysis unit. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and encourages the user to take appropriate rest. Rest includes, for example, rest time, rest quality, and rest environment, but is not limited to these examples. For example, the generation AI analyzes the user's biometric data and suggests an appropriate rest time. The generation AI can also provide advice to improve the quality of rest based on the user's biometric data. Furthermore, the generation AI can also suggest an appropriate rest environment based on the user's biometric data. This makes it possible to promote rest based on the results of biometric data analysis.

[0087] The virtual environment providing unit can provide a virtual environment using AR or VR technology. The virtual environment providing unit can provide a virtual environment using AR or VR technology, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and can provide an appropriate virtual environment for the user. Examples of virtual environments include, but are not limited to, a relaxation environment, a concentration environment, and an entertainment environment. For example, when providing a relaxation environment, the generation AI can provide a virtual environment that includes calming music and scenery. When providing a concentration environment, the generation AI can also eliminate noise to provide an environment that is easy to concentrate in. Furthermore, when providing an entertainment environment, the generation AI can also provide content tailored to the user's preferences. This makes it possible to provide a virtual environment using AR or VR technology.

[0088] The social support unit can facilitate connections between users and provide an anonymous and safe shared area. The social support unit can facilitate connections between users and provide an anonymous and safe shared area, for example, using a generation AI. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and supports connections between users. Social support can include, but is not limited to, anonymous support, group support, individual support, etc. For example, when providing anonymous support, the generation AI can provide support while protecting the user's privacy. Furthermore, when providing group support, the generation AI can also provide support that promotes communication within the group. Furthermore, when providing individual support, the generation AI can also provide support that meets the user's individual needs. This makes it possible for users to connect with each other and provide a safe shared area.

[0089] The emotion note interpretation unit can estimate the user's emotion and adjust the interpretation method of the emotion note based on the estimated user emotion. The emotion note interpretation unit, for example, uses a generation AI to estimate the user's emotion and adjust the interpretation method of the emotion note based on the estimated user emotion. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotion and adjusts the interpretation method of the emotion note. For example, if the user is feeling stressed, the generation AI simplifies the interpretation of the emotion note and extracts only the important points. In addition, if the user is relaxed, the generation AI can provide a detailed interpretation and analyze emotional changes in detail. Furthermore, if the user is in a hurry, the generation AI can quickly perform an interpretation and provide results in a short time. This makes it possible to adjust the interpretation method according to the user's emotion.

[0090] The emotion note interpretation unit can improve the accuracy of the interpretation when interpreting the emotion note by referring to the user's past emotion note history. The emotion note interpretation unit, for example, uses a generation AI to improve the accuracy of the interpretation when interpreting the emotion note by referring to the user's past emotion note history. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past emotion note history to improve the accuracy of the interpretation. For example, the generation AI refers to the user's past emotion note history, identifies similar emotion patterns, and reflects them in the interpretation. The generation AI can also extract specific trigger events from the user's past emotion note history and use them in the interpretation. Furthermore, the generation AI can analyze the user's past emotion note history, grasp trends in emotional changes, and reflect them in the interpretation. In this way, the accuracy of the interpretation is improved by referring to the past emotion note history.

[0091] The emotion note interpretation unit can take into account the user's current living situation and environment when interpreting the emotion note. The emotion note interpretation unit, for example, uses a generation AI to take into account the user's current living situation and environment when interpreting the emotion note. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects this in the interpretation of the emotion note. For example, the generation AI interprets the emotion note taking into account the user's current living situation (work, family, health, etc.). The generation AI can also interpret the emotion note taking into account the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the interpretation of the emotion note based on the user's current living situation and environment. This enables interpretation that takes into account the user's current living situation and environment.

[0092] The emotion note interpretation unit can optimize the interpretation algorithm according to different input methods when interpreting emotion notes. The emotion note interpretation unit, for example, uses a generation AI to optimize the interpretation algorithm according to different input methods (voice, text, image, etc.) when interpreting emotion notes. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and applies an interpretation algorithm according to the input method. For example, the generation AI converts emotion notes input by voice into text using voice recognition technology and interprets them. The generation AI can also interpret emotion notes input by text using natural language processing technology. Furthermore, the generation AI can convert emotion notes input by image into text using image recognition technology and interpret them. This makes it possible to optimize the interpretation algorithm according to different input methods.

[0093] The emotion note interpretation unit can estimate the user's emotions and adjust the display method of the interpretation results based on the estimated user emotions. The emotion note interpretation unit can estimate the user's emotions using, for example, a generation AI and adjust the display method of the interpretation results based on the estimated user emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyze the user's emotions and adjust the display method of the interpretation results. For example, if the user is feeling stressed, the generation AI can display a concise interpretation result and emphasize only the important points. Alternatively, if the user is relaxed, the generation AI can display a detailed interpretation result and explain the changes in emotions in detail. Furthermore, if the user is in a hurry, the generation AI can quickly display the interpretation result so that it can be understood in a short amount of time. This makes it possible to adjust the display method of the interpretation results according to the user's emotions.

[0094] The emotion note interpretation unit can take into account the user's geographical location information when interpreting the emotion note. The emotion note interpretation unit, for example, uses a generation AI to take into account the user's geographical location information when interpreting the emotion note. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes geographical location information and reflects it in the interpretation of the emotion note. For example, the generation AI obtains the user's current location and reflects emotion triggers related to that location in the interpretation. Furthermore, when the user is in a specific location, the generation AI can also refer to past emotion notes related to that location to perform the interpretation. Furthermore, the generation AI can customize the interpretation of the emotion note based on the user's geographical location information. This makes it possible to perform an interpretation that takes geographical location information into account.

[0095] The emotion note interpretation unit can analyze the user's social media activity when interpreting the emotion note and reflect related information in the interpretation. The emotion note interpretation unit can, for example, use a generation AI to analyze the user's social media activity when interpreting the emotion note and reflect related information in the interpretation. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activity and reflects it in the interpretation of the emotion note. For example, the generation AI can analyze the content of the user's social media posts and reflect this in the interpretation of the emotion note. The generation AI can also refer to the activity of the user's friends on social media and reflect this in the interpretation of the emotion note. Furthermore, the generation AI can refer to the user's social media check-in information and reflect this in the interpretation of the emotion note. This makes it possible to make an interpretation that reflects social media activity.

[0096] The emotion note interpretation unit can customize the interpretation method when interpreting emotion notes by reflecting the user's past feedback. The emotion note interpretation unit, for example, uses a generation AI to customize the interpretation method when interpreting emotion notes by reflecting the user's past feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the interpretation method. For example, the generation AI can refer to feedback provided by the user in the past and adjust the interpretation method. Furthermore, if the generation AI determines from the user's past feedback that a specific interpretation method is effective, it can preferentially use that method. Furthermore, the generation AI can customize the interpretation method based on the user's past feedback. This makes it possible to customize the interpretation method by reflecting past feedback.

[0097] The feedback providing unit can estimate the user's emotions and adjust the content of the feedback based on the estimated user's emotions. The feedback providing unit, for example, uses a generation AI to estimate the user's emotions and adjust the content of the feedback based on the estimated user's emotions. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the content of the feedback. For example, if the user is feeling stressed, the generation AI can provide feedback to relax. Also, if the user is relaxed, the generation AI can provide feedback that explains the change in emotions in detail. Furthermore, if the user is in a hurry, the generation AI can provide feedback that is easy to understand quickly. This makes it possible to adjust the content of the feedback according to the user's emotions.

[0098] The feedback providing unit can adjust the level of detail of the feedback based on the importance of the emotion notes when providing feedback. The feedback providing unit, for example, uses a generation AI to adjust the level of detail of the feedback based on the importance of the emotion notes when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of the emotion notes and adjusts the level of detail of the feedback. For example, the generation AI provides detailed feedback when the importance of the emotion notes is high. The generation AI can also provide brief feedback when the importance of the emotion notes is low. Furthermore, the generation AI can adjust the level of detail of the feedback according to the importance of the emotion notes. This makes it possible to adjust the level of detail of the feedback according to the importance of the emotion notes.

[0099] The feedback providing unit can apply different feedback algorithms depending on the category of the emotion note when providing feedback. The feedback providing unit, for example, uses a generation AI to apply different feedback algorithms depending on the category of the emotion note when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the category of the emotion note and applies an appropriate feedback algorithm. For example, if the emotion note is related to stress, the generation AI can provide feedback to reduce stress. Also, if the emotion note is related to joy, the generation AI can provide feedback to maintain that emotion. Furthermore, if the emotion note is related to sadness, the generation AI can provide comforting feedback. This makes it possible to apply feedback algorithms depending on the category of the emotion note.

[0100] The feedback providing unit can improve the accuracy of the feedback when providing feedback by referring to the user's past feedback history. The feedback providing unit, for example, uses a generation AI to improve the accuracy of the feedback when providing feedback by referring to the user's past feedback history. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past feedback history to improve the accuracy of the feedback. For example, the generation AI refers to the user's past feedback history to provide optimal feedback. Furthermore, if the generation AI finds that a specific feedback is effective from the user's past feedback history, it can preferentially use that method. Furthermore, the generation AI can improve the accuracy of the feedback based on the user's past feedback history. This makes it possible to improve the accuracy of feedback by referring to the past feedback history.

[0101] The feedback providing unit can estimate the user's emotions and adjust the length of the feedback based on the estimated user's emotions. The feedback providing unit, for example, uses a generation AI to estimate the user's emotions and adjust the length of the feedback based on the estimated user's emotions. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the length of the feedback. For example, if the user is feeling stressed, the generation AI can provide short, to-the-point feedback. In addition, if the user is relaxed, the generation AI can also provide detailed feedback. Furthermore, if the user is in a hurry, the generation AI can provide short, quickly understandable feedback. This makes it possible to adjust the length of the feedback according to the user's emotions.

[0102] The feedback providing unit can determine the priority of feedback based on the time when the emotion note was submitted when providing feedback. The feedback providing unit, for example, uses a generation AI to determine the priority of feedback based on the time when the emotion note was submitted when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the time of submission to determine the priority of feedback. For example, the generation AI provides feedback preferentially if the emotion note was submitted recently. Furthermore, the generation AI can also provide feedback later if the emotion note was submitted in the past. Furthermore, the generation AI can adjust the priority of feedback depending on the time when the emotion note was submitted. This makes it possible to determine the priority of feedback depending on the time when the emotion note was submitted.

[0103] The feedback providing unit can adjust the order of feedback based on the relevance of the emotion notes when providing feedback. The feedback providing unit, for example, uses a generation AI to adjust the order of feedback based on the relevance of the emotion notes when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of the emotion notes and adjusts the order of feedback. For example, the generation AI provides feedback preferentially when the emotion notes are highly relevant. Furthermore, the generation AI can also provide feedback later when the emotion notes are less relevant. Furthermore, the generation AI can adjust the order of feedback according to the relevance of the emotion notes. This makes it possible to adjust the order of feedback according to the relevance of the emotion notes.

[0104] The feedback providing unit can adjust the use of technical terms in the feedback according to the user's level of expertise when providing feedback. The feedback providing unit, for example, uses a generation AI to adjust the use of technical terms in the feedback according to the user's level of expertise when providing feedback. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's level of expertise and adjusts the use of technical terms in the feedback. For example, if the user has technical knowledge, the generation AI provides feedback using technical terms. Also, if the user does not have technical knowledge, the generation AI can provide feedback in simple language. Furthermore, the generation AI can adjust the use of technical terms in the feedback according to the user's level of expertise. This makes it possible to adjust the use of technical terms in the feedback according to the user's level of expertise.

[0105] The biometric data analysis unit can estimate the user's emotions and adjust the biometric data analysis method based on the estimated user emotions. The biometric data analysis unit, for example, uses a generation AI to estimate the user's emotions and adjust the biometric data analysis method based on the estimated user emotions. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the biometric data analysis method. For example, if the user is feeling stressed, the generation AI may focus on analyzing heart rate and blood pressure data. Also, if the user is relaxed, the generation AI may focus on analyzing breathing patterns and body temperature data. Furthermore, if the user is in a hurry, the generation AI can perform a quick analysis and provide results in a short time. This makes it possible to adjust the biometric data analysis method according to the user's emotions.

[0106] The biometric data analysis unit can improve the accuracy of the analysis by referring to the user's past biometric data history when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to improve the accuracy of the analysis by referring to the user's past biometric data history when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past biometric data history to improve the accuracy of the analysis. For example, the generation AI refers to the user's past biometric data history, identifies similar patterns, and reflects them in the analysis. The generation AI can also extract specific trigger events from the user's past biometric data history and use them in the analysis. Furthermore, the generation AI can analyze the user's past biometric data history to understand trends in health status and reflect them in the analysis. In this way, the accuracy of the analysis is improved by referring to the past biometric data history.

[0107] The biometric data analysis unit can perform the analysis by taking into account the user's current living situation and environment when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to perform the analysis by taking into account the user's current living situation and environment when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects this in the analysis of the biometric data. For example, the generation AI analyzes the biometric data by taking into account the user's current living situation (work, family, health, etc.). The generation AI can also analyze the biometric data by taking into account the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the analysis of the biometric data based on the user's current living situation and environment. This enables analysis that takes into account the user's current living situation and environment.

[0108] The biometric data analysis unit can optimize the analysis algorithm according to different types of biometric data when analyzing the biometric data. For example, the biometric data analysis unit uses a generation AI to optimize the analysis algorithm according to different types of biometric data (heart rate, body temperature, blood pressure, etc.) when analyzing the biometric data. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the type of biometric data and applies an appropriate analysis algorithm. For example, the generation AI may analyze heart rate data and evaluate stress levels. The generation AI may also analyze body temperature data and evaluate health conditions. Furthermore, the generation AI may analyze blood pressure data and evaluate cardiovascular health conditions. This makes it possible to optimize the analysis algorithm according to different types of biometric data.

[0109] The biometric data analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The biometric data analysis unit, for example, uses a generation AI to estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the display method of the analysis results. For example, if the user is feeling stressed, the generation AI may display the analysis results concisely and highlight only the important points. Alternatively, if the user is relaxed, the generation AI may display detailed analysis results and provide a detailed explanation of changes in health status. Furthermore, if the user is in a hurry, the generation AI may quickly display the analysis results so that they can be understood in a short amount of time. This makes it possible to adjust the display method of the analysis results according to the user's emotions.

[0110] The biometric data analysis unit can perform analysis taking into account the user's geographical location information when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to perform analysis taking into account the user's geographical location information when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information and reflects it in the analysis of the biometric data. For example, the generation AI obtains the user's current location and reflects health risks associated with that location in the analysis. Furthermore, when the user is in a specific location, the generation AI can also perform analysis by referring to past biometric data related to that location. Furthermore, the generation AI can customize the analysis of the biometric data based on the user's geographical location information. This makes it possible to perform analysis taking into account geographical location information.

[0111] The biometric data analysis unit can analyze the user's social media activities during biometric data analysis and reflect related information in the analysis. The biometric data analysis unit can, for example, use a generation AI to analyze the user's social media activities during biometric data analysis and reflect related information in the analysis. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activities and reflects them in the analysis of the biometric data. For example, the generation AI can analyze the content of the user's social media posts and reflect them in the analysis of the biometric data. The generation AI can also refer to the activities of the user's friends on social media and reflect them in the analysis of the biometric data. Furthermore, the generation AI can refer to the user's check-in information on social media and reflect them in the analysis of the biometric data. This makes it possible to perform an analysis that reflects social media activities.

[0112] The biometric data analysis unit can customize the analysis method by reflecting the user's past feedback when analyzing the biometric data. The biometric data analysis unit, for example, uses a generation AI to customize the analysis method by reflecting the user's past feedback when analyzing the biometric data. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the analysis method. For example, the generation AI refers to feedback provided by the user in the past and adjusts the analysis method. Furthermore, if the user's past feedback indicates that a specific analysis method is effective, the generation AI can preferentially use that method. Furthermore, the generation AI can customize the analysis method based on the user's past feedback. This makes it possible to customize the analysis method by reflecting past feedback.

[0113] The rest promotion unit can estimate the user's emotions and adjust how the system encourages rest based on the estimated user emotions. The rest promotion unit, for example, uses a generation AI to estimate the user's emotions and adjust how the system encourages rest based on the estimated user emotions. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts how the system encourages rest. For example, if the user is feeling stressed, the generation AI can suggest a rest method to help the user relax. Also, if the user is relaxed, the generation AI can suggest a rest method that explains in detail the change in emotions. Furthermore, if the user is in a hurry, the generation AI can suggest a rest method that can be implemented quickly. This makes it possible to adjust how the system encourages rest according to the user's emotions.

[0114] The rest promotion unit can adjust the level of detail of rest based on the importance of biometric data when promoting rest. The rest promotion unit, for example, uses a generation AI to adjust the level of detail of rest based on the importance of biometric data when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the importance of biometric data and adjusts the level of detail of rest. For example, the generation AI may suggest a detailed rest method when the importance of biometric data is high. The generation AI may also suggest a simple rest method when the importance of biometric data is low. Furthermore, the generation AI can adjust the level of detail of rest according to the importance of biometric data. This makes it possible to adjust the level of detail of rest according to the importance of biometric data.

[0115] The rest promotion unit can apply different rest promotion algorithms depending on the category of biometric data when promoting rest. The rest promotion unit, for example, uses a generation AI to apply different rest promotion algorithms depending on the category of biometric data when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the category of biometric data and applies an appropriate rest promotion algorithm. For example, if the biometric data is related to stress, the generation AI can suggest a rest method to reduce stress. Also, if the biometric data is related to fatigue, the generation AI can suggest a rest method to recover from fatigue. Furthermore, if the biometric data is related to maintaining health, the generation AI can suggest a rest method to maintain health. This makes it possible to apply a rest promotion algorithm depending on the category of biometric data.

[0116] The rest promotion unit can improve the accuracy of rest by referring to the user's past rest history when promoting rest. The rest promotion unit, for example, uses a generation AI to improve the accuracy of rest by referring to the user's past rest history when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past rest history to improve the accuracy of rest. For example, the generation AI can refer to the user's past rest history and suggest an optimal rest method. Furthermore, if a specific rest method is found to be effective based on the user's past rest history, the generation AI can preferentially use that method. Furthermore, the generation AI can improve the accuracy of rest based on the user's past rest history. This makes it possible to improve the accuracy of rest by referring to the past rest history.

[0117] The rest promotion unit can estimate the user's emotions and adjust the length of rest based on the estimated user emotions. The rest promotion unit, for example, uses a generation AI to estimate the user's emotions and adjust the length of rest based on the estimated user emotions. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the length of rest. For example, if the user is feeling stressed, the generation AI can suggest a short, effective method of rest. If the user is relaxed, the generation AI can also suggest a longer method of rest. Furthermore, if the user is in a hurry, the generation AI can suggest a short method of rest that can be implemented quickly. This makes it possible to adjust the length of rest according to the user's emotions.

[0118] The rest promotion unit can determine rest priorities based on the time of submission of biometric data when promoting rest. The rest promotion unit, for example, uses a generation AI to determine rest priorities based on the time of submission of biometric data when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the time of submission and determines rest priorities. For example, the generation AI may preferentially suggest rest methods if biometric data was submitted recently. Furthermore, the generation AI may postpone suggesting rest methods if biometric data was submitted in the past. Furthermore, the generation AI can adjust rest priorities based on the time of submission of biometric data. This makes it possible to determine rest priorities based on the time of submission of biometric data.

[0119] The rest promotion unit can adjust the order of rest based on the relevance of the biometric data when promoting rest. The rest promotion unit adjusts the order of rest based on the relevance of the biometric data when promoting rest, for example, using a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the relevance of the biometric data to adjust the order of rest. For example, if the biometric data is highly relevant, the generation AI can prioritize suggesting a rest method. Also, if the biometric data is less relevant, the generation AI can postpone suggesting a rest method. Furthermore, the generation AI can adjust the order of rest based on the relevance of the biometric data. This makes it possible to adjust the order of rest based on the relevance of the biometric data.

[0120] The rest promotion unit can adjust the use of rest terminology according to the user's level of expertise when promoting rest. The rest promotion unit, for example, uses a generation AI to adjust the use of rest terminology according to the user's level of expertise when promoting rest. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's level of expertise and adjusts the use of rest terminology. For example, if the user has expertise, the generation AI can suggest a rest method using technical terminology. Also, if the user does not have expertise, the generation AI can suggest a rest method in simple terms. Furthermore, the generation AI can adjust the use of rest terminology according to the user's level of expertise. This makes it possible to adjust the use of rest terminology according to the user's level of expertise.

[0121] The virtual environment providing unit can estimate the user's emotions and adjust the method of providing the virtual environment based on the estimated user emotions. The virtual environment providing unit can, for example, use a generation AI to estimate the user's emotions and adjust the method of providing the virtual environment based on the estimated user emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyze the user's emotions and adjust the method of providing the virtual environment. For example, if the user is feeling stressed, the generation AI can provide a virtual environment that helps the user relax. Furthermore, if the user is relaxed, the generation AI can also provide a virtual environment that explains changes in emotions in detail. Furthermore, if the user is in a hurry, the generation AI can provide a virtual environment that can be executed quickly. This makes it possible to adjust the method of providing the virtual environment according to the user's emotions.

[0122] The virtual environment providing unit can improve the accuracy of the virtual environment provision by referring to the user's past virtual environment usage history when providing the virtual environment. The virtual environment providing unit, for example, uses a generation AI to improve the accuracy of the virtual environment provision by referring to the user's past virtual environment usage history when providing the virtual environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past virtual environment usage history to improve the accuracy of the provision. For example, the generation AI can provide the optimal virtual environment by referring to the user's past virtual environment usage history. Furthermore, if a specific virtual environment is found to be effective based on the user's past virtual environment usage history, the generation AI can also preferentially provide that environment. Furthermore, the generation AI can improve the accuracy of the virtual environment provision based on the user's past virtual environment usage history. In this way, the accuracy of the provision is improved by referring to the past virtual environment usage history.

[0123] The virtual environment providing unit can provide the virtual environment while taking into consideration the user's current living situation and environment. The virtual environment providing unit, for example, uses a generation AI to provide the virtual environment while taking into consideration the user's current living situation and environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects them in the provision of the virtual environment. For example, the generation AI provides the virtual environment while taking into consideration the user's current living situation (work, family, health, etc.). The generation AI can also provide the virtual environment while taking into consideration the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the provision of the virtual environment based on the user's current living situation and environment. This makes it possible to provide a virtual environment that takes into consideration the user's current living situation and environment.

[0124] The virtual environment providing unit can optimize the provision algorithm according to different types of virtual environments when providing a virtual environment. For example, the virtual environment providing unit uses a generation AI to optimize the provision algorithm according to different types of virtual environments (relaxation, concentration, entertainment, etc.) when providing a virtual environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the type of virtual environment and applies an appropriate provision algorithm. For example, when providing a relaxation environment, the generation AI provides a virtual environment including calming music and scenery. Furthermore, when providing a concentration environment, the generation AI can eliminate noise to provide an environment that is easy to concentrate in. Furthermore, when providing an entertainment environment, the generation AI can provide content tailored to the user's preferences. This enables the provision algorithm to be optimized according to different types of virtual environments.

[0125] The virtual environment providing unit can estimate the user's emotions and adjust the display method of the virtual environment based on the estimated user emotions. The virtual environment providing unit can estimate the user's emotions using, for example, a generation AI and adjust the display method of the virtual environment based on the estimated user emotions. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyze the user's emotions and adjust the display method of the virtual environment. For example, if the user is feeling stressed, the generation AI can display the virtual environment using calming colors and music. Alternatively, if the user is feeling relaxed, the generation AI can display the virtual environment using detailed graphics and music. Furthermore, if the user is in a hurry, the generation AI can display a concise and quickly understandable virtual environment. This makes it possible to adjust the display method of the virtual environment according to the user's emotions.

[0126] The virtual environment providing unit can provide the virtual environment taking into account the user's geographical location information. The virtual environment providing unit, for example, uses a generation AI to provide the virtual environment taking into account the user's geographical location information. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information and reflects it in the provision of the virtual environment. For example, the generation AI obtains the user's current location and provides a virtual environment related to that location. Furthermore, if the user is in a specific location, the generation AI can also provide a virtual environment related to that location. Furthermore, the generation AI can customize the provision of the virtual environment based on the user's geographical location information. This makes it possible to provide a virtual environment that takes geographical location information into account.

[0127] The virtual environment providing unit can analyze the user's social media activity when providing the virtual environment and reflect related information in the provided environment. The virtual environment providing unit can, for example, use a generation AI to analyze the user's social media activity when providing the virtual environment and reflect related information in the provided environment. The generation AI can be a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activity and reflects it in the provided virtual environment. For example, the generation AI can analyze the content of the user's social media posts and reflect it in the provided virtual environment. The generation AI can also refer to the activity of the user's friends on social media and reflect it in the provided virtual environment. Furthermore, the generation AI can refer to the user's check-in information on social media and reflect it in the provided virtual environment. This makes it possible to provide a virtual environment that reflects social media activity.

[0128] The virtual environment providing unit can customize the method of providing a virtual environment by reflecting the user's past feedback when providing the virtual environment. The virtual environment providing unit, for example, uses a generation AI to customize the method of providing a virtual environment by reflecting the user's past feedback when providing the virtual environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the method of providing the virtual environment. For example, the generation AI refers to feedback provided by the user in the past and adjusts the method of providing the virtual environment. Furthermore, if the user's past feedback indicates that a specific virtual environment is effective, the generation AI can preferentially provide that environment. Furthermore, the generation AI can customize the method of providing the virtual environment based on the user's past feedback. This makes it possible to customize the method of providing a virtual environment by reflecting past feedback.

[0129] The social support unit can estimate the user's emotions and adjust the method of providing social support based on the estimated user emotions. The social support unit, for example, uses a generation AI to estimate the user's emotions and adjust the method of providing social support based on the estimated user emotions. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the method of providing social support. For example, if the user is feeling stressed, the generation AI can provide social support to help the user relax. Furthermore, if the user is relaxed, the generation AI can also provide social support that explains changes in emotions in detail. Furthermore, if the user is in a hurry, the generation AI can provide social support that can be implemented quickly. This makes it possible to adjust the method of providing social support according to the user's emotions.

[0130] The social support unit can improve the accuracy of social support provision by referring to the user's past social support usage history when providing social support. The social support unit, for example, uses a generation AI to improve the accuracy of social support provision by referring to the user's past social support usage history when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the past social support usage history to improve the accuracy of provision. For example, the generation AI can provide optimal social support by referring to the user's past social support usage history. Furthermore, if a specific support method is found to be effective based on the user's past social support usage history, the generation AI can preferentially provide that method. Furthermore, the generation AI can improve the accuracy of social support provision based on the user's past social support usage history. In this way, the accuracy of provision is improved by referring to the past social support usage history.

[0131] The social support unit can provide social support while taking into account the user's current living situation and environment. The social support unit, for example, uses a generation AI to provide social support while taking into account the user's current living situation and environment. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's living situation and environment and reflects this in the provision of social support. For example, the generation AI provides social support while taking into account the user's current living situation (work, family, health, etc.). The generation AI can also provide social support while taking into account the user's current environment (weather, location, time of day, etc.). Furthermore, the generation AI can customize the provision of social support based on the user's current living situation and environment. This makes it possible to provide social support while taking into account the user's current living situation and environment.

[0132] The social support unit can optimize the provision algorithm according to different types of social support when providing social support. For example, the social support unit uses a generation AI to optimize the provision algorithm according to different types of social support (anonymous, group, individual, etc.) when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the type of social support and applies an appropriate provision algorithm. For example, when providing anonymous support, the generation AI provides support while protecting the user's privacy. Furthermore, when providing group support, the generation AI can also provide support that promotes communication within the group. Furthermore, when providing individual support, the generation AI can also provide support that meets the user's individual needs. This makes it possible to optimize the provision algorithm according to different types of social support.

[0133] The social support unit can estimate the user's emotions and adjust the display method of social support based on the estimated user emotions. The social support unit, for example, uses a generation AI to estimate the user's emotions and adjust the display method of social support based on the estimated user emotions. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the user's emotions and adjusts the display method of social support. For example, if the user is feeling stressed, the generation AI can provide a concise and highly visible display method. Furthermore, if the user is relaxed, the generation AI can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the generation AI can provide a display method that focuses on the main points. This makes it possible to adjust the display method of social support according to the user's emotions.

[0134] The social support unit can provide social support while taking into account the user's geographical location information. The social support unit, for example, uses a generation AI to provide social support while taking into account the user's geographical location information. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes the geographical location information and reflects it in the provision of social support. For example, the generation AI obtains the user's current location and provides social support related to that location. Furthermore, if the user is in a specific location, the generation AI can also provide social support related to that location. Furthermore, the generation AI can customize the provision of social support based on the user's geographical location information. This makes it possible to provide social support while taking into account the geographical location information.

[0135] The social support unit can analyze the user's social media activities and reflect related information in the social support provided when providing social support. The social support unit, for example, uses a generation AI to analyze the user's social media activities and reflect related information in the social support provided when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes social media activities and reflects them in the social support provided. For example, the generation AI analyzes the content of the user's social media posts and reflects them in the social support provided. The generation AI can also refer to the activities of the user's friends on social media and reflect them in the social support provided. Furthermore, the generation AI can refer to the user's social media check-in information and reflect them in the social support provided. This makes it possible to provide social support that reflects social media activities.

[0136] The social support unit can customize the method of providing social support by reflecting the user's past feedback when providing social support. The social support unit, for example, uses a generation AI to customize the method of providing social support by reflecting the user's past feedback when providing social support. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, and analyzes past feedback to customize the method of providing social support. For example, the generation AI refers to feedback provided by the user in the past and adjusts the method of providing social support. Furthermore, if a specific method of social support is found to be effective based on the user's past feedback, the generation AI can provide that method preferentially. Furthermore, the generation AI can customize the method of providing social support based on the user's past feedback. This makes it possible to customize the method of providing social support by reflecting past feedback. === Hard Collateral 1-1 === Each of the plurality of elements including the emotion note interpretation unit, feedback provision unit, biometric data analysis unit, rest promotion unit, virtual environment provision unit, and social support unit described above is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the emotion note interpretation unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the feedback provision unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the biometric data analysis unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the rest promotion unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the virtual environment provision unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. For example, the social support unit is realized by the control unit 46A of the smart device 14 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the plurality of elements including the above-mentioned emotion note interpretation unit, feedback provision unit, biometric data analysis unit, rest promotion unit, virtual environment provision unit, and social support unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the emotion note interpretation unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the feedback provision unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the biometric data analysis unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the rest promotion unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the virtual environment provision unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. For example, the social support unit is realized by the control unit 46A of the smart glasses 214 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned emotion note interpretation unit, feedback provision unit, biometric data analysis unit, rest promotion unit, virtual environment provision unit, and social support unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the emotion note interpretation unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the feedback provision unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the biometric data analysis unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the rest promotion unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the virtual environment provision unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. For example, the social support unit is realized by the control unit 46A of the headset type terminal 314 or the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-4 === Each of the plurality of elements including the emotion note interpretation unit, feedback provision unit, biometric data analysis unit, rest promotion unit, virtual environment provision unit, and social support unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the emotion note interpretation unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the feedback provision unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the biometric data analysis unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the rest promotion unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the virtual environment provision unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12. For example, the social support unit is realized by the control unit 46A of the robot 414 or the specific processing unit 290 of the data processing device 12.

[0137] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0138] When interpreting a user's emotion note, the emotion note interpretation unit can improve the accuracy of the interpretation by referring to the user's past behavioral patterns. For example, it can analyze what emotions the user has expressed in specific situations in the past and reflect this in the interpretation of the current emotion note. It can also take into account what emotions the user tends to express at specific times or places when making an interpretation. Furthermore, it can extract specific trigger events from the user's past behavioral patterns and use them in the interpretation. In this way, by referring to past behavioral patterns, the accuracy of the interpretation can be improved.

[0139] The feedback providing unit can estimate the user's emotions and adjust the timing of the feedback based on the estimated user's emotions. For example, if the user is feeling stressed, the feedback providing unit can immediately provide feedback to help the user relax. Also, if the user is relaxed, the feedback providing unit can provide feedback that explains the change in emotions in detail. Furthermore, if the user is in a hurry, the feedback providing unit can provide feedback that can be quickly understood. This makes it possible to adjust the timing of the feedback according to the user's emotions.

[0140] The biometric data analysis unit can estimate the user's emotions and adjust the frequency of biometric data collection based on the estimated user emotions. For example, if the user is feeling stressed, heart rate and blood pressure data can be collected more frequently. If the user is relaxed, the collection frequency can be reduced. Furthermore, if the user is in a hurry, data can be collected quickly and results can be provided in a short time. This makes it possible to adjust the frequency of biometric data collection according to the user's emotions.

[0141] The rest promotion unit can estimate the user's emotions and suggest types of rest based on the estimated user emotions. For example, if the user is feeling stressed, it can suggest a rest method to relax. Also, if the user is relaxed, it can suggest a rest method that explains the change in emotions in detail. Furthermore, if the user is in a hurry, it can suggest a rest method that can be implemented quickly. This makes it possible to suggest types of rest according to the user's emotions.

[0142] The virtual environment providing unit can estimate the user's emotions and adjust the content of the virtual environment based on the estimated user's emotions. For example, if the user is feeling stressed, a virtual environment that allows the user to relax can be provided. Also, if the user is relaxed, a virtual environment that explains the change in emotions in detail can be provided. Furthermore, if the user is in a hurry, a virtual environment that can be quickly executed can be provided. This makes it possible to adjust the content of the virtual environment according to the user's emotions.

[0143] The emotion note interpretation unit can support input in different languages ​​when interpreting a user's emotion notes. For example, if a user inputs emotion notes in different languages, such as English, Spanish, and French, it will provide an interpretation that corresponds to each language. It can also use generative AI to translate between different languages ​​and provide interpretation results. Furthermore, if a user uses multiple languages, it can provide an interpretation that corresponds to each language and provide an integrated interpretation result. This improves the accuracy of interpretation by supporting input in different languages.

[0144] The feedback providing unit can refer to the user's feedback history and customize new feedback based on the content of past feedback. For example, it can analyze the content of feedback the user has received in the past and provide feedback in similar situations. It can also evaluate the effectiveness of feedback the user has received in the past and provide effective feedback preferentially. Furthermore, it can extract specific feedback patterns from the user's feedback history and reflect them in new feedback. In this way, the accuracy of feedback can be improved by referring to the past feedback history.

[0145] When analyzing a user's biometric data, the biometric data analysis unit can integrate data from different devices. For example, it can integrate biometric data collected from different devices, such as smart glasses, smart watches, and smartphones, to perform a comprehensive analysis. It can also synchronize data between different devices to provide consistent data. It can also compare data from different devices and detect outliers. This improves the accuracy of the analysis by integrating data from different devices.

[0146] The rest promotion unit can refer to the user's rest history and suggest new rest methods based on past rest methods. For example, it can evaluate the effectiveness of the user's past rest methods and prioritize suggesting effective rest methods. It can also extract specific rest patterns from the user's rest history and reflect them in new rest methods. It can also suggest individually customized rest methods based on the user's rest history. This improves the accuracy of rest methods by referring to past rest history.

[0147] The virtual environment providing unit can refer to the user's virtual environment usage history and provide a new virtual environment based on past usage. For example, it can evaluate the effectiveness of virtual environments used by the user in the past and provide effective virtual environments preferentially. It can also extract specific usage patterns from the user's virtual environment usage history and reflect them in a new virtual environment. Furthermore, it can provide an individually customized virtual environment based on the user's virtual environment usage history. This improves the accuracy of the virtual environment provided by referring to past usage history.

[0148] The processing flow of the second embodiment will be briefly explained below.

[0149] Step 1: The emotion note interpretation unit interprets the emotion note entered by the user manually on a smartphone or by voice on the smart glasses. Emotion notes can be in text, audio, or image format. The emotion note interpretation unit uses generative AI to interpret the emotion note in natural language and grasp changes in emotions. Step 2: The feedback providing unit provides feedback based on the results interpreted by the emotion note interpretation unit. The feedback may be a text message, a voice message, or visual feedback. The feedback providing unit uses a generation AI to provide appropriate feedback to the user. Step 3: The biometric data analysis unit analyzes the biometric data obtained using the smart glasses. The biometric data includes heart rate, body temperature, blood pressure, etc. The biometric data analysis unit uses generative AI to analyze the biometric data and understand the user's emotional state. Step 4: The rest promotion unit encourages the user to take a rest based on the results of the analysis by the biometric data analysis unit. Rest includes rest time, quality of rest, and rest environment. The rest promotion unit uses generation AI to encourage the user to take an appropriate rest. Step 5: The virtual environment providing unit provides a virtual environment using AR or VR technology. The virtual environment can be a relaxation environment, a concentration environment, an entertainment environment, etc. The virtual environment providing unit uses a generating AI to provide an appropriate virtual environment for the user. Step 6: The social support section facilitates connections between users and provides an anonymous and safe sharing area. Social support includes anonymous support, group support, and individual support. The social support section uses generative AI to help users connect with each other.

[0150] 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.

[0151] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] 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.

[0153] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0154] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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).

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0168] 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.

[0169] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0170] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0181] 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.

[0182] 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.

[0183] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0184] 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.

[0185] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0186] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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).

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0198] 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.

[0199] 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.

[0200] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0201] 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.

[0202] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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).

[0207] 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.

[0208] 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."

[0209] 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.

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.

[0217] 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.

[0218] 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.

[0219] 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.

[0220] 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.

[0221] [Explanation of symbols]

[0222] 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. an emotion note interpretation unit that interprets the emotion note; a feedback providing unit that provides feedback based on the result of interpretation by the emotion note interpretation unit; a biometric data analysis unit that analyzes biometric data obtained using smart glasses; a rest promotion unit that promotes rest based on the results of the analysis by the biological data analysis unit; a virtual environment providing unit that provides a virtual environment using AR or VR technology; A social support unit that facilitates connections between users. A system characterized by:

2. The emotion note interpretation unit Interprets emotion notes entered manually by the user on a smartphone or spoken via smart glasses in natural language.

2. The system of claim 1.

3. The feedback providing unit: Providing feedback based on the results interpreted by the emotion note interpretation unit 2. The system of claim 1.

4. The biological data analysis unit Analyzing biometric data obtained using smart glasses 2. The system of claim 1.

5. The rest promotion unit includes: Prompting the user to rest based on the results of the analysis by the biological data analysis unit 2. The system of claim 1.

6. The virtual environment providing unit Providing a virtual environment using AR or VR technology 2. The system of claim 1.

7. The social support department Facilitate connections between users and provide anonymous and secure sharing areas 2. The system of claim 1.

8. The emotion note interpretation unit Inferring a user's emotion and adjusting the interpretation method of emotion notes based on the estimated user's emotion 2. The system of claim 1.

Images