System

Abstract

An object of a system according to an embodiment is to appropriately grasp a user's mental state and provide a necessary program.SOLUTION: A system includes a reception part, a grasping part, a provision part, and an intervention part. The receiving unit receives a dialogue content of a user. The grasping unit analyzes the dialogue content received by the reception unit and grasps a mental condition of the user. The providing unit provides a specific program on the basis of the mental condition grasped by the grasping unit. The intervention unit performs crisis intervention based on a specific condition based on the program provided by the providing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has had the problem of making it difficult to properly grasp a user's mental state and provide the necessary programs.

[0005] The system according to the embodiment aims to properly grasp the mental state of the user and provide the necessary programs. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, a determination unit, a provision unit, and an intervention unit. The reception unit receives the content of the user's dialogue. The determination unit analyzes the content of the dialogue received by the reception unit and determines the user's mental state. The provision unit provides a specific program based on the mental state determined by the determination unit. The intervention unit performs crisis intervention based on specific conditions and the program provided by the provision unit. [Effects of the Invention]

[0007] The system according to the embodiment can appropriately grasp the mental state of the user and provide the necessary programs. [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 mental care system according to an embodiment of the present invention automatically receives a user's dialogue, analyzes it using a generation AI, understands the user's mental state, provides an appropriate program, and performs crisis intervention as needed. The mental care system receives a user's dialogue, analyzes it using a generation AI, understands the user's mental state, provides an appropriate program, and performs crisis intervention as needed. For example, in a mental care system, a user interacts with a conversational AI. For example, the user can freely talk about their feelings and situation. This dialogue content is input to the generation AI. The mental care system then uses the generation AI to analyze the input dialogue content and understand the user's mental state. The input to the generation AI is the user's dialogue content itself, and the generation AI understands the user's mental state based on that content. For example, the generation AI analyzes content such as "I've been feeling stressed lately" and understands that the user is feeling stressed. Based on the understood mental state, the generation AI then provides an appropriate program. For example, if the user is feeling stressed, the generation AI provides relaxation music or meditation guides. It can also provide advice for stress management. Next, if the user's mental condition is serious, the mental care system's generating AI will intervene in the crisis, refer the user to a specialist, or take emergency action. This allows the user to receive appropriate support quickly. This allows the mental care system to support the user's daily mental care and maintain balance. It also enables rapid response in emergencies. This allows the mental care system to automatically grasp the user's mental condition, provide appropriate programs, and intervene in the crisis as needed. For example, the user can maintain mental balance by using relaxation music or meditation guides on a daily basis. Furthermore, if the user experiences severe stress or anxiety, the generating AI will refer the user to a specialist or take emergency action, allowing the user to receive appropriate support quickly.

[0029] The mental care system according to the embodiment includes a reception unit, a comprehension unit, a provision unit, and an intervention unit. The reception unit receives the content of a user's dialogue. The content of the user's dialogue includes, but is not limited to, voice, text, and images. The reception unit receives the content of the user's dialogue using, for example, voice input. The reception unit can also receive the content of the user's dialogue using text input. The reception unit can also receive the content of the user's dialogue using image input. For example, the reception unit converts the voice input into text data using voice recognition technology. The text input can be input by a user using a keyboard or a touch screen. The image input can be input by a user taking an image using a camera and analyzing the image. The comprehension unit analyzes the content of the dialogue received by the reception unit using a generation AI to comprehend the user's mental state. Comprehension is performed using, for example, natural language processing technology, but is not limited to, an example. For example, the generation AI analyzes the content of the dialogue using a text generation AI (e.g., LLM) to comprehend the user's mental state. The comprehension unit can also analyze the content of the dialogue using a multimodal generation AI. The comprehension unit can also use the generation AI to analyze the content of the user's speech and grasp the user's mental state. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, in addition to text. The generation AI uses keyword extraction technology to pick out particularly important information from the conversation and grasp the user's mental state based on that information. The provision unit provides an appropriate program based on the mental state grasped by the comprehension unit. Examples of programs include, but are not limited to, music for relaxation, meditation guides, and advice for stress management. The provision unit can provide, for example, music for relaxation. The provision unit can also provide meditation guides. The provision unit can also provide advice for stress management. For example, the provision unit selects and provides an optimal program based on the user's mental state.The intervention unit performs crisis intervention as needed based on the program provided by the provision unit. Intervention is performed, for example, when the user's mental condition is serious, but is not limited to this example. For example, the intervention unit may refer the user to a specialist when the user's mental condition is serious. The intervention unit may also provide emergency care when the user's mental condition is serious. The intervention unit may also select and execute an appropriate intervention method depending on the user's mental condition. For example, the intervention unit may monitor the user's mental condition in real time and immediately intervene as needed. This allows the mental care system according to the embodiment to automatically grasp the user's mental condition, provide an appropriate program, and perform crisis intervention as needed. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit may input the user's mental condition into the generation AI and cause the generation AI to select an appropriate intervention method.

[0030] The providing unit can provide music for relaxation or a meditation guide. Examples of music for relaxation include, but are not limited to, classical music and natural sounds. The providing unit can provide, for example, classical music. The providing unit can also provide natural sounds. The providing unit can also select and provide music for relaxation according to the user's preferences. For example, the providing unit can automatically select and provide music that helps the user relax. Examples of meditation guides include, but are not limited to, audio guides and video guides. The providing unit can provide, for example, audio guides. The providing unit can also provide video guides. The providing unit can also select and provide an optimal meditation guide according to the user's mental state. For example, the providing unit can automatically select and provide a meditation guide that helps the user relax. By providing relaxation music or a meditation guide, the user's mind can be trained and balanced. Some or all of the above-described processing by the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the user's mental state into the generating AI and have the generating AI select music for relaxation or a meditation guide.

[0031] The providing unit can provide advice for stress management. Examples of advice for stress management include, but are not limited to, breathing techniques and time management tips. The providing unit can provide, for example, breathing techniques. The providing unit can also provide time management tips. The providing unit can also select and provide optimal stress management advice depending on the user's mental state. For example, the providing unit can automatically select and provide advice that helps the user reduce stress. In this way, by providing advice for stress management, the user's mental state can be trained and balanced. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the user's mental state into a generating AI and cause the generating AI to select advice for stress management.

[0032] The intervention unit can refer the user to a specialist if the user's mental condition exceeds a specific standard. The specific standard includes, but is not limited to, a mental health assessment score, a specialist's diagnostic criteria, and the like. For example, the intervention unit can refer the user to a specialist if the user's mental health assessment score is high. The intervention unit can also refer the user to a specialist based on the specialist's diagnostic criteria. The intervention unit can also select and refer the user to an optimal specialist depending on the user's mental condition. For example, the intervention unit can automatically select and refer the user to an expert optimal for the user's mental condition. This allows the user to receive prompt and appropriate support by referring the user to an expert if the user's mental condition is serious. Some or all of the above-described processing in the intervention unit can be performed, for example, using AI or without AI. For example, the intervention unit can input the user's mental condition into a generation AI and have the generation AI make a decision on whether to refer the user to a specialist.

[0033] The intervention unit can take emergency action when the user's mental state exceeds a specific standard. The specific standard includes, but is not limited to, a mental health assessment score, an urgency index, and the like. For example, the intervention unit can take emergency action when the mental health assessment score is high. The intervention unit can also take emergency action for the user based on the urgency index. The intervention unit can also select and execute an optimal emergency action depending on the user's mental state. For example, the intervention unit can automatically select and execute an optimal emergency action for the user's mental state. This allows the user to receive prompt and appropriate support by taking emergency action when the user's mental state is serious. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit can input the user's mental state into a generation AI and have the generation AI execute an emergency response decision.

[0034] The comprehension unit can analyze the user's utterance content using natural language processing technology to grasp the user's mental state. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the comprehension unit analyzes the user's utterance content using morphological analysis. The comprehension unit can also analyze the user's utterance content using grammatical analysis. The comprehension unit can also analyze the user's utterance content using semantic analysis. For example, the comprehension unit performs morphological analysis on the user's utterance content to analyze the meaning of each word. Grammatical analysis analyzes the structure of a sentence, and semantic analysis analyzes the meaning of the entire sentence. In this way, by using natural language processing technology, the user's utterance content can be accurately analyzed and the user's mental state can be grasped. Some or all of the above-described processing in the comprehension unit may be performed using, for example, AI, or may be performed without using AI. For example, the comprehension unit can input the user's utterance content to a generation AI and cause the generation AI to grasp the user's mental state.

[0035] The reception unit can analyze the user's past interaction history and select a specific reception method. Specific reception methods include, but are not limited to, voice reception and text reception. For example, the reception unit can prioritize and suggest a dialogue format that the user has frequently used in the past. The reception unit can also select a reception method suitable for a specific time period based on the user's past interaction history. The reception unit can also suggest the most effective reception method based on the user's past interaction history. For example, if the user has frequently used voice input in the past, the reception unit can prioritize and suggest voice reception. Text reception can be input by the user using a keyboard or touchscreen. By analyzing the user's past interaction history, the reception unit can select the optimal reception method and conduct a dialogue suitable for the user. Some or all of the above-described processing in the reception unit can be performed using, for example, AI. For example, the reception unit can input the user's past interaction history into a generation AI and have the generation AI select the optimal reception method.

[0036] The reception unit may filter the dialogue content based on the user's current living situation and areas of interest when receiving the dialogue. Examples of the current living situation include, but are not limited to, work status and family status. Examples of areas of interest include, but are not limited to, hobbies and topics of interest. For example, when the user inputs their current living situation, the reception unit filters the dialogue content based on the information. The reception unit may also preferentially receive related dialogue content based on the user's areas of interest. The reception unit may also suggest optimal dialogue content taking the user's living situation and areas of interest into consideration. For example, when the user inputs their current living situation, the reception unit filters the dialogue content based on the information. The areas of interest are selected based on the user's topics and hobbies. This allows for more relevant dialogue by filtering the dialogue content based on the user's current living situation and areas of interest. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input data on the user's living situation and areas of interest to a generation AI and cause the generation AI to filter the dialogue content.

[0037] When receiving a dialogue, the reception unit can select the optimal reception means depending on the user's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the user selects voice input, the reception unit can receive the dialogue using voice recognition technology. Furthermore, if the user selects text input, the reception unit can also receive the dialogue using text analysis technology. Furthermore, if the user selects image input, the reception unit can also receive the dialogue using image analysis technology. For example, if the user selects voice input, the reception unit converts the voice into text data using voice recognition technology. For text input, the user can input using a keyboard or a touch screen. For image input, the user can take an image using a camera and analyze the image. This allows for smoother dialogue by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's input data into a generation AI and have the generation AI select the optimal reception means.

[0038] When receiving a dialogue, the reception unit can prioritize receiving a dialogue that is highly relevant by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a specific area, the reception unit prioritizes receiving a dialogue related to that area. The reception unit can also suggest optimal dialogue content based on the user's geographical location information. The reception unit can also prioritize receiving a dialogue that is relevant based on the user's current location. For example, if the user is in a specific area, the reception unit prioritizes receiving a dialogue related to that area. The location information service acquires the user's current location in real time and filters the dialogue content based on that information. This allows for prioritized reception of a dialogue that is highly relevant by taking the user's geographical location information into account. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information to a generation AI and cause the generation AI to filter the dialogue content.

[0039] The reception unit may analyze the user's social media activity when receiving a dialogue and receive related dialogues. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and comments. For example, the reception unit may analyze the content of the user's social media posts and prioritize receiving related dialogues. The reception unit may also suggest related dialogues by referring to the activities of the user's friends on social media. The reception unit may also receive related dialogues based on the user's social media check-in information. For example, the reception unit may analyze the content of the user's social media posts and prioritize receiving related dialogues. The activities of friends are selected by referring to the posts and comments of the user's friends on social media. In this way, by analyzing the user's social media activity, related dialogues can be prioritized. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input data on the user's social media activity into a generation AI and cause the generation AI to select the content of the dialogue.

[0040] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a dialogue. Past feedback includes, but is not limited to, user ratings, comments, and survey results. For example, the reception unit can suggest an optimal reception method based on feedback previously provided by the user. The reception unit can also improve the dialogue reception procedure by reflecting the user's past feedback. The reception unit can also customize the reception method based on the user's feedback. For example, the reception unit can suggest an optimal reception method based on feedback previously provided by the user. The survey results are selected with reference to the results of surveys previously answered by the user. By doing so, a more appropriate reception method can be provided by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback into a generation AI and have the generation AI customize the reception method.

[0041] When grasping the mental state, the grasping unit can adjust the level of detail of the grasping based on the importance of the dialogue content. The importance of the dialogue content includes, but is not limited to, for example, the frequency of keyword appearances and the user's urgency. For example, in the case of important dialogue content, the grasping unit asks detailed questions to grasp the mental state in depth. Furthermore, in the case of less important dialogue content, the grasping unit can grasp the mental state with brief questions. Furthermore, the grasping unit can adjust the level of detail of the grasping based on the importance of the dialogue content. For example, in the case of important dialogue content, the grasping unit asks detailed questions to grasp the mental state in depth. The frequency of keyword appearances is evaluated based on the number of times particularly important keywords appear in the dialogue content. Thus, by adjusting the level of detail of the grasping based on the importance of the dialogue content, the mental state can be grasped efficiently. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit may input dialogue content data to a generation AI and cause the generation AI to adjust the level of detail of the grasping.

[0042] When grasping the mental state, the grasping unit can apply different analysis algorithms depending on the category of the dialogue. The dialogue categories include, but are not limited to, for example, consultation content and question content. For example, the grasping unit applies a stress analysis algorithm to a dialogue about stress management. Furthermore, the grasping unit can also apply a relaxation analysis algorithm to a dialogue about relaxation. Furthermore, the grasping unit can also apply a mental health analysis algorithm to a dialogue about mental health. For example, the grasping unit applies a stress analysis algorithm to a dialogue about stress management. The consultation content is categorized based on the content the user wants to discuss. Applying different analysis algorithms depending on the category of the dialogue enables a more accurate grasping of the mental state. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit can input dialogue category data to a generation AI and cause the generation AI to apply an analysis algorithm.

[0043] When assessing the mental state, the assessment unit can improve the accuracy of assessment by referring to the user's past dialogue results. Past dialogue results include, but are not limited to, for example, a dialogue history and user feedback. The assessment unit, for example, improves the accuracy of assessment of the mental state based on the user's past dialogue results. The assessment unit can also select optimal questions by referring to the user's past dialogue results. The assessment unit can also analyze the user's past dialogue results to improve the accuracy of assessment of the mental state. For example, the assessment unit improves the accuracy of assessment of the mental state based on the user's past dialogue results. The dialogue history is evaluated based on the content of dialogues the user had in the past. In this way, by referring to the user's past dialogue results, the accuracy of assessment of the mental state can be improved. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without using AI. For example, the assessment unit can input the user's past dialogue results into the generation AI and cause the generation AI to improve the accuracy of assessment.

[0044] When grasping the mental state, the grasping unit can determine the priority of grasping based on the time of submission of the dialogue. The submission time includes, for example, a timestamp of the dialogue, a submission date and time, etc., but is not limited to these examples. For example, the grasping unit prioritizes grasping the content of the most recent dialogue. The grasping unit can also postpone dialogue content submitted earlier. The grasping unit can also determine the priority of grasping the mental state based on the time of submission. For example, the grasping unit prioritizes grasping the content of the most recent dialogue. The timestamp is evaluated based on the date and time the dialogue was conducted. In this way, by determining the priority of grasping based on the time of submission of the dialogue, it is possible to prioritize grasping more important dialogues. Some or all of the above-mentioned processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit can input dialogue submission date data to the generation AI and cause the generation AI to determine the priority of grasping.

[0045] When grasping the mental state, the grasping unit can adjust the order of grasping based on the relevance of the dialogue. The relevance of the dialogue includes, but is not limited to, for example, the co-occurrence of keywords and the similarity of topics. For example, the grasping unit prioritizes grasping highly relevant dialogue content. The grasping unit can also postpone less relevant dialogue content. The grasping unit can also adjust the order of grasping the mental state based on the relevance of the dialogue. For example, the grasping unit prioritizes grasping highly relevant dialogue content. The co-occurrence of keywords is evaluated based on the number of co-occurrences of particularly important keywords in the dialogue content. In this way, by adjusting the order of grasping based on the relevance of the dialogue, more relevant dialogues can be prioritized for grasping. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit can input dialogue relevance data to the generation AI and cause the generation AI to adjust the order of grasping.

[0046] When assessing the mental state, the assessment unit can adjust the use of technical terms in the analysis according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the user's occupation, educational background, and past conversations. For example, if the user has specialized knowledge, the assessment unit can perform the analysis using technical terms. Furthermore, if the user does not have specialized knowledge, the assessment unit can also perform the analysis using simple language. Furthermore, the assessment unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has specialized knowledge, the assessment unit can perform the analysis using technical terms. The occupation is evaluated based on the user's occupation. By adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without AI. For example, the assessment unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0047] When providing a program, the providing unit can adjust the level of detail of the program based on the importance of the mental state. The importance of the mental state includes, but is not limited to, stress level, emotional state, etc. For example, the providing unit provides a detailed program when the mental state is important. The providing unit can also provide a concise program when the mental state is less important. The providing unit can also adjust the level of detail of the program based on the importance of the mental state. For example, the providing unit provides a detailed program when the mental state is important. The stress level is evaluated based on the user's stress level. This allows for a more appropriate program to be provided by adjusting the level of detail of the program based on the importance of the mental state. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input mental state data into a generation AI and cause the generation AI to adjust the level of detail of the program.

[0048] When providing a program, the providing unit can apply different providing algorithms depending on the category of the mental condition. Examples of mental condition categories include, but are not limited to, stress, depression, and anxiety. For example, in the case of a program related to stress management, the providing unit can apply a stress management algorithm. Furthermore, in the case of a program related to relaxation, the providing unit can also apply a relaxation algorithm. Furthermore, in the case of a program related to mental health, the providing unit can also apply a mental health algorithm. For example, in the case of a program related to stress management, the providing unit can apply a stress management algorithm. Depression is classified based on the user's mental condition. This allows for the provision of a more appropriate program by applying different providing algorithms depending on the category of the mental condition. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input mental condition category data into the generating AI and cause the generating AI to apply the providing algorithm.

[0049] When providing a program, the providing unit can improve the accuracy of the program provision by referring to the user's past program results. Past program results include, but are not limited to, for example, the program's effectiveness and user feedback. For example, the providing unit provides an optimal program based on the user's past program results. The providing unit can also improve the accuracy of the program provision by referring to the user's past program results. The providing unit can also analyze the user's past program results and suggest an optimal program. For example, the providing unit provides an optimal program based on the user's past program results. The effectiveness of the program is evaluated based on the effectiveness of programs the user has previously received. This allows the accuracy of the program provision to be improved by referring to the user's past program results. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the user's past program results into the generation AI and cause the generation AI to improve the accuracy of the program provision.

[0050] When providing a program, the providing unit can determine the priority of providing the program based on the time of submission of the mental state. The submission time includes, but is not limited to, for example, a timestamp of the dialogue, a submission date and time, etc. The providing unit can, for example, provide the program preferentially based on the most recent mental state. The providing unit can also postpone mental states submitted earlier. The providing unit can also determine the priority of providing the program based on the time of submission. For example, the providing unit can provide the program preferentially based on the most recent mental state. The timestamp is evaluated based on the date and time of the dialogue. In this way, by determining the priority of providing the program based on the time of submission of the mental state, more important programs can be provided preferentially. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input data on the time of submission of the mental state to the generation AI and cause the generation AI to determine the priority of providing the program.

[0051] When providing programs, the providing unit can adjust the order of program provision based on the relevance of mental states. Examples of relevance of mental states include, but are not limited to, keyword co-occurrence and topic similarity. For example, the providing unit can prioritize providing programs based on highly relevant mental states. The providing unit can also postpone less relevant mental states. The providing unit can also adjust the order of program provision based on the relevance of mental states. For example, the providing unit prioritizes providing programs based on highly relevant mental states. Keyword co-occurrence is evaluated based on the number of co-occurrences of particularly important keywords among mental states. In this way, by adjusting the order of program provision based on the relevance of mental states, more relevant programs can be provided preferentially. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input mental state relevance data to a generation AI and cause the generation AI to adjust the order of program provision.

[0052] When providing a program, the providing unit can adjust the use of technical terms in the program according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the user's occupation, educational background, and past conversations. For example, if the user has specialized knowledge, the providing unit can provide the program using technical terms. Furthermore, if the user does not have specialized knowledge, the providing unit can also provide the program in simple language. Furthermore, the providing unit can adjust the use of technical terms in the program according to the user's level of expertise. For example, if the user has specialized knowledge, the providing unit can provide the program using technical terms. The user's level of expertise is evaluated based on the user's occupation. This allows the program to be more easily understood by adjusting the use of technical terms in the program according to the user's level of expertise. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or without AI. For example, the providing unit can input the user's level of expertise data into a generation AI and cause the generation AI to adjust the use of technical terms.

[0053] When intervening, the intervention unit can analyze the user's past mental state and select the optimal intervention method. Past mental states include, but are not limited to, past diagnosis results, dialogue history, etc. The intervention unit selects the optimal intervention method based on, for example, the user's past mental state. The intervention unit can also analyze the user's past mental state and propose an effective intervention method. The intervention unit can also customize the intervention method by referring to the user's past mental state. For example, the intervention unit selects the optimal intervention method based on the user's past mental state. The diagnosis results are evaluated based on the results of diagnoses the user has received in the past. This allows the analysis of the user's past mental state to select the optimal intervention method and provide more effective intervention. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit can input the user's past mental state data into the generation AI and have the generation AI select the intervention method.

[0054] During intervention, the intervention unit can customize the intervention measures based on the user's current living situation. Examples of the current living situation include, but are not limited to, work and home situations. For example, the intervention unit can propose optimal intervention measures by taking the user's current living situation into consideration. The intervention unit can also customize the intervention measures based on the user's living situation. The intervention unit can also provide effective intervention measures by reflecting the user's living situation. For example, the intervention unit proposes optimal intervention measures by taking the user's current living situation into consideration. The work situation is evaluated based on the user's work situation. This allows for more appropriate intervention by customizing the intervention measures based on the user's current living situation. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without using AI. For example, the intervention unit can input the user's living situation data into a generation AI and cause the generation AI to customize the intervention measures.

[0055] During intervention, the intervention unit can improve the intervention method by reflecting user feedback. Feedback includes, but is not limited to, user ratings, comments, and survey results. For example, the intervention unit improves the intervention method based on user feedback. The intervention unit can also propose an optimal intervention method by reflecting user feedback. The intervention unit can also customize the intervention method by referring to user feedback. For example, the intervention unit improves the intervention method based on user feedback. Survey results are selected by referring to results of surveys previously answered by the user. By doing so, the intervention method can be improved and more effective intervention can be performed by reflecting user feedback. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or without AI. For example, the intervention unit can input user feedback data into a generation AI and cause the generation AI to improve the intervention method.

[0056] When intervening, the intervention unit can select an optimal intervention method by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, the intervention unit can propose an optimal intervention method based on the user's geographical location information. The intervention unit can also provide relevant intervention methods based on the user's current location. The intervention unit can also select an effective intervention method by taking into account the user's geographical location information. For example, the intervention unit proposes an optimal intervention method based on the user's geographical location information. The location information service acquires the user's current location in real time and selects an intervention method based on that information. This allows the optimal intervention method to be selected by taking into account the user's geographical location information, resulting in more effective intervention. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit can input the user's geographical location information into the generation AI and cause the generation AI to select an intervention method.

[0057] During intervention, the intervention unit can analyze the user's social media activity and suggest intervention measures. Social media activity includes, but is not limited to, post content, the number of likes, and comments. For example, the intervention unit can analyze the user's social media posts and suggest relevant intervention measures. The intervention unit can also provide effective intervention measures by referring to the activities of the user's friends on social media. The intervention unit can also suggest optimal intervention methods based on the user's social media check-in information. For example, the intervention unit can analyze the user's social media posts and suggest relevant intervention measures. The friend's activities are selected by referring to the posts and comments of the user's friends on social media. By analyzing the user's social media activity, relevant intervention measures can be suggested, enabling more effective intervention. Some or all of the above-described processing in the intervention unit can be performed, for example, using AI or without AI. For example, the intervention unit can input data on the user's social media activity into a generation AI and have the generation AI execute the suggested intervention measures.

[0058] During intervention, the intervention unit can customize the intervention method by reflecting the user's past feedback. Past feedback includes, but is not limited to, user ratings, comments, and survey results. For example, the intervention unit can propose an optimal intervention method based on the user's past feedback. The intervention unit can also customize the intervention method by reflecting the user's past feedback. The intervention unit can also provide effective intervention measures by referring to the user's feedback. For example, the intervention unit proposes an optimal intervention method based on the user's past feedback. The survey results are selected by referring to the results of surveys previously answered by the user. By doing so, the intervention method can be customized by reflecting the user's past feedback, enabling more effective intervention. Some or all of the above-described processing in the intervention unit may be performed, for example, using AI or without AI. For example, the intervention unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the intervention method.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] When receiving the user's dialogue content, the reception unit can monitor the user's current activity status in real time and determine the appropriate timing for the dialogue. For example, if the user is exercising, the reception unit can temporarily suspend the dialogue and resume it after the exercise is finished. Also, if the user is in a meeting, the reception unit can suspend the dialogue until the meeting ends. Furthermore, it can detect the time period when the user is relaxing and start the dialogue during that time period. This makes it possible to provide more effective mental care by adjusting the timing of the dialogue according to the user's activity status.

[0061] The provider can provide a customized fitness program based on the user's mental state. For example, if the user is feeling stressed, the provider can provide a yoga or stretching program to relieve stress. If the user feels a lack of energy, the provider can also provide an aerobic exercise program to increase energy. Furthermore, if the user is seeking relaxation, the provider can also provide a breathing exercise or meditation program for relaxation. In this way, by providing a fitness program that suits the user's mental state, it is possible to support both the mental and physical aspects of the user.

[0062] When analyzing the content of a user's dialogue, the comprehension unit can adjust the analysis method taking into account the user's cultural background and language differences. For example, if users have different cultural backgrounds, the analysis can take into account expressions and phrases specific to those cultures. Also, if a user speaks multiple languages, the comprehension unit can apply analysis algorithms compatible with those languages. Furthermore, it can select an appropriate mental care approach based on the user's cultural background. This makes it possible to more accurately comprehend the mental state by taking into account the user's cultural background and language differences.

[0063] When analyzing the content of a user's dialogue, the comprehension unit can adjust the analysis method by taking into account the user's lifestyle habits and daily behavior patterns. For example, if the user is a nocturnal person, the analysis can be performed taking into account the mental state specific to that time of day. Also, if the user exercises regularly, the analysis can take into account the effects of that exercise. Furthermore, if the user has specific eating habits, the analysis can take into account the effects of those meals. This makes it possible to more accurately comprehend the mental state by taking into account the user's lifestyle habits and behavior patterns.

[0064] When analyzing the content of a user's dialogue, the comprehension unit can adjust the analysis method by taking into account the user's hobbies and interests. For example, if the user is interested in music, the analysis can be performed by placing emphasis on dialogue related to that music. If the user is interested in sports, the analysis can be performed by placing emphasis on dialogue related to that sport. Furthermore, if the user is interested in reading, the analysis can be performed by placing emphasis on dialogue related to reading. In this way, by taking the user's hobbies and interests into consideration, it is possible to more accurately grasp the mental state.

[0065] The processing flow of the first embodiment will be briefly explained below.

[0066] Step 1: The reception unit receives the user's dialogue content. The user's dialogue content includes voice, text, images, etc. For example, the reception unit receives the user's dialogue content using voice input and converts the voice input into text data using voice recognition technology. The user can input text using a keyboard or touch screen, and the user can input images using a camera and analyze the images. Step 2: The understanding unit uses the generation AI to analyze the dialogue content received by the reception unit and understand the user's mental state. For example, the dialogue content is analyzed using natural language processing technology, and the user's utterances are analyzed using a text generation AI (e.g., LLM) or a multimodal generation AI. The generation AI uses keyword extraction technology to pick out particularly important information from the dialogue content and understand the user's mental state based on that information. Step 3: The provider provides an appropriate program based on the mental state grasped by the grasper. The program may include music for relaxation, guided meditation, and advice on stress management. The provider selects and provides the optimal program according to the user's mental state. Step 4: The intervention unit performs crisis intervention as needed based on the program provided by the provider unit. For example, if the user's mental condition is serious, the intervention unit may refer the user to a specialist or provide emergency care. The intervention unit monitors the user's mental condition in real time and can intervene immediately if needed.

[0067] (Example 2) A mental care system according to an embodiment of the present invention automatically receives a user's dialogue, analyzes it using a generation AI, understands the user's mental state, provides an appropriate program, and performs crisis intervention as needed. The mental care system receives a user's dialogue, analyzes it using a generation AI, understands the user's mental state, provides an appropriate program, and performs crisis intervention as needed. For example, in a mental care system, a user interacts with a conversational AI. For example, the user can freely talk about their feelings and situation. This dialogue content is input to the generation AI. The mental care system then uses the generation AI to analyze the input dialogue content and understand the user's mental state. The input to the generation AI is the user's dialogue content itself, and the generation AI understands the user's mental state based on that content. For example, the generation AI analyzes content such as "I've been feeling stressed lately" and understands that the user is feeling stressed. Based on the understood mental state, the generation AI then provides an appropriate program. For example, if the user is feeling stressed, the generation AI provides relaxation music or meditation guides. It can also provide advice for stress management. Next, if the user's mental condition is serious, the mental care system's generating AI will intervene in the crisis, refer the user to a specialist, or take emergency action. This allows the user to receive appropriate support quickly. This allows the mental care system to support the user's daily mental care and maintain balance. It also enables rapid response in emergencies. This allows the mental care system to automatically grasp the user's mental condition, provide appropriate programs, and intervene in the crisis as needed. For example, the user can maintain mental balance by using relaxation music or meditation guides on a daily basis. Furthermore, if the user experiences severe stress or anxiety, the generating AI will refer the user to a specialist or take emergency action, allowing the user to receive appropriate support quickly.

[0068] The mental care system according to the embodiment includes a reception unit, a comprehension unit, a provision unit, and an intervention unit. The reception unit receives the content of a user's dialogue. The content of the user's dialogue includes, but is not limited to, voice, text, and images. The reception unit receives the content of the user's dialogue using, for example, voice input. The reception unit can also receive the content of the user's dialogue using text input. The reception unit can also receive the content of the user's dialogue using image input. For example, the reception unit converts the voice input into text data using voice recognition technology. The text input can be input by a user using a keyboard or a touch screen. The image input can be input by a user taking an image using a camera and analyzing the image. The comprehension unit analyzes the content of the dialogue received by the reception unit using a generation AI to comprehend the user's mental state. Comprehension is performed using, for example, natural language processing technology, but is not limited to, an example. For example, the generation AI analyzes the content of the dialogue using a text generation AI (e.g., LLM) to comprehend the user's mental state. The comprehension unit can also analyze the content of the dialogue using a multimodal generation AI. The comprehension unit can also use the generation AI to analyze the content of the user's speech and grasp the user's mental state. For example, the text generation AI has learned a large amount of text data and has advanced natural language processing capabilities. The multimodal generation AI can handle multiple modalities, such as images and audio, in addition to text. The generation AI uses keyword extraction technology to pick out particularly important information from the conversation and grasp the user's mental state based on that information. The provision unit provides an appropriate program based on the mental state grasped by the comprehension unit. Examples of programs include, but are not limited to, music for relaxation, meditation guides, and advice for stress management. The provision unit can provide, for example, music for relaxation. The provision unit can also provide meditation guides. The provision unit can also provide advice for stress management. For example, the provision unit selects and provides an optimal program based on the user's mental state.The intervention unit performs crisis intervention as needed based on the program provided by the provision unit. Intervention is performed, for example, when the user's mental condition is serious, but is not limited to this example. For example, the intervention unit may refer the user to a specialist when the user's mental condition is serious. The intervention unit may also provide emergency care when the user's mental condition is serious. The intervention unit may also select and execute an appropriate intervention method depending on the user's mental condition. For example, the intervention unit may monitor the user's mental condition in real time and immediately intervene as needed. This allows the mental care system according to the embodiment to automatically grasp the user's mental condition, provide an appropriate program, and perform crisis intervention as needed. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit may input the user's mental condition into the generation AI and cause the generation AI to select an appropriate intervention method.

[0069] The providing unit can provide music for relaxation or a meditation guide. Examples of music for relaxation include, but are not limited to, classical music and natural sounds. The providing unit can provide, for example, classical music. The providing unit can also provide natural sounds. The providing unit can also select and provide music for relaxation according to the user's preferences. For example, the providing unit can automatically select and provide music that helps the user relax. Examples of meditation guides include, but are not limited to, audio guides and video guides. The providing unit can provide, for example, audio guides. The providing unit can also provide video guides. The providing unit can also select and provide an optimal meditation guide according to the user's mental state. For example, the providing unit can automatically select and provide a meditation guide that helps the user relax. By providing relaxation music or a meditation guide, the user's mind can be trained and balanced. Some or all of the above-described processing by the providing unit can be performed, for example, using AI or without AI. For example, the providing unit can input the user's mental state into the generating AI and have the generating AI select music for relaxation or a meditation guide.

[0070] The providing unit can provide advice for stress management. Examples of advice for stress management include, but are not limited to, breathing techniques and time management tips. The providing unit can provide, for example, breathing techniques. The providing unit can also provide time management tips. The providing unit can also select and provide optimal stress management advice depending on the user's mental state. For example, the providing unit can automatically select and provide advice that helps the user reduce stress. In this way, by providing advice for stress management, the user's mental state can be trained and balanced. Some or all of the above-described processing by the providing unit can be performed using, for example, AI, or can be performed without using AI. For example, the providing unit can input the user's mental state into a generating AI and cause the generating AI to select advice for stress management.

[0071] The intervention unit can refer the user to a specialist if the user's mental condition exceeds a specific standard. The specific standard includes, but is not limited to, a mental health assessment score, a specialist's diagnostic criteria, and the like. For example, the intervention unit can refer the user to a specialist if the user's mental health assessment score is high. The intervention unit can also refer the user to a specialist based on the specialist's diagnostic criteria. The intervention unit can also select and refer the user to an optimal specialist depending on the user's mental condition. For example, the intervention unit can automatically select and refer the user to an expert optimal for the user's mental condition. This allows the user to receive prompt and appropriate support by referring the user to an expert if the user's mental condition is serious. Some or all of the above-described processing in the intervention unit can be performed, for example, using AI or without AI. For example, the intervention unit can input the user's mental condition into a generation AI and have the generation AI make a decision on whether to refer the user to a specialist.

[0072] The intervention unit can take emergency action when the user's mental state exceeds a specific standard. The specific standard includes, but is not limited to, a mental health assessment score, an urgency index, and the like. For example, the intervention unit can take emergency action when the mental health assessment score is high. The intervention unit can also take emergency action for the user based on the urgency index. The intervention unit can also select and execute an optimal emergency action depending on the user's mental state. For example, the intervention unit can automatically select and execute an optimal emergency action for the user's mental state. This allows the user to receive prompt and appropriate support by taking emergency action when the user's mental state is serious. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit can input the user's mental state into a generation AI and have the generation AI execute an emergency response decision.

[0073] The comprehension unit can analyze the user's utterance content using natural language processing technology to grasp the user's mental state. Natural language processing technology includes, but is not limited to, morphological analysis, grammatical analysis, and semantic analysis. For example, the comprehension unit analyzes the user's utterance content using morphological analysis. The comprehension unit can also analyze the user's utterance content using grammatical analysis. The comprehension unit can also analyze the user's utterance content using semantic analysis. For example, the comprehension unit performs morphological analysis on the user's utterance content to analyze the meaning of each word. Grammatical analysis analyzes the structure of a sentence, and semantic analysis analyzes the meaning of the entire sentence. In this way, by using natural language processing technology, the user's utterance content can be accurately analyzed and the user's mental state can be grasped. Some or all of the above-described processing in the comprehension unit may be performed using, for example, AI, or may be performed without using AI. For example, the comprehension unit can input the user's utterance content to a generation AI and cause the generation AI to grasp the user's mental state.

[0074] The reception unit can estimate the user's emotion and adjust the timing of accepting dialogue based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. The reception unit can estimate the user's emotion using, for example, voice analysis. The reception unit can also estimate the user's emotion using facial expression recognition. The reception unit can also estimate the user's emotion using text analysis. For example, the reception unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's speech and estimates the emotion. This allows the dialogue to be held at a more appropriate timing by adjusting the timing of accepting dialogue according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input user emotion data to the generation AI and cause the generation AI to adjust the timing of receiving the dialogue.

[0075] The reception unit can analyze the user's past interaction history and select a specific reception method. Specific reception methods include, but are not limited to, voice reception and text reception. For example, the reception unit can prioritize and suggest a dialogue format that the user has frequently used in the past. The reception unit can also select a reception method suitable for a specific time period based on the user's past interaction history. The reception unit can also suggest the most effective reception method based on the user's past interaction history. For example, if the user has frequently used voice input in the past, the reception unit can prioritize and suggest voice reception. Text reception can be input by the user using a keyboard or touchscreen. By analyzing the user's past interaction history, the reception unit can select the optimal reception method and conduct a dialogue suitable for the user. Some or all of the above-described processing in the reception unit can be performed using, for example, AI. For example, the reception unit can input the user's past interaction history into a generation AI and have the generation AI select the optimal reception method.

[0076] The reception unit may filter the dialogue content based on the user's current living situation and areas of interest when receiving the dialogue. Examples of the current living situation include, but are not limited to, work status and family status. Examples of areas of interest include, but are not limited to, hobbies and topics of interest. For example, when the user inputs their current living situation, the reception unit filters the dialogue content based on the information. The reception unit may also preferentially receive related dialogue content based on the user's areas of interest. The reception unit may also suggest optimal dialogue content taking the user's living situation and areas of interest into consideration. For example, when the user inputs their current living situation, the reception unit filters the dialogue content based on the information. The areas of interest are selected based on the user's topics and hobbies. This allows for more relevant dialogue by filtering the dialogue content based on the user's current living situation and areas of interest. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit may input data on the user's living situation and areas of interest to a generation AI and cause the generation AI to filter the dialogue content.

[0077] When receiving a dialogue, the reception unit can select the optimal reception means depending on the user's input method. Examples of input methods include, but are not limited to, voice input, text input, and image input. For example, if the user selects voice input, the reception unit can receive the dialogue using voice recognition technology. Furthermore, if the user selects text input, the reception unit can also receive the dialogue using text analysis technology. Furthermore, if the user selects image input, the reception unit can also receive the dialogue using image analysis technology. For example, if the user selects voice input, the reception unit converts the voice into text data using voice recognition technology. For text input, the user can input using a keyboard or a touch screen. For image input, the user can take an image using a camera and analyze the image. This allows for smoother dialogue by selecting the optimal reception means depending on the user's input method. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without AI. For example, the reception unit can input the user's input data into a generation AI and have the generation AI select the optimal reception means.

[0078] The reception unit can estimate the user's emotion and determine the priority of dialogues to be received based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. The reception unit can estimate the user's emotion using, for example, voice analysis. The reception unit can also estimate the user's emotion using facial expression recognition. The reception unit can also estimate the user's emotion using text analysis. For example, the reception unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's utterances and estimates the emotion. This allows for more appropriate dialogue by determining the priority of dialogues based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input user emotion data to the generation AI and have the generation AI determine the priority of the dialogue.

[0079] When receiving a dialogue, the reception unit can prioritize receiving a dialogue that is highly relevant by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, if the user is in a specific area, the reception unit prioritizes receiving a dialogue related to that area. The reception unit can also suggest optimal dialogue content based on the user's geographical location information. The reception unit can also prioritize receiving a dialogue that is relevant based on the user's current location. For example, if the user is in a specific area, the reception unit prioritizes receiving a dialogue related to that area. The location information service acquires the user's current location in real time and filters the dialogue content based on that information. This allows for prioritized reception of a dialogue that is highly relevant by taking the user's geographical location information into account. Some or all of the above-described processing by the reception unit may be performed using, or without, AI. For example, the reception unit can input the user's geographical location information to a generation AI and cause the generation AI to filter the dialogue content.

[0080] The reception unit may analyze the user's social media activity when receiving a dialogue and receive related dialogues. Social media activity includes, but is not limited to, for example, the content of posts, the number of likes, and comments. For example, the reception unit may analyze the content of the user's social media posts and prioritize receiving related dialogues. The reception unit may also suggest related dialogues by referring to the activities of the user's friends on social media. The reception unit may also receive related dialogues based on the user's social media check-in information. For example, the reception unit may analyze the content of the user's social media posts and prioritize receiving related dialogues. The activities of friends are selected by referring to the posts and comments of the user's friends on social media. In this way, by analyzing the user's social media activity, related dialogues can be prioritized. Some or all of the above-described processing by the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit may input data on the user's social media activity into a generation AI and cause the generation AI to select the content of the dialogue.

[0081] The reception unit can customize the reception method by reflecting the user's past feedback when receiving a dialogue. Past feedback includes, but is not limited to, user ratings, comments, and survey results. For example, the reception unit can suggest an optimal reception method based on feedback previously provided by the user. The reception unit can also improve the dialogue reception procedure by reflecting the user's past feedback. The reception unit can also customize the reception method based on the user's feedback. For example, the reception unit can suggest an optimal reception method based on feedback previously provided by the user. The survey results are selected with reference to the results of surveys previously answered by the user. By doing so, a more appropriate reception method can be provided by reflecting the user's past feedback. Some or all of the above-described processing in the reception unit may be performed using, for example, AI, or may be performed without using AI. For example, the reception unit can input the user's past feedback into a generation AI and have the generation AI customize the reception method.

[0082] The assessment unit can estimate the user's emotion and adjust the method for assessing the mental state based on the estimated user emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. For example, the assessment unit estimates the user's emotion using voice analysis. The assessment unit can also estimate the user's emotion using facial expression recognition. The assessment unit can also estimate the user's emotion using text analysis. For example, the assessment unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's speech and estimates the emotion. This enables more accurate assessment of the mental state by adjusting the method for assessing the user's mental state based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without using AI. For example, the assessment unit may input the user's emotional data into the generation AI and cause the generation AI to adjust the method of assessing the mental state.

[0083] When grasping the mental state, the grasping unit can adjust the level of detail of the grasping based on the importance of the dialogue content. The importance of the dialogue content includes, but is not limited to, for example, the frequency of keyword appearances and the user's urgency. For example, in the case of important dialogue content, the grasping unit asks detailed questions to grasp the mental state in depth. Furthermore, in the case of less important dialogue content, the grasping unit can grasp the mental state with brief questions. Furthermore, the grasping unit can adjust the level of detail of the grasping based on the importance of the dialogue content. For example, in the case of important dialogue content, the grasping unit asks detailed questions to grasp the mental state in depth. The frequency of keyword appearances is evaluated based on the number of times particularly important keywords appear in the dialogue content. Thus, by adjusting the level of detail of the grasping based on the importance of the dialogue content, the mental state can be grasped efficiently. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit may input dialogue content data to a generation AI and cause the generation AI to adjust the level of detail of the grasping.

[0084] When grasping the mental state, the grasping unit can apply different analysis algorithms depending on the category of the dialogue. The dialogue categories include, but are not limited to, for example, consultation content and question content. For example, the grasping unit applies a stress analysis algorithm to a dialogue about stress management. Furthermore, the grasping unit can also apply a relaxation analysis algorithm to a dialogue about relaxation. Furthermore, the grasping unit can also apply a mental health analysis algorithm to a dialogue about mental health. For example, the grasping unit applies a stress analysis algorithm to a dialogue about stress management. The consultation content is categorized based on the content the user wants to discuss. Applying different analysis algorithms depending on the category of the dialogue enables a more accurate grasping of the mental state. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit can input dialogue category data to a generation AI and cause the generation AI to apply an analysis algorithm.

[0085] When assessing the mental state, the assessment unit can improve the accuracy of assessment by referring to the user's past dialogue results. Past dialogue results include, but are not limited to, for example, a dialogue history and user feedback. The assessment unit, for example, improves the accuracy of assessment of the mental state based on the user's past dialogue results. The assessment unit can also select optimal questions by referring to the user's past dialogue results. The assessment unit can also analyze the user's past dialogue results to improve the accuracy of assessment of the mental state. For example, the assessment unit improves the accuracy of assessment of the mental state based on the user's past dialogue results. The dialogue history is evaluated based on the content of dialogues the user had in the past. In this way, by referring to the user's past dialogue results, the accuracy of assessment of the mental state can be improved. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without using AI. For example, the assessment unit can input the user's past dialogue results into the generation AI and cause the generation AI to improve the accuracy of assessment.

[0086] The grasping unit can estimate the user's emotion and adjust the length of grasping the mental state based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. For example, the grasping unit estimates the user's emotion using voice analysis. The grasping unit can also estimate the user's emotion using facial expression recognition. The grasping unit can also estimate the user's emotion using text analysis. For example, the grasping unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's speech and estimates the emotion. This allows the mental state to be grasped in a more appropriate amount of time by adjusting the length of grasping the mental state based on the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit may input the user's emotional data into the generating AI and cause the generating AI to adjust the length of grasping of the mental state.

[0087] When grasping the mental state, the grasping unit can determine the priority of grasping based on the time of submission of the dialogue. The submission time includes, for example, a timestamp of the dialogue, a submission date and time, etc., but is not limited to these examples. For example, the grasping unit prioritizes grasping the content of the most recent dialogue. The grasping unit can also postpone dialogue content submitted earlier. The grasping unit can also determine the priority of grasping the mental state based on the time of submission. For example, the grasping unit prioritizes grasping the content of the most recent dialogue. The timestamp is evaluated based on the date and time the dialogue was conducted. In this way, by determining the priority of grasping based on the time of submission of the dialogue, it is possible to prioritize grasping more important dialogues. Some or all of the above-mentioned processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit can input dialogue submission date data to the generation AI and cause the generation AI to determine the priority of grasping.

[0088] When grasping the mental state, the grasping unit can adjust the order of grasping based on the relevance of the dialogue. The relevance of the dialogue includes, but is not limited to, for example, the co-occurrence of keywords and the similarity of topics. For example, the grasping unit prioritizes grasping highly relevant dialogue content. The grasping unit can also postpone less relevant dialogue content. The grasping unit can also adjust the order of grasping the mental state based on the relevance of the dialogue. For example, the grasping unit prioritizes grasping highly relevant dialogue content. The co-occurrence of keywords is evaluated based on the number of co-occurrences of particularly important keywords in the dialogue content. In this way, by adjusting the order of grasping based on the relevance of the dialogue, more relevant dialogues can be prioritized for grasping. Some or all of the above-described processing in the grasping unit may be performed using, for example, AI, or may be performed without using AI. For example, the grasping unit can input dialogue relevance data to the generation AI and cause the generation AI to adjust the order of grasping.

[0089] When assessing the mental state, the assessment unit can adjust the use of technical terms in the analysis according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the user's occupation, educational background, and past conversations. For example, if the user has specialized knowledge, the assessment unit can perform the analysis using technical terms. Furthermore, if the user does not have specialized knowledge, the assessment unit can also perform the analysis using simple language. Furthermore, the assessment unit can adjust the use of technical terms in the analysis according to the user's level of expertise. For example, if the user has specialized knowledge, the assessment unit can perform the analysis using technical terms. The occupation is evaluated based on the user's occupation. By adjusting the use of technical terms in the analysis according to the user's level of expertise, it is possible to provide analysis results that are easier to understand. Some or all of the above-described processing in the assessment unit may be performed using, for example, AI, or may be performed without AI. For example, the assessment unit can input the user's level of expertise data into the generation AI and cause the generation AI to adjust the use of technical terms.

[0090] The providing unit can estimate the user's emotion and adjust the program provision method based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. For example, the providing unit estimates the user's emotion using voice analysis. The providing unit can also estimate the user's emotion using facial expression recognition. The providing unit can also estimate the user's emotion using text analysis. For example, the providing unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's speech and estimates the emotion. This allows the program provision method to be adjusted based on the user's emotion, thereby providing a more appropriate program. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit may input user emotion data to the generating AI and cause the generating AI to adjust the method of providing the program.

[0091] When providing a program, the providing unit can adjust the level of detail of the program based on the importance of the mental state. The importance of the mental state includes, but is not limited to, stress level, emotional state, etc. For example, the providing unit provides a detailed program when the mental state is important. The providing unit can also provide a concise program when the mental state is less important. The providing unit can also adjust the level of detail of the program based on the importance of the mental state. For example, the providing unit provides a detailed program when the mental state is important. The stress level is evaluated based on the user's stress level. This allows for a more appropriate program to be provided by adjusting the level of detail of the program based on the importance of the mental state. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input mental state data into a generation AI and cause the generation AI to adjust the level of detail of the program.

[0092] When providing a program, the providing unit can apply different providing algorithms depending on the category of the mental condition. Examples of mental condition categories include, but are not limited to, stress, depression, and anxiety. For example, in the case of a program related to stress management, the providing unit can apply a stress management algorithm. Furthermore, in the case of a program related to relaxation, the providing unit can also apply a relaxation algorithm. Furthermore, in the case of a program related to mental health, the providing unit can also apply a mental health algorithm. For example, in the case of a program related to stress management, the providing unit can apply a stress management algorithm. Depression is classified based on the user's mental condition. This allows for the provision of a more appropriate program by applying different providing algorithms depending on the category of the mental condition. Some or all of the above-described processing in the providing unit may be performed using, or without, AI. For example, the providing unit can input mental condition category data into the generating AI and cause the generating AI to apply the providing algorithm.

[0093] When providing a program, the providing unit can improve the accuracy of the program provision by referring to the user's past program results. Past program results include, but are not limited to, for example, the program's effectiveness and user feedback. For example, the providing unit provides an optimal program based on the user's past program results. The providing unit can also improve the accuracy of the program provision by referring to the user's past program results. The providing unit can also analyze the user's past program results and suggest an optimal program. For example, the providing unit provides an optimal program based on the user's past program results. The effectiveness of the program is evaluated based on the effectiveness of programs the user has previously received. This allows the accuracy of the program provision to be improved by referring to the user's past program results. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input the user's past program results into the generation AI and cause the generation AI to improve the accuracy of the program provision.

[0094] The providing unit can estimate the user's emotion and adjust the length of the program based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. The providing unit can estimate the user's emotion using, for example, voice analysis. The providing unit can also estimate the user's emotion using facial expression recognition. The providing unit can also estimate the user's emotion using text analysis. For example, the providing unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's speech and estimates the emotion. This allows the program length to be adjusted based on the user's emotion, thereby providing a more appropriate program. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the providing unit may be performed using, for example, AI, or without AI. For example, the providing unit can input the user's emotional data into the generating AI and cause the generating AI to adjust the length of the program.

[0095] When providing a program, the providing unit can determine the priority of providing the program based on the time of submission of the mental state. The submission time includes, but is not limited to, for example, a timestamp of the dialogue, a submission date and time, etc. The providing unit can, for example, provide the program preferentially based on the most recent mental state. The providing unit can also postpone mental states submitted earlier. The providing unit can also determine the priority of providing the program based on the time of submission. For example, the providing unit can provide the program preferentially based on the most recent mental state. The timestamp is evaluated based on the date and time of the dialogue. In this way, by determining the priority of providing the program based on the time of submission of the mental state, more important programs can be provided preferentially. Some or all of the above-described processing in the providing unit may be performed, for example, using AI or without AI. For example, the providing unit can input data on the time of submission of the mental state to the generation AI and cause the generation AI to determine the priority of providing the program.

[0096] When providing programs, the providing unit can adjust the order of program provision based on the relevance of mental states. Examples of relevance of mental states include, but are not limited to, keyword co-occurrence and topic similarity. For example, the providing unit can prioritize providing programs based on highly relevant mental states. The providing unit can also postpone less relevant mental states. The providing unit can also adjust the order of program provision based on the relevance of mental states. For example, the providing unit prioritizes providing programs based on highly relevant mental states. Keyword co-occurrence is evaluated based on the number of co-occurrences of particularly important keywords among mental states. In this way, by adjusting the order of program provision based on the relevance of mental states, more relevant programs can be provided preferentially. Some or all of the above-described processing by the providing unit may be performed using, for example, AI, or may be performed without using AI. For example, the providing unit can input mental state relevance data to a generation AI and cause the generation AI to adjust the order of program provision.

[0097] When providing a program, the providing unit can adjust the use of technical terms in the program according to the user's level of expertise. Examples of the level of expertise include, but are not limited to, the user's occupation, educational background, and past conversations. For example, if the user has specialized knowledge, the providing unit can provide the program using technical terms. Furthermore, if the user does not have specialized knowledge, the providing unit can also provide the program in simple language. Furthermore, the providing unit can adjust the use of technical terms in the program according to the user's level of expertise. For example, if the user has specialized knowledge, the providing unit can provide the program using technical terms. The user's level of expertise is evaluated based on the user's occupation. This allows the program to be more easily understood by adjusting the use of technical terms in the program according to the user's level of expertise. Some or all of the above-described processing in the providing unit may be performed using AI, for example, or without AI. For example, the providing unit can input the user's level of expertise data into a generation AI and cause the generation AI to adjust the use of technical terms.

[0098] The intervention unit can estimate the user's emotion and adjust the intervention method based on the estimated user's emotion. Specific methods for estimating emotion include, but are not limited to, voice analysis, facial expression recognition, and text analysis. For example, the intervention unit estimates the user's emotion using voice analysis. The intervention unit can also estimate the user's emotion using facial expression recognition. The intervention unit can also estimate the user's emotion using text analysis. For example, the intervention unit analyzes the user's voice data to estimate the emotion. Facial expression recognition captures the user's facial expression with a camera and estimates the emotion. Text analysis analyzes the content of the user's speech and estimates the emotion. This allows for more appropriate intervention by adjusting the intervention method based on the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without using AI. For example, the intervention unit may input user emotion data to the generation AI and cause the generation AI to adjust the intervention method.

[0099] When intervening, the intervention unit can analyze the user's past mental state and select the optimal intervention method. Past mental states include, but are not limited to, past diagnosis results, dialogue history, etc. The intervention unit selects the optimal intervention method based on, for example, the user's past mental state. The intervention unit can also analyze the user's past mental state and propose an effective intervention method. The intervention unit can also customize the intervention method by referring to the user's past mental state. For example, the intervention unit selects the optimal intervention method based on the user's past mental state. The diagnosis results are evaluated based on the results of diagnoses the user has received in the past. This allows the analysis of the user's past mental state to select the optimal intervention method and provide more effective intervention. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit can input the user's past mental state data into the generation AI and have the generation AI select the intervention method.

[0100] During intervention, the intervention unit can customize the intervention measures based on the user's current living situation. Examples of the current living situation include, but are not limited to, work and home situations. For example, the intervention unit can propose optimal intervention measures by taking the user's current living situation into consideration. The intervention unit can also customize the intervention measures based on the user's living situation. The intervention unit can also provide effective intervention measures by reflecting the user's living situation. For example, the intervention unit proposes optimal intervention measures by taking the user's current living situation into consideration. The work situation is evaluated based on the user's work situation. This allows for more appropriate intervention by customizing the intervention measures based on the user's current living situation. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without using AI. For example, the intervention unit can input the user's living situation data into a generation AI and cause the generation AI to customize the intervention measures.

[0101] During intervention, the intervention unit can improve the intervention method by reflecting user feedback. Feedback includes, but is not limited to, user ratings, comments, and survey results. For example, the intervention unit improves the intervention method based on user feedback. The intervention unit can also propose an optimal intervention method by reflecting user feedback. The intervention unit can also customize the intervention method by referring to user feedback. For example, the intervention unit improves the intervention method based on user feedback. Survey results are selected by referring to results of surveys previously answered by the user. By doing so, the intervention method can be improved and more effective intervention can be performed by reflecting user feedback. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or without AI. For example, the intervention unit can input user feedback data into a generation AI and cause the generation AI to improve the intervention method.

[0102] The intervention unit can estimate the user's emotions and determine the priority of interventions based on the estimated user emotions. Specific methods for estimating emotions include, but are not limited to, voice analysis, facial expression recognition, and text analysis. For example, the intervention unit estimates the user's emotions using voice analysis. The intervention unit can also estimate the user's emotions using facial expression recognition. The intervention unit can also estimate the user's emotions using text analysis. For example, the intervention unit analyzes the user's voice data to estimate the emotions. Facial expression recognition captures the user's facial expressions with a camera and estimates the emotions. Text analysis analyzes the content of the user's speech and estimates the emotions. This allows for more appropriate interventions by determining the priority of interventions based on the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without using AI. For example, the intervention unit may input user emotion data to the generation AI and have the generation AI determine the priority of intervention.

[0103] When intervening, the intervention unit can select an optimal intervention method by taking into account the user's geographical location information. Examples of geographical location information include, but are not limited to, GPS data and location information services. For example, the intervention unit can propose an optimal intervention method based on the user's geographical location information. The intervention unit can also provide relevant intervention methods based on the user's current location. The intervention unit can also select an effective intervention method by taking into account the user's geographical location information. For example, the intervention unit proposes an optimal intervention method based on the user's geographical location information. The location information service acquires the user's current location in real time and selects an intervention method based on that information. This allows the optimal intervention method to be selected by taking into account the user's geographical location information, resulting in more effective intervention. Some or all of the above-described processing in the intervention unit may be performed using, for example, AI, or may be performed without AI. For example, the intervention unit can input the user's geographical location information into the generation AI and cause the generation AI to select an intervention method.

[0104] During intervention, the intervention unit can analyze the user's social media activity and suggest intervention measures. Social media activity includes, but is not limited to, post content, the number of likes, and comments. For example, the intervention unit can analyze the user's social media posts and suggest relevant intervention measures. The intervention unit can also provide effective intervention measures by referring to the activities of the user's friends on social media. The intervention unit can also suggest optimal intervention methods based on the user's social media check-in information. For example, the intervention unit can analyze the user's social media posts and suggest relevant intervention measures. The friend's activities are selected by referring to the posts and comments of the user's friends on social media. By analyzing the user's social media activity, relevant intervention measures can be suggested, enabling more effective intervention. Some or all of the above-described processing in the intervention unit can be performed, for example, using AI or without AI. For example, the intervention unit can input data on the user's social media activity into a generation AI and have the generation AI execute the suggested intervention measures.

[0105] During intervention, the intervention unit can customize the intervention method by reflecting the user's past feedback. Past feedback includes, but is not limited to, user ratings, comments, and survey results. For example, the intervention unit can propose an optimal intervention method based on the user's past feedback. The intervention unit can also customize the intervention method by reflecting the user's past feedback. The intervention unit can also provide effective intervention measures by referring to the user's feedback. For example, the intervention unit proposes an optimal intervention method based on the user's past feedback. The survey results are selected by referring to the results of surveys previously answered by the user. By doing so, the intervention method can be customized by reflecting the user's past feedback, enabling more effective intervention. Some or all of the above-described processing in the intervention unit may be performed, for example, using AI or without AI. For example, the intervention unit can input the user's past feedback data into the generation AI and cause the generation AI to customize the intervention method. === Hard Collateral 1-1 === Each of the multiple elements, including the reception unit, the understanding unit, the provision unit, and the intervention 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 reception unit can receive the user's dialogue content using the microphone 38B or the camera 42 of the smart device 14. For example, the understanding unit can analyze the dialogue content using a generation AI by the specific processing unit 290 of the data processing device 12 to understand the user's mental state. For example, the provision unit can provide relaxation music or meditation guides by the control unit 46A of the smart device 14. For example, the intervention unit can refer the user to a specialist or take emergency measures when the user's mental state is serious by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-2 === Each of the multiple elements, including the reception unit, understanding unit, provision unit, and intervention unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the reception unit can receive the user's dialogue content using the microphone 238 or camera 42 of the smart glasses 214. For example, the understanding unit can analyze the dialogue content using a generation AI by the specific processing unit 290 of the data processing device 12 to understand the user's mental state. For example, the provision unit can provide relaxation music or meditation guides by the control unit 46A of the smart glasses 214. For example, the intervention unit can refer the user to a specialist or take emergency measures when the user's mental state is serious by the specific processing unit 290 of the data processing device 12. === Hard Collateral 1-3 === Each of the multiple elements including the reception unit, understanding unit, provision unit, and intervention unit described above is realized, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the reception unit can receive the content of the user's dialogue using the microphone 238 or camera 42 of the headset-type terminal 314. For example, the understanding unit can analyze the content of the dialogue using a generation AI by the specific processing unit 290 of the data processing device 12 to understand the user's mental state. For example, the provision unit can provide relaxation music or meditation guides by the control unit 46A of the headset-type terminal 314. For example, the intervention unit can refer the user to a specialist or take emergency measures by the specific processing unit 290 of the data processing device 12 when the user's mental state is serious. === Hard Collateral 1-4 === Each of the multiple elements including the reception unit, understanding unit, provision unit, and intervention unit described above is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the reception unit can receive the content of the user's dialogue using the microphone 238 or camera 42 of the robot 414. For example, the understanding unit can analyze the content of the dialogue using a generation AI by the specific processing unit 290 of the data processing device 12 to understand the user's mental state. For example, the provision unit can provide relaxation music or meditation guides by the control unit 46A of the robot 414. For example, the intervention unit can refer the user to a specialist or take emergency measures by the specific processing unit 290 of the data processing device 12 when the user's mental state is serious.

[0106] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0107] When receiving the user's dialogue content, the reception unit can monitor the user's current activity status in real time and determine the appropriate timing for the dialogue. For example, if the user is exercising, the reception unit can temporarily suspend the dialogue and resume it after the exercise is finished. Also, if the user is in a meeting, the reception unit can suspend the dialogue until the meeting ends. Furthermore, it can detect the time period when the user is relaxing and start the dialogue during that time period. This makes it possible to provide more effective mental care by adjusting the timing of the dialogue according to the user's activity status.

[0108] The provider can provide a customized fitness program based on the user's mental state. For example, if the user is feeling stressed, the provider can provide a yoga or stretching program to relieve stress. If the user feels a lack of energy, the provider can also provide an aerobic exercise program to increase energy. Furthermore, if the user is seeking relaxation, the provider can also provide a breathing exercise or meditation program for relaxation. In this way, by providing a fitness program that suits the user's mental state, it is possible to support both the mental and physical aspects of the user.

[0109] The intervention unit can send notifications to the user's family and friends if the user's mental condition is serious. For example, if the user shows suicidal thoughts, the intervention unit can send an emergency notification to the user's family and friends to urge them to provide prompt support. Also, if the user feels extremely anxious, the intervention unit can send a notification to the user's trusted friends to request support. Furthermore, if the user feels lonely, the intervention unit can send a notification to the user's family to urge them to get in touch. This allows the user to quickly obtain support from those around them if their mental condition is serious.

[0110] When analyzing the content of a user's dialogue, the comprehension unit can adjust the analysis method taking into account the user's cultural background and language differences. For example, if users have different cultural backgrounds, the analysis can take into account expressions and phrases specific to those cultures. Also, if a user speaks multiple languages, the comprehension unit can apply analysis algorithms compatible with those languages. Furthermore, it can select an appropriate mental care approach based on the user's cultural background. This makes it possible to more accurately comprehend the mental state by taking into account the user's cultural background and language differences.

[0111] The providing unit can estimate the user's emotions and adjust the tone and content of the feedback to the user based on the estimated emotions. For example, if the user is feeling sad, the providing unit can provide an encouraging message in a gentle tone. If the user is feeling angry, the providing unit can also proceed with the dialogue in a calm tone. Furthermore, if the user is feeling happy, the providing unit can emphasize positive feedback. This makes it possible to provide more effective mental care by providing feedback according to the user's emotions.

[0112] The intervention unit can send a notification to the user's workplace or school if the user's mental condition is serious. For example, if the user expresses suicidal thoughts, the intervention unit can send an emergency notification to the user's workplace or school to prompt a prompt response. Also, if the user is feeling extremely anxious, the intervention unit can send a notification to the user's workplace or school to request support. Furthermore, if the user has been experiencing mental health problems for a long period of time, the intervention unit can also send a notification to the user's workplace or school to prompt an appropriate response. This allows the user to quickly obtain support from their workplace or school if their mental condition is serious.

[0113] When analyzing the content of a user's dialogue, the comprehension unit can adjust the analysis method by taking into account the user's lifestyle habits and daily behavior patterns. For example, if the user is a nocturnal person, the analysis can be performed taking into account the mental state specific to that time of day. Also, if the user exercises regularly, the analysis can take into account the effects of that exercise. Furthermore, if the user has specific eating habits, the analysis can take into account the effects of those meals. This makes it possible to more accurately comprehend the mental state by taking into account the user's lifestyle habits and behavior patterns.

[0114] The providing unit can estimate the user's emotions and adjust the progress speed of the mental care program for the user based on the estimated emotions. For example, if the user is feeling impatient, the providing unit can slow down the progress speed of the program to allow the user to relax. Also, if the user is excited, the providing unit can speed up the progress speed of the program to utilize the user's energy. Furthermore, if the user is calm, the providing unit can provide the program at a normal progress speed. In this way, more effective mental care can be achieved by adjusting the progress speed of the program according to the user's emotions.

[0115] The intervention unit can send a notification to the user's medical institution if the user's mental condition is serious. For example, if the user expresses suicidal thoughts, the intervention unit can send an emergency notification to the user's medical institution to prompt a prompt response. In addition, if the user is experiencing extreme anxiety, the intervention unit can also send a notification to the user's medical institution to request support. Furthermore, if the user has been experiencing mental health problems for a long period of time, the intervention unit can also send a notification to the user's medical institution to prompt an appropriate response. This allows the user to quickly obtain support from a medical institution if their mental condition is serious.

[0116] When analyzing the content of a user's dialogue, the comprehension unit can adjust the analysis method by taking into account the user's hobbies and interests. For example, if the user is interested in music, the analysis can be performed by placing emphasis on dialogue related to that music. If the user is interested in sports, the analysis can be performed by placing emphasis on dialogue related to that sport. Furthermore, if the user is interested in reading, the analysis can be performed by placing emphasis on dialogue related to reading. In this way, by taking the user's hobbies and interests into consideration, it is possible to more accurately grasp the mental state.

[0117] The processing flow of the second embodiment will be briefly explained below.

[0118] Step 1: The reception unit receives the user's dialogue content. The user's dialogue content includes voice, text, images, etc. For example, the reception unit receives the user's dialogue content using voice input and converts the voice input into text data using voice recognition technology. The user can input text using a keyboard or touch screen, and the user can input images using a camera and analyze the images. Step 2: The understanding unit uses the generation AI to analyze the dialogue content received by the reception unit and understand the user's mental state. For example, the dialogue content is analyzed using natural language processing technology, and the user's utterances are analyzed using a text generation AI (e.g., LLM) or a multimodal generation AI. The generation AI uses keyword extraction technology to pick out particularly important information from the dialogue content and understand the user's mental state based on that information. Step 3: The provider provides an appropriate program based on the mental state grasped by the grasper. The program may include music for relaxation, guided meditation, and advice on stress management. The provider selects and provides the optimal program according to the user's mental state. Step 4: The intervention unit performs crisis intervention as needed based on the program provided by the provider unit. For example, if the user's mental condition is serious, the intervention unit may refer the user to a specialist or provide emergency care. The intervention unit monitors the user's mental condition in real time and can intervene immediately if needed.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0137] 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.

[0138] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0139] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0140] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0153] 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.

[0154] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0155] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0156] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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).

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0170] 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.

[0171] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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).

[0176] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0177] 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."

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] [Explanation of symbols]

[0191] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a reception unit that receives the content of a user's dialogue; a recognition unit that analyzes the content of the dialogue received by the reception unit and recognizes the mental state of the user; a providing unit that provides a specific program based on the mental state grasped by the grasping unit; an intervention unit that performs crisis intervention under specific conditions based on the program provided by the provision unit; Equipped with A system characterized by:

2. The providing unit Providing relaxation music or guided meditation 2. The system of claim 1.

3. The providing unit Providing advice for managing stress 2. The system of claim 1.

4. The intervention unit is Refer users to specialists if their mental health exceeds certain thresholds 2. The system of claim 1.

5. The intervention unit is Take emergency action if the user's mental state exceeds a certain threshold 2. The system of claim 1.

6. The grasping unit Analyzing user comments using natural language processing technology to understand their mental state 2. The system of claim 1.

7. The reception unit Estimates the user's emotions and adjusts the timing of accepting dialogue based on the estimated user emotions.

2. The system of claim 1.

8. The reception unit Analyze the user's past interaction history and select a specific reception method 2. The system of claim 1.

Images