System

Abstract

To provide a system that analyzes emotions and sources of stress of users and proposes appropriate relaxation methods or consultations with experts.SOLUTION: A system according to an embodiment comprises a reception unit, an analysis unit, a proposal unit, a provision unit, and a recommendation unit. The reception unit receives the statements of users. The analysis unit analyzes the statements received by the reception unit. The proposal unit proposes relaxation methods on the basis of the analysis results obtained by the analysis unit. The provision unit provides the relaxation methods proposed by the proposal unit to the users. The recommendation unit recommends consultations with experts on the basis of the analysis results obtained by the analysis 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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technologies have the problem of not being able to accurately grasp the user's emotions and the causes of stress, and not being able to adequately suggest appropriate relaxation methods or advice from a specialist.

[0005] The system according to the embodiment aims to analyze the user's emotions and causes of stress, and to suggest appropriate relaxation methods or consultation with a specialist. [Means for solving the problem]

[0006] The system according to the embodiment includes a reception unit, an analysis unit, a proposal unit, a provision unit, and a recommendation unit. The reception unit accepts the content of a user's statement. The analysis unit analyzes the content of the statement accepted by the reception unit. The proposal unit proposes a relaxation method based on the analysis result obtained by the analysis unit. The provision unit provides the user with the relaxation method proposed by the proposal unit. The recommendation unit recommends consulting an expert based on the analysis result obtained by the analysis unit. Effect of the Invention

[0007] The system according to the embodiment can analyze the user's emotions and causes of stress, and suggest appropriate relaxation methods or consultation with a specialist. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 PREFERRED EMBODIMENTS

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

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

[0011] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed 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 and 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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, the RAM 30, and the 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 (e.g., 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., voice and / or text). Display 40A displays visible information such as text and images according to instructions from processor 46. Speaker 40B outputs voice according to 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 Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0024] As shown in Fig. 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[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 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. Also, the data processing device 12 may be a server device, or may be a terminal device (e.g., a mobile phone, a robot, a home appliance, etc.) owned by a user. Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The AI ​​counselor AI assistant system for mental health support according to an embodiment of the present invention is a system that understands daily emotions and causes of stress through conversation with the user, suggests methods for relaxing the mind and refreshing the mood, and recommends consulting a specialist if necessary. This system accepts the user's remarks, and the AI ​​analyzes the remarks and suggests a relaxation method. The proposed relaxation method is provided to the user. In addition, it is also possible to recommend consulting a specialist based on the analysis results. For example, if a user says "I've been feeling stressed lately," the content is input to the AI. Next, the AI ​​analyzes the input remarks. The AI ​​analyzes the user's remarks and understands the cause of stress and the emotional state. For example, if a user says "I'm tired because I'm busy at work," the AI ​​analyzes the content and identifies that work is the cause of stress. Based on the analysis results, the AI ​​suggests a relaxation method. For example, if a user says "I want to relax," the AI ​​suggests relaxation methods such as "taking a deep breath" and "listening to music." The proposed relaxation method is provided to the user. For example, a notification of the relaxation method is sent to the user's smartphone. In addition, based on the analysis results, the AI ​​can also recommend consulting a specialist. For example, if a user says, "I can't sleep because I'm so stressed," the AI ​​will recommend consulting a specialist. The recommended specialists are prioritized from those in the user's area. The recommendation is also made taking into consideration the experts' ratings and reviews. This allows users to understand their daily emotions and the causes of stress, and by practicing relaxation methods, they can relax their mind and refresh their mood. In addition, they can receive appropriate mental health care by consulting a specialist if necessary. This allows the AI ​​counselor AI assistant system for mental health support to understand the user's emotions and the causes of stress, suggest relaxation methods, and recommend consulting a specialist if necessary.

[0029] The AI ​​counselor AI assistant system for mental health support according to the embodiment includes a reception unit, an analysis unit, a proposal unit, a provision unit, and a recommendation unit. The reception unit accepts the user's remarks. The user's remarks include, for example, text, voice, and emotional expressions, but are not limited to such examples. The reception unit converts the user's remarks into text data, for example, using a voice recognition technology. The reception unit can also accept text input. Furthermore, the reception unit can also include a sensor for analyzing the emotional expressions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The analysis unit uses AI to analyze the remarks accepted by the reception unit. The analysis is performed, for example, using a natural language processing technology or an emotion analysis technology, but are not limited to such examples. For example, the analysis unit extracts keywords from the user's remarks and identifies the cause of stress. The analysis unit can also understand the user's emotional state using emotion analysis technology. The proposal unit proposes a relaxation method based on the analysis result obtained by the analysis unit. Examples of the relaxation method include, but are not limited to, deep breathing, meditation, and music therapy. For example, when the user says "I want to relax," the suggestion unit suggests deep breathing. Also, when the user says "I want to listen to music," the suggestion unit can also suggest music therapy. The provision unit provides the user with the relaxation method suggested by the suggestion unit. Examples of the provision method include, but are not limited to, notifications to a smartphone, guidance by a voice assistant, and cooperation with a smart home device. For example, the provision unit transmits a notification of the relaxation method to the user's smartphone. Also, the provision unit can guide the relaxation method using a voice assistant. Furthermore, the provision unit can cooperate with a smart home device to prepare a relaxing environment. The recommendation unit recommends consulting an expert based on the analysis result obtained by the analysis unit. Examples of the recommendation method include, but are not limited to, a method of taking into account the evaluation and review of an expert, a method of prioritizing an expert in the user's area, and a method of adjusting the recommendation timing based on the user's stress level.For example, the recommendation unit recommends a reliable expert based on the expert's evaluation and review. The recommendation unit can also preferentially recommend experts in the user's area. Furthermore, the recommendation unit can adjust the timing of recommending consultation with an expert based on the user's stress level. In this way, the AI ​​counselor AI assistant system for mental health support according to the embodiment can efficiently analyze the content of the user's remarks and recommend relaxation methods and consultation with an expert.

[0030] The reception unit receives the user's utterance. The user's utterance includes, for example, text, voice, and emotional expression, but is not limited to such examples. The reception unit converts the user's utterance into text data, for example, using a voice recognition technology. Specifically, the voice recognition technology analyzes the user's voice in real time and accurately converts the utterance into text. As a result, the content uttered by the user through voice is instantly recorded as text data. The reception unit can also accept text input. Text data input by the user using a keyboard or touch screen is also accepted in the same way and transmitted to the analysis unit. Furthermore, the reception unit can also include a sensor for analyzing emotional expression. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The camera captures the user's face with high resolution and detects subtle changes in the facial expression. The emotion estimation algorithm analyzes the characteristics of the facial expression and estimates the emotional state of the user, such as whether the user is happy, sad, or angry. As a result, the reception unit can grasp not only the user's utterance but also the emotional state at the same time. In addition, the reception unit can analyze voice characteristics such as the tone, speed, and volume of the user's voice to estimate the user's emotional state, which allows for a more accurate understanding of the user's emotional state when speaking.

[0031] The analysis unit uses AI to analyze the content of the remarks received by the reception unit. The analysis is performed, for example, using natural language processing technology and emotion analysis technology, but is not limited to such examples. Specifically, the natural language processing technology is used to extract keywords from the content of the user's remarks and understand the context. For example, if a user remarks, "I've been busy with work recently and I'm stressed," the analysis unit extracts keywords such as "work," "busy," and "stress," and identifies the cause of the user's stress by analyzing the relevance of these keywords. The analysis unit can also understand the user's emotional state using emotion analysis technology. The emotion analysis technology analyzes the content of the user's remarks, voice characteristics, and facial expression data to estimate the emotional state of the user. For example, if the content of the user's remarks contains many negative expressions, the analysis unit can determine that the user is feeling stressed. Furthermore, the analysis unit can also analyze the user's emotional state and stress patterns by referring to past data and the user's history. As a result, the analysis unit can comprehensively analyze the content of the user's remarks and accurately grasp the user's emotional state and the cause of stress.

[0032] The suggestion unit suggests a relaxation method based on the analysis result obtained by the analysis unit. Examples of the relaxation method include, but are not limited to, deep breathing, meditation, and music therapy. Specifically, the suggestion unit selects an optimal relaxation method according to the user's statement and emotional state. For example, if the user says "I want to relax," the suggestion unit suggests deep breathing. Deep breathing is an easy relaxation method that can be performed and has the effect of reducing stress. In addition, if the user says "I want to listen to music," the suggestion unit can also suggest music therapy. Music therapy is a method of achieving a relaxing effect by listening to specific music, and can suggest music according to the user's preferences. Furthermore, the suggestion unit can also suggest an individually customized relaxation method taking into account the user's past history and preferences. For example, if the user liked meditation in the past, the suggestion unit can suggest meditation. As a result, the suggestion unit can suggest an optimal relaxation method according to the user's needs and effectively reduce the user's stress.

[0033] The providing unit provides the user with the relaxation method proposed by the suggesting unit. The providing method includes, for example, a notification to a smartphone, guidance by a voice assistant, cooperation with a smart home device, and the like, but is not limited to such examples. Specifically, the providing unit transmits a notification of the relaxation method to the user's smartphone. The notification includes a detailed explanation of the relaxation method and an implementation procedure, and the user can implement the relaxation method by checking the notification. The providing unit can also guide the relaxation method using a voice assistant. The voice assistant explains the relaxation method to the user by voice and guides the implementation procedure. Furthermore, the providing unit can also prepare a relaxing environment in cooperation with a smart home device. For example, it is possible to adjust smart lighting to create an environment that is easy to relax, or to play relaxing music using a smart speaker. In this way, the providing unit can provide an environment that is easy for the user to implement the relaxation method and support the user's stress reduction. Furthermore, the providing unit can collect user feedback and use it to improve the providing method. For example, by sending feedback evaluating the effect of the relaxation method to the providing unit, the providing unit can optimize the providing method based on the feedback.

[0034] The recommendation unit recommends consulting with an expert based on the analysis result obtained by the analysis unit. The recommendation method includes, for example, a method of considering the evaluation and review of an expert, a method of giving priority to an expert in the user's area, and a method of adjusting the recommendation timing based on the user's stress level, but is not limited to such examples. Specifically, the recommendation unit recommends a reliable expert based on the evaluation and review of the expert. For example, by preferentially recommending experts who have been highly rated by past users, the user can consult with a reliable expert. The recommendation unit can also preferentially recommend experts in the user's area. This allows the user to quickly access nearby experts, lowering the hurdle for consultation. Furthermore, the recommendation unit can also adjust the recommendation timing of consulting with an expert based on the user's stress level. For example, if the user's stress level is high, the recommendation unit recommends consulting with an expert as soon as possible, and if the stress level is low, the recommendation unit recommends regular check-ins. This allows the recommendation unit to recommend consulting with an expert at an appropriate timing according to the user's situation and support the user's mental health. Furthermore, the recommendation unit can improve the recommendation algorithm based on user feedback and make more accurate recommendations. For example, if a user provides highly satisfactory feedback about a recommended expert, that expert may be recommended to other users more frequently.

[0035] The providing unit can send a notification of the relaxation method to the user's smartphone. The notification includes, for example, a push notification, an SMS, an email, and the like, but is not limited to such examples. The providing unit, for example, sends a push notification to the user's smartphone. The providing unit can also send the notification of the relaxation method using an SMS. Furthermore, the providing unit can also send the notification of the relaxation method using an email. This allows the user to immediately receive the relaxation method. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the providing unit can input the notification of the relaxation method to a generating AI and cause the generating AI to generate the notification content.

[0036] The recommendation unit can make a recommendation based on the evaluation and review of the expert. The evaluation and review include, for example, user evaluation, expert feedback, and the like, but are not limited to such examples. The recommendation unit recommends an expert based on, for example, user evaluation. The recommendation unit can also make a recommendation based on expert feedback. Furthermore, the recommendation unit can also analyze the evaluation and review data and recommend a reliable expert. This allows the user to be recommended a reliable expert. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input the evaluation and review data to the generation AI and cause the generation AI to execute the recommendation of an expert.

[0037] The recommendation unit can adjust the timing of recommending consultation with a specialist based on the user's stress level. The stress level includes, for example, self-report, biofeedback, behavioral data, and the like, but is not limited to such examples. The recommendation unit, for example, evaluates the stress level based on the self-report and adjusts the recommendation timing. The recommendation unit can also evaluate the stress level based on biofeedback data and adjust the recommendation timing. Furthermore, the recommendation unit can evaluate the stress level based on behavioral data and adjust the recommendation timing. This makes it possible to recommend consultation with a specialist at an appropriate timing according to the user's stress level. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input data on the stress level to the generation AI and cause the generation AI to adjust the recommendation timing.

[0038] The providing unit can prepare a relaxing environment in cooperation with the user's smart home device. Smart home devices include, but are not limited to, smart lights, smart speakers, thermostats, etc. The providing unit prepares a relaxing environment, for example, using a smart light. The providing unit can also play relaxing music using a smart speaker. Furthermore, the providing unit can adjust the room temperature using a thermostat. This allows the user to prepare an environment that is easy to relax in. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the control of the smart home device to the generating AI and cause the generating AI to prepare a relaxing environment.

[0039] The suggestion unit can suggest the user's interaction with the pet as a relaxation method. Interaction with the pet includes, for example, walking, playing, touching, etc., but is not limited to such examples. For example, the suggestion unit suggests the user to walk with the pet. The suggestion unit can also suggest the user to play with the pet. Furthermore, the suggestion unit can also suggest the user to touch the pet. This allows the user to relax through interaction with the pet. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input a method of interacting with the pet to the generation AI and cause the generation AI to execute a proposal of a relaxation method.

[0040] The recommendation unit can give priority to recommending experts in the user's area. Local experts include, for example, geographical ranges, fields of expertise, and the like, but are not limited to such examples. For example, the recommendation unit gives priority to recommending experts in the area where the user lives. The recommendation unit can also give priority to recommending experts near the user's workplace. Furthermore, the recommendation unit can make recommendations taking into account the ratings and reviews of experts in the user's area. This allows the user to quickly access local experts. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input data of local experts to the generation AI and cause the generation AI to recommend experts.

[0041] The analysis unit analyzes the genetic information of the user, and the suggestion unit can suggest a relaxation method based on the genetic stress factors of the user. The genetic information includes, for example, DNA sequencing, genetic markers, etc., but is not limited to such examples. The analysis unit analyzes the genetic information of the user using, for example, DNA sequencing technology. The analysis unit can also identify stress factors using genetic markers. The suggestion unit suggests a relaxation method based on the genetic stress factors obtained by the analysis unit. For example, the suggestion unit suggests a relaxation method such as deep breathing or meditation based on the genetic stress factors of the user. This makes it possible to suggest a relaxation method based on the genetic stress factors of the user. A part or all of the above-mentioned processing in the analysis unit and the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data of the genetic information to the generation AI and cause the generation AI to execute an analysis of the stress factors. Also, the suggestion unit can input the analysis result to the generation AI and cause the generation AI to execute a proposal of a relaxation method.

[0042] The reception unit can analyze the user's past speech history and select the optimal reception method. The speech history includes, for example, a text log, a voice record, a time range, and the like, but is not limited to such examples. For example, the reception unit saves the user's past speech history as a text log. The reception unit can also save a voice record and analyze the contents of the past speech. Furthermore, the reception unit can select the optimal reception method in consideration of the time range of the speech. For example, the reception unit preferentially accepts phrases that the user has frequently used in the past. Furthermore, the reception unit can analyze the user's past speech patterns and select the optimal reception timing. Furthermore, the reception unit can preferentially accept specific keywords from the contents of the user's past speech. This makes it possible to select the optimal reception method based on the user's past speech history. A part or all of the above-mentioned 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 data of the speech history to the generation AI and cause the generation AI to select the optimal reception method.

[0043] The reception unit can filter the utterance contents based on the user's current living situation and field of interest when receiving the utterance contents. The living situation includes, for example, occupation, home environment, health condition, etc., but is not limited to such examples. For example, when the user inputs the current living situation, the reception unit filters the utterance contents based on the information. In addition, the reception unit can preferentially receive related utterance contents based on the user's field of interest. Furthermore, the reception unit can filter unnecessary utterance contents based on the user's living situation and field of interest. This makes it possible to filter the utterance contents based on the user's living situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input data on the living situation and field of interest to the generation AI and cause the generation AI to execute filtering of the utterance contents.

[0044] The reception unit can preferentially receive remarks with high relevance based on the geographical location information of the user when receiving the remark contents. The geographical location information includes, for example, GPS data, address information, and the like, but is not limited to such examples. For example, when the user is in a specific area, the reception unit preferentially receives remark contents related to the area. The reception unit can also filter related remark contents based on the geographical location information of the user. Furthermore, when the user is moving, it can also preferentially receive remark contents related to the current location. This makes it possible to preferentially receive remarks with high relevance based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input data of the geographical location information to the generation AI and cause the generation AI to execute the determination of the priority order of the remark contents.

[0045] The reception unit can analyze the social media activity of the user when receiving the comment content, and receive related comments. The social media activity includes, but is not limited to, for example, the post content, the number of likes, and the number of followers. The reception unit, for example, analyzes the social media activity of the user, and preferentially receives the related comment content. The reception unit can also filter the comment content based on keywords frequently used by the user on social media. Furthermore, the reception unit can identify a current interest from the user's social media activity, and preferentially receive the related comment content. This makes it possible to receive related comments based on the user's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input data of the social media activity to the generation AI, and cause the generation AI to filter the comment content.

[0046] The analysis unit can adjust the level of detail of the analysis based on the importance of the comment content during analysis. The importance includes, for example, the user's interest level, urgency, etc., but is not limited to such examples. For example, the analysis unit performs a detailed analysis of comment content with high importance. The analysis unit can also perform a concise analysis of comment content with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance of the comment content. This allows the analysis to be performed with a level of detail according to the importance of the comment content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the importance data of the comment content to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0047] The analysis unit can apply different analysis algorithms depending on the category of the comment content during analysis. The categories include, for example, topics, themes, genres, etc., but are not limited to such examples. For example, the analysis unit applies a stress analysis algorithm to comment content related to stress. The analysis unit can also apply a relaxation analysis algorithm to comment content related to relaxation. Furthermore, a quick analysis algorithm can be applied to urgent content. This makes it possible to apply an appropriate analysis algorithm depending on the category of the comment content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input category data of the comment content to the generation AI and cause the generation AI to apply the analysis algorithm.

[0048] The analysis unit can determine the priority of the analysis based on the submission time of the comment content during the analysis. The submission time includes, but is not limited to, for example, a timestamp and a submission date. The analysis unit, for example, prioritizes the analysis of the most recent comment content. The analysis unit can also prioritize the analysis of the current comment content while referring to the past comment content. Furthermore, the analysis unit can dynamically adjust the priority of the analysis based on the submission time. This allows the priority to be determined based on the submission time of the comment content, and the analysis to be performed efficiently. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input data on the submission time to the generation AI and cause the generation AI to determine the priority of the analysis.

[0049] The analysis unit can adjust the order of analysis based on the relevance of the utterance contents during analysis. The relevance includes, for example, the degree of topic agreement, the co-occurrence of keywords, and the like, but is not limited to such examples. For example, the analysis unit prioritizes the analysis of highly relevant utterance contents. The analysis unit can also postpone the analysis of less relevant utterance contents. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the utterance contents. This allows the analysis to be efficiently performed by adjusting the order of analysis based on the relevance of the utterance contents. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the relevance data of the utterance contents to the generation AI and cause the generation AI to adjust the order of analysis.

[0050] The suggestion unit can adjust the level of detail of the proposal based on the importance of the relaxation method when making a proposal. The level of importance includes, for example, the user's interest level, urgency, etc., but is not limited to such examples. For example, the suggestion unit makes a detailed proposal for a relaxation method with a high level of importance. The suggestion unit can also make a concise proposal for a relaxation method with a low level of importance. Furthermore, the suggestion unit can dynamically adjust the level of detail of the proposal according to the importance of the relaxation method. This makes it possible to make a proposal with a level of detail according to the importance of the relaxation method. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input importance data of the relaxation method to the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0051] The suggestion unit can apply different suggestion algorithms according to the category of the relaxation method when making a suggestion. The categories include, for example, topics, themes, genres, and the like, but are not limited to such examples. For example, the suggestion unit applies a deep breathing suggestion algorithm to a relaxation method related to deep breathing. The suggestion unit can also apply a music suggestion algorithm to a relaxation method related to music. Furthermore, the suggestion unit can also apply a meditation suggestion algorithm to a relaxation method related to meditation. This makes it possible to apply an appropriate suggestion algorithm according to the category of the relaxation method. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input category data of the relaxation method to the generation AI and cause the generation AI to apply the suggestion algorithm.

[0052] The suggestion unit can determine the priority of the proposal based on the submission time of the relaxation method at the time of proposal. The submission time includes, but is not limited to, for example, a timestamp, a submission date, etc. The suggestion unit, for example, preferentially proposes a recent relaxation method. The suggestion unit can also preferentially propose a current relaxation method while referring to past relaxation methods. Furthermore, the priority of the proposal can be dynamically adjusted based on the submission time. This allows the priority to be determined based on the submission time of the relaxation method, and the proposal can be made efficiently. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input data on the submission time to the generation AI and cause the generation AI to determine the priority of the proposal.

[0053] The suggestion unit can adjust the order of the suggestions based on the relevance of the relaxation methods when making suggestions. The relevance includes, for example, the degree of matching of topics, co-occurrence of keywords, and the like, but is not limited to such examples. For example, the suggestion unit preferentially suggests relaxation methods with high relevance. The suggestion unit can also postpone relaxation methods with low relevance. Furthermore, the suggestion unit can dynamically adjust the order of the suggestions based on the relevance of the relaxation methods. This allows the order of the suggestions to be adjusted based on the relevance of the relaxation methods, and suggestions can be made efficiently. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input relevance data of the relaxation methods to the generation AI, and cause the generation AI to adjust the order of the suggestions.

[0054] The providing unit can select the optimal providing method by referring to the history of the user's past relaxation methods at the time of providing. The history of the relaxation methods includes, for example, past proposal contents, implementation history, etc., but is not limited to such examples. For example, the providing unit selects the optimal providing method based on the relaxation methods used by the user in the past. The providing unit can also analyze the history of the user's past relaxation methods and provide the most effective method. Furthermore, the providing unit can also suggest a new relaxation method while referring to the history of the user's past relaxation methods. This makes it possible to select the optimal providing method based on the history of the user's past relaxation methods. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the history data of the relaxation methods to the generating AI and cause the generating AI to select the optimal providing method.

[0055] The providing unit can customize the means for providing the relaxation method based on the user's current living situation at the time of providing. The living situation includes, for example, occupation, home environment, health condition, etc., but is not limited to such examples. For example, when the user is busy, the providing unit provides a relaxation method that can be practiced in a short time. In addition, when the user is relaxed, the providing unit can also provide a detailed relaxation method. Furthermore, the providing unit can customize and provide an optimal relaxation method based on the user's living situation. This makes it possible to provide a relaxation method in an appropriate manner according to the user's living situation. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input living situation data to the generating AI and cause the generating AI to execute customization of the providing means.

[0056] The providing unit can provide an appropriate relaxation method based on the geographical location information of the user at the time of providing. The geographical location information includes, for example, GPS data, address information, and the like, but is not limited to such examples. For example, when the user is at home, the providing unit provides a relaxation method that can be practiced at home. In addition, when the user is out, the providing unit can also provide a relaxation method that can be practiced while out. Furthermore, the providing unit can customize and provide an optimal relaxation method based on the geographical location information of the user. This makes it possible to provide an optimal relaxation method based on the geographical location information of the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input geographical location information data to the generating AI and cause the generating AI to execute the provision of the relaxation method.

[0057] At the time of providing, the providing unit can analyze the social media activity of the user and suggest a means for providing a relaxation method. The social media activity includes, for example, the content of posts, the number of likes, the number of followers, etc., but is not limited to such examples. For example, the providing unit analyzes the social media activity of the user and provides a related relaxation method. The providing unit can also suggest a relaxation method based on keywords frequently used by the user on social media. Furthermore, the providing unit can identify a current interest from the social media activity of the user and provide a related relaxation method. In this way, an appropriate relaxation method can be provided based on the social media activity of the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input social media activity data to the generating AI and cause the generating AI to execute a suggestion of a means for providing a relaxation method.

[0058] The recommendation unit can select the optimal recommendation method by referring to the user's past consultation history at the time of recommendation. The consultation history includes, for example, past consultation content, implementation history, etc., but is not limited to such examples. For example, the recommendation unit recommends the optimal expert based on experts the user has consulted in the past. The recommendation unit can also analyze the user's past consultation history and recommend the most effective expert. Furthermore, the recommendation unit can also recommend a new expert while referring to the user's past consultation history. This makes it possible to select the optimal recommendation method based on the user's past consultation history. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input consultation history data to the generation AI and cause the generation AI to select the optimal recommendation method.

[0059] The recommendation unit can customize the recommendation means for consulting with an expert based on the user's current living situation at the time of recommendation. The living situation includes, for example, occupation, home environment, health condition, etc., but is not limited to such examples. For example, when the user is busy, the recommendation unit recommends an expert who can be consulted online. In addition, when the user is relaxed, the recommendation unit can also recommend an expert who can be consulted face-to-face. Furthermore, the recommendation unit can customize and recommend an optimal expert based on the living situation of the user. This makes it possible to recommend consultation with an expert in an appropriate manner according to the living situation of the user. Part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input living situation data to the generation AI and cause the generation AI to execute customization of the recommendation means.

[0060] The recommendation unit can recommend an optimal expert by considering the geographical location information of the user at the time of recommendation. The geographical location information includes, for example, GPS data, address information, and the like, but is not limited to such examples. For example, when the user is at home, the recommendation unit recommends an expert near the user's home. In addition, when the user is out, the recommendation unit can also recommend an expert who can be consulted while out. Furthermore, the recommendation unit can customize and recommend an optimal expert based on the geographical location information of the user. This makes it possible to recommend an optimal expert based on the geographical location information of the user. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input geographical location information data to the generation AI and cause the generation AI to execute the recommendation of an expert.

[0061] At the time of recommendation, the recommendation unit can analyze the user's social media activity and suggest a recommended means of consulting an expert. The social media activity includes, but is not limited to, for example, the content of posts, the number of likes, the number of followers, etc. The recommendation unit, for example, analyzes the user's social media activity and recommends a related expert. The recommendation unit can also recommend an expert based on keywords frequently used by the user on social media. Furthermore, the recommendation unit can identify a current interest from the user's social media activity and recommend a related expert. This makes it possible to recommend an appropriate expert based on the user's social media activity. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI or may be performed without using AI. For example, the recommendation unit can input social media activity data to the generation AI and cause the generation AI to execute a suggestion of a recommended means of an expert.

[0062] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0063] When analyzing the content of a user's statement, the analysis unit can improve the accuracy of the analysis by referring to the user's past statement history. For example, if a user has previously stated that "I'm busy at work," the analysis unit can more accurately analyze the current content of the statement by taking that history into account. Also, if a user has previously stated that "listening to music helps me relax," the analysis unit can optimize suggestions of relaxation methods based on that information. Furthermore, if a user has previously stated that "I would like to consult an expert," the analysis unit can recommend consulting an expert based on that history. This makes it possible to perform more accurate analysis and suggestions by utilizing the user's past statement history.

[0064] When sending a notification of a relaxation method to the user's smartphone, the providing unit can adjust the timing of the notification in consideration of the user's current activity status. For example, if the user is exercising, the providing unit can send the notification after the user finishes exercising. If the user is in a meeting, the providing unit can also send the notification after the meeting ends. Furthermore, if the user is sleeping, the providing unit can also send the notification after the user wakes up. This makes it possible to provide a notification of a relaxation method at an appropriate timing according to the user's activity status.

[0065] When making recommendations based on the evaluations and reviews of experts, the recommendation unit can filter experts based on the individual needs and preferences of the user. For example, if the user desires an expert in a specific field, experts specializing in that field are recommended with priority. In addition, if the user desires an expert of a specific gender or age, experts who meet those conditions can be recommended. Furthermore, experts to whom the user has given good evaluations in the past can be recommended with priority. In this way, experts according to the individual needs and preferences of the user can be recommended.

[0066] When adjusting the timing of recommending a consultation with a specialist based on the user's stress level, the recommendation unit can optimize the recommendation timing by taking into consideration the user's life rhythm and schedule. For example, if the user is prone to feeling stressed at night, the recommendation unit can recommend a consultation with a specialist at night. Also, if the user is prone to relaxing on weekends, the recommendation unit can recommend a consultation with a specialist on weekends. Furthermore, the recommendation unit can recommend a consultation with a specialist in between work by taking into consideration the user's work schedule. This makes it possible to recommend a consultation with a specialist at an appropriate timing according to the user's life rhythm and schedule.

[0067] When the providing unit cooperates with the user's smart home device to prepare a relaxing environment, the providing unit can set the optimal environment in consideration of the user's preferences and past usage history. For example, if the user liked to listen to a particular piece of music in the past, that music can be played. Also, if the user liked a particular lighting setting in the past, that setting can be applied. Furthermore, if the user liked a particular temperature setting in the past, the temperature can be adjusted to that temperature. This makes it possible to provide an optimal relaxing environment based on the user's preferences and past usage history.

[0068] When suggesting interaction with the user's pet as a relaxation method, the suggestion unit can suggest an optimal interaction method based on the type and personality of the user's pet. For example, if the user has a dog, walking or playing can be suggested. Also, if the user has a cat, petting or brushing can be suggested. Furthermore, if the user has a bird, talking to it or feeding it can be suggested. In this way, it is possible to suggest an optimal interaction method according to the type and personality of the user's pet.

[0069] The process flow of the first embodiment will be briefly described below.

[0070] Step 1: The reception unit receives the user's utterance. The user's utterance includes, for example, text, voice, and emotional expressions. The reception unit converts the user's utterance into text data using voice recognition technology. The reception unit can also receive text input and can be equipped with a sensor for analyzing emotional expressions. For example, the user's facial expression is captured by a camera, and the emotion is estimated using an emotion estimation algorithm. Step 2: The analysis unit uses AI to analyze the content of the comments received by the reception unit. The analysis is performed using natural language processing technology and sentiment analysis technology. For example, keywords are extracted from the user's comments to identify the cause of stress. Sentiment analysis technology can also be used to understand the user's emotional state. Step 3: The suggestion unit suggests a relaxation method based on the analysis results obtained by the analysis unit. The relaxation methods include deep breathing, meditation, music therapy, etc. For example, if the user says "I want to relax," deep breathing is suggested. Also, if the user says "I want to listen to music," music therapy can be suggested. Step 4: The providing unit provides the user with the relaxation method proposed by the suggesting unit. The providing method includes a notification to a smartphone, guidance by a voice assistant, and cooperation with a smart home device. For example, a notification of the relaxation method is sent to the user's smartphone. Also, the relaxation method can be guided using a voice assistant. Furthermore, a relaxing environment can be created by cooperation with a smart home device. Step 5: The recommendation unit recommends consulting an expert based on the analysis results obtained by the analysis unit. Recommendation methods include a method of taking into account the evaluation and reviews of experts, a method of prioritizing experts in the user's area, and a method of adjusting the recommendation timing based on the user's stress level. For example, a highly reliable expert is recommended based on the evaluation and reviews of experts. It is also possible to give priority to the recommendation of experts in the user's area. Furthermore, it is also possible to adjust the recommendation timing of consulting an expert based on the user's stress level.

[0071] (Example 2) The AI ​​counselor AI assistant system for mental health support according to an embodiment of the present invention is a system that understands daily emotions and causes of stress through conversation with the user, suggests methods for relaxing the mind and refreshing the mood, and recommends consulting a specialist if necessary. This system accepts the user's remarks, and the AI ​​analyzes the remarks and suggests a relaxation method. The proposed relaxation method is provided to the user. In addition, it is also possible to recommend consulting a specialist based on the analysis results. For example, if a user says "I've been feeling stressed lately," the content is input to the AI. Next, the AI ​​analyzes the input remarks. The AI ​​analyzes the user's remarks and understands the cause of stress and the emotional state. For example, if a user says "I'm tired because I'm busy at work," the AI ​​analyzes the content and identifies that work is the cause of stress. Based on the analysis results, the AI ​​suggests a relaxation method. For example, if a user says "I want to relax," the AI ​​suggests relaxation methods such as "taking a deep breath" and "listening to music." The proposed relaxation method is provided to the user. For example, a notification of the relaxation method is sent to the user's smartphone. In addition, based on the analysis results, the AI ​​can also recommend consulting a specialist. For example, if a user says, "I can't sleep because I'm so stressed," the AI ​​will recommend consulting a specialist. The recommended specialists are prioritized from those in the user's area. The recommendation is also made taking into consideration the experts' ratings and reviews. This allows users to understand their daily emotions and the causes of stress, and by practicing relaxation methods, they can relax their mind and refresh their mood. In addition, they can receive appropriate mental health care by consulting a specialist if necessary. This allows the AI ​​counselor AI assistant system for mental health support to understand the user's emotions and the causes of stress, suggest relaxation methods, and recommend consulting a specialist if necessary.

[0072] The AI ​​counselor AI assistant system for mental health support according to the embodiment includes a reception unit, an analysis unit, a proposal unit, a provision unit, and a recommendation unit. The reception unit accepts the user's remarks. The user's remarks include, for example, text, voice, and emotional expressions, but are not limited to such examples. The reception unit converts the user's remarks into text data, for example, using a voice recognition technology. The reception unit can also accept text input. Furthermore, the reception unit can also include a sensor for analyzing the emotional expressions. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The analysis unit uses AI to analyze the remarks accepted by the reception unit. The analysis is performed, for example, using a natural language processing technology or an emotion analysis technology, but are not limited to such examples. For example, the analysis unit extracts keywords from the user's remarks and identifies the cause of stress. The analysis unit can also understand the user's emotional state using emotion analysis technology. The proposal unit proposes a relaxation method based on the analysis result obtained by the analysis unit. Examples of the relaxation method include, but are not limited to, deep breathing, meditation, and music therapy. For example, when the user says "I want to relax," the suggestion unit suggests deep breathing. Also, when the user says "I want to listen to music," the suggestion unit can also suggest music therapy. The provision unit provides the user with the relaxation method suggested by the suggestion unit. Examples of the provision method include, but are not limited to, notifications to a smartphone, guidance by a voice assistant, and cooperation with a smart home device. For example, the provision unit transmits a notification of the relaxation method to the user's smartphone. Also, the provision unit can guide the relaxation method using a voice assistant. Furthermore, the provision unit can cooperate with a smart home device to prepare a relaxing environment. The recommendation unit recommends consulting an expert based on the analysis result obtained by the analysis unit. Examples of the recommendation method include, but are not limited to, a method of taking into account the evaluation and review of an expert, a method of prioritizing an expert in the user's area, and a method of adjusting the recommendation timing based on the user's stress level.For example, the recommendation unit recommends a reliable expert based on the expert's evaluation and review. The recommendation unit can also preferentially recommend experts in the user's area. Furthermore, the recommendation unit can adjust the timing of recommending consultation with an expert based on the user's stress level. In this way, the AI ​​counselor AI assistant system for mental health support according to the embodiment can efficiently analyze the content of the user's remarks and recommend relaxation methods and consultation with an expert.

[0073] The reception unit receives the user's utterance. The user's utterance includes, for example, text, voice, and emotional expression, but is not limited to such examples. The reception unit converts the user's utterance into text data, for example, using a voice recognition technology. Specifically, the voice recognition technology analyzes the user's voice in real time and accurately converts the utterance into text. As a result, the content uttered by the user through voice is instantly recorded as text data. The reception unit can also accept text input. Text data input by the user using a keyboard or touch screen is also accepted in the same way and transmitted to the analysis unit. Furthermore, the reception unit can also include a sensor for analyzing emotional expression. For example, the reception unit captures the user's facial expression with a camera and estimates the emotion using an emotion estimation algorithm. The camera captures the user's face with high resolution and detects subtle changes in the facial expression. The emotion estimation algorithm analyzes the characteristics of the facial expression and estimates the emotional state of the user, such as whether the user is happy, sad, or angry. As a result, the reception unit can grasp not only the user's utterance but also the emotional state at the same time. In addition, the reception unit can analyze voice characteristics such as the tone, speed, and volume of the user's voice to estimate the user's emotional state, which allows for a more accurate understanding of the user's emotional state when speaking.

[0074] The analysis unit uses AI to analyze the content of the remarks received by the reception unit. The analysis is performed, for example, using natural language processing technology and emotion analysis technology, but is not limited to such examples. Specifically, the natural language processing technology is used to extract keywords from the content of the user's remarks and understand the context. For example, if a user remarks, "I've been busy with work recently and I'm stressed," the analysis unit extracts keywords such as "work," "busy," and "stress," and identifies the cause of the user's stress by analyzing the relevance of these keywords. The analysis unit can also understand the user's emotional state using emotion analysis technology. The emotion analysis technology analyzes the content of the user's remarks, voice characteristics, and facial expression data to estimate the emotional state of the user. For example, if the content of the user's remarks contains many negative expressions, the analysis unit can determine that the user is feeling stressed. Furthermore, the analysis unit can also analyze the user's emotional state and stress patterns by referring to past data and the user's history. As a result, the analysis unit can comprehensively analyze the content of the user's remarks and accurately grasp the user's emotional state and the cause of stress.

[0075] The suggestion unit suggests a relaxation method based on the analysis result obtained by the analysis unit. Examples of the relaxation method include, but are not limited to, deep breathing, meditation, and music therapy. Specifically, the suggestion unit selects an optimal relaxation method according to the user's statement and emotional state. For example, if the user says "I want to relax," the suggestion unit suggests deep breathing. Deep breathing is an easy relaxation method that can be performed and has the effect of reducing stress. In addition, if the user says "I want to listen to music," the suggestion unit can also suggest music therapy. Music therapy is a method of achieving a relaxing effect by listening to specific music, and can suggest music according to the user's preferences. Furthermore, the suggestion unit can also suggest an individually customized relaxation method taking into account the user's past history and preferences. For example, if the user liked meditation in the past, the suggestion unit can suggest meditation. As a result, the suggestion unit can suggest an optimal relaxation method according to the user's needs and effectively reduce the user's stress.

[0076] The providing unit provides the user with the relaxation method proposed by the suggesting unit. The providing method includes, for example, a notification to a smartphone, guidance by a voice assistant, cooperation with a smart home device, and the like, but is not limited to such examples. Specifically, the providing unit transmits a notification of the relaxation method to the user's smartphone. The notification includes a detailed explanation of the relaxation method and an implementation procedure, and the user can implement the relaxation method by checking the notification. The providing unit can also guide the relaxation method using a voice assistant. The voice assistant explains the relaxation method to the user by voice and guides the implementation procedure. Furthermore, the providing unit can also prepare a relaxing environment in cooperation with a smart home device. For example, it is possible to adjust smart lighting to create an environment that is easy to relax, or to play relaxing music using a smart speaker. In this way, the providing unit can provide an environment that is easy for the user to implement the relaxation method and support the user's stress reduction. Furthermore, the providing unit can collect user feedback and use it to improve the providing method. For example, by sending feedback evaluating the effect of the relaxation method to the providing unit, the providing unit can optimize the providing method based on the feedback.

[0077] The recommendation unit recommends consulting with an expert based on the analysis result obtained by the analysis unit. The recommendation method includes, for example, a method of considering the evaluation and review of an expert, a method of giving priority to an expert in the user's area, and a method of adjusting the recommendation timing based on the user's stress level, but is not limited to such examples. Specifically, the recommendation unit recommends a reliable expert based on the evaluation and review of the expert. For example, by preferentially recommending experts who have been highly rated by past users, the user can consult with a reliable expert. The recommendation unit can also preferentially recommend experts in the user's area. This allows the user to quickly access nearby experts, lowering the hurdle for consultation. Furthermore, the recommendation unit can also adjust the recommendation timing of consulting with an expert based on the user's stress level. For example, if the user's stress level is high, the recommendation unit recommends consulting with an expert as soon as possible, and if the stress level is low, the recommendation unit recommends regular check-ins. This allows the recommendation unit to recommend consulting with an expert at an appropriate timing according to the user's situation and support the user's mental health. Furthermore, the recommendation unit can improve the recommendation algorithm based on user feedback and make more accurate recommendations. For example, if a user provides highly satisfactory feedback about a recommended expert, that expert may be recommended to other users more frequently.

[0078] The providing unit can send a notification of the relaxation method to the user's smartphone. The notification includes, for example, a push notification, an SMS, an email, and the like, but is not limited to such examples. The providing unit, for example, sends a push notification to the user's smartphone. The providing unit can also send the notification of the relaxation method using an SMS. Furthermore, the providing unit can also send the notification of the relaxation method using an email. This allows the user to immediately receive the relaxation method. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using an AI, or may be performed without using an AI. For example, the providing unit can input the notification of the relaxation method to a generating AI and cause the generating AI to generate the notification content.

[0079] The recommendation unit can make a recommendation based on the evaluation and review of the expert. The evaluation and review include, for example, user evaluation, expert feedback, and the like, but are not limited to such examples. The recommendation unit recommends an expert based on, for example, user evaluation. The recommendation unit can also make a recommendation based on expert feedback. Furthermore, the recommendation unit can also analyze the evaluation and review data and recommend a reliable expert. This allows the user to be recommended a reliable expert. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input the evaluation and review data to the generation AI and cause the generation AI to execute the recommendation of an expert.

[0080] The recommendation unit can adjust the timing of recommending consultation with a specialist based on the user's stress level. The stress level includes, for example, self-report, biofeedback, behavioral data, and the like, but is not limited to such examples. The recommendation unit, for example, evaluates the stress level based on the self-report and adjusts the recommendation timing. The recommendation unit can also evaluate the stress level based on biofeedback data and adjust the recommendation timing. Furthermore, the recommendation unit can evaluate the stress level based on behavioral data and adjust the recommendation timing. This makes it possible to recommend consultation with a specialist at an appropriate timing according to the user's stress level. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input data on the stress level to the generation AI and cause the generation AI to adjust the recommendation timing.

[0081] The providing unit can prepare a relaxing environment in cooperation with the user's smart home device. Smart home devices include, but are not limited to, smart lights, smart speakers, thermostats, etc. The providing unit prepares a relaxing environment, for example, using a smart light. The providing unit can also play relaxing music using a smart speaker. Furthermore, the providing unit can adjust the room temperature using a thermostat. This allows the user to prepare an environment that is easy to relax in. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the control of the smart home device to the generating AI and cause the generating AI to prepare a relaxing environment.

[0082] The suggestion unit can suggest the user's interaction with the pet as a relaxation method. Interaction with the pet includes, for example, walking, playing, touching, etc., but is not limited to such examples. For example, the suggestion unit suggests the user to walk with the pet. The suggestion unit can also suggest the user to play with the pet. Furthermore, the suggestion unit can also suggest the user to touch the pet. This allows the user to relax through interaction with the pet. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input a method of interacting with the pet to the generation AI and cause the generation AI to execute a proposal of a relaxation method.

[0083] The recommendation unit can give priority to recommending experts in the user's area. Local experts include, for example, geographical ranges, fields of expertise, and the like, but are not limited to such examples. For example, the recommendation unit gives priority to recommending experts in the area where the user lives. The recommendation unit can also give priority to recommending experts near the user's workplace. Furthermore, the recommendation unit can make recommendations taking into account the ratings and reviews of experts in the user's area. This allows the user to quickly access local experts. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input data of local experts to the generation AI and cause the generation AI to recommend experts.

[0084] The analysis unit analyzes the genetic information of the user, and the suggestion unit can suggest a relaxation method based on the genetic stress factors of the user. The genetic information includes, for example, DNA sequencing, genetic markers, etc., but is not limited to such examples. The analysis unit analyzes the genetic information of the user using, for example, DNA sequencing technology. The analysis unit can also identify stress factors using genetic markers. The suggestion unit suggests a relaxation method based on the genetic stress factors obtained by the analysis unit. For example, the suggestion unit suggests a relaxation method such as deep breathing or meditation based on the genetic stress factors of the user. This makes it possible to suggest a relaxation method based on the genetic stress factors of the user. A part or all of the above-mentioned processing in the analysis unit and the suggestion unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input data of the genetic information to the generation AI and cause the generation AI to execute an analysis of the stress factors. Also, the suggestion unit can input the analysis result to the generation AI and cause the generation AI to execute a proposal of a relaxation method.

[0085] The reception unit can estimate the user's emotion and adjust the timing of receiving the utterance content based on the estimated user's emotion. The emotion includes, for example, facial expression recognition, voice analysis, self-report, etc., but is not limited to such examples. The reception unit estimates the user's emotion using, for example, facial expression recognition technology. The reception unit can also estimate the emotion using voice analysis technology. Furthermore, the reception unit can estimate the emotion based on the self-report. The reception unit adjusts the timing of receiving the utterance content based on the estimated emotion. For example, when the user is stressed, the reception unit immediately receives the utterance content and responds quickly. Furthermore, when the user is relaxed, the reception unit can also receive the utterance content after a moderate interval. Furthermore, when the user is in a hurry, the reception unit can immediately receive the utterance content and quickly start analyzing it. This makes it possible to receive the utterance content at an appropriate timing according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit may input emotion data to a generation AI and cause the generation AI to adjust the reception timing.

[0086] The reception unit can analyze the user's past speech history and select the optimal reception method. The speech history includes, for example, a text log, a voice record, a time range, and the like, but is not limited to such examples. For example, the reception unit saves the user's past speech history as a text log. The reception unit can also save a voice record and analyze the contents of the past speech. Furthermore, the reception unit can select the optimal reception method in consideration of the time range of the speech. For example, the reception unit preferentially accepts phrases that the user has frequently used in the past. Furthermore, the reception unit can analyze the user's past speech patterns and select the optimal reception timing. Furthermore, the reception unit can preferentially accept specific keywords from the contents of the user's past speech. This makes it possible to select the optimal reception method based on the user's past speech history. A part or all of the above-mentioned 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 data of the speech history to the generation AI and cause the generation AI to select the optimal reception method.

[0087] The reception unit can filter the utterance contents based on the user's current living situation and field of interest when receiving the utterance contents. The living situation includes, for example, occupation, home environment, health condition, etc., but is not limited to such examples. For example, when the user inputs the current living situation, the reception unit filters the utterance contents based on the information. In addition, the reception unit can preferentially receive related utterance contents based on the user's field of interest. Furthermore, the reception unit can filter unnecessary utterance contents based on the user's living situation and field of interest. This makes it possible to filter the utterance contents based on the user's living situation and field of interest. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input data on the living situation and field of interest to the generation AI and cause the generation AI to execute filtering of the utterance contents.

[0088] The reception unit can estimate the user's emotion and determine the priority of the utterance contents to be received based on the estimated user's emotion. The priority includes, for example, urgency, importance, and emotional state, but is not limited to such examples. For example, when the user is stressed, the reception unit preferentially receives utterance contents related to stress. Furthermore, when the user is relaxed, the reception unit can also preferentially receive utterance contents related to relaxation. Furthermore, when the user is in a hurry, the reception unit can also preferentially receive urgent contents. This makes it possible to receive utterance contents in a priority order according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the reception unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the reception unit can input emotion data to the generation AI and cause the generation AI to execute the determination of the priority order of the utterance contents.

[0089] The reception unit can preferentially receive remarks with high relevance based on the geographical location information of the user when receiving the remark contents. The geographical location information includes, for example, GPS data, address information, and the like, but is not limited to such examples. For example, when the user is in a specific area, the reception unit preferentially receives remark contents related to the area. The reception unit can also filter related remark contents based on the geographical location information of the user. Furthermore, when the user is moving, it can also preferentially receive remark contents related to the current location. This makes it possible to preferentially receive remarks with high relevance based on the geographical location information of the user. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input data of the geographical location information to the generation AI and cause the generation AI to execute the determination of the priority order of the remark contents.

[0090] The reception unit can analyze the social media activity of the user when receiving the comment content, and receive related comments. The social media activity includes, but is not limited to, for example, the post content, the number of likes, and the number of followers. The reception unit, for example, analyzes the social media activity of the user, and preferentially receives the related comment content. The reception unit can also filter the comment content based on keywords frequently used by the user on social media. Furthermore, the reception unit can identify a current interest from the user's social media activity, and preferentially receive the related comment content. This makes it possible to receive related comments based on the user's social media activity. A part or all of the above-mentioned processing in the reception unit may be performed, for example, using AI, or may be performed without using AI. For example, the reception unit can input data of the social media activity to the generation AI, and cause the generation AI to filter the comment content.

[0091] The analysis unit can estimate the user's emotion and adjust the expression method of the analysis based on the estimated user's emotion. The expression method includes, for example, wording, tone, and level of detail, but is not limited to such examples. For example, when the user is stressed, the analysis unit uses a concise and easy-to-understand expression method. In addition, when the user is relaxed, the analysis unit can also provide a detailed analysis result. Furthermore, when the user is in a hurry, the analysis unit can also provide an analysis result that focuses on the main points. This makes it possible to provide the analysis result in an appropriate expression method according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input emotion data to the generation AI and cause the generation AI to adjust the expression method.

[0092] The analysis unit can adjust the level of detail of the analysis based on the importance of the comment content during analysis. The importance includes, for example, the user's interest level, urgency, etc., but is not limited to such examples. For example, the analysis unit performs a detailed analysis of comment content with high importance. The analysis unit can also perform a concise analysis of comment content with low importance. Furthermore, the analysis unit can dynamically adjust the level of detail of the analysis according to the importance of the comment content. This allows the analysis to be performed with a level of detail according to the importance of the comment content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input the importance data of the comment content to the generation AI and cause the generation AI to adjust the level of detail of the analysis.

[0093] The analysis unit can apply different analysis algorithms depending on the category of the comment content during analysis. The categories include, for example, topics, themes, genres, etc., but are not limited to such examples. For example, the analysis unit applies a stress analysis algorithm to comment content related to stress. The analysis unit can also apply a relaxation analysis algorithm to comment content related to relaxation. Furthermore, a quick analysis algorithm can be applied to urgent content. This makes it possible to apply an appropriate analysis algorithm depending on the category of the comment content. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can input category data of the comment content to the generation AI and cause the generation AI to apply the analysis algorithm.

[0094] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user's emotion. The length includes, for example, the length of the sentence, the level of detail of the analysis, and the like, but is not limited to such examples. For example, when the user is stressed, the analysis unit performs a short and to the point analysis. In addition, when the user is relaxed, the analysis unit can also perform a detailed analysis. Furthermore, when the user is in a hurry, the analysis unit can also perform a quick analysis. This allows the analysis to be performed at an appropriate length according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input emotion data to the generation AI and cause the generation AI to adjust the length of the analysis.

[0095] The analysis unit can determine the priority of the analysis based on the submission time of the comment content during the analysis. The submission time includes, but is not limited to, for example, a timestamp and a submission date. The analysis unit, for example, prioritizes the analysis of the most recent comment content. The analysis unit can also prioritize the analysis of the current comment content while referring to the past comment content. Furthermore, the analysis unit can dynamically adjust the priority of the analysis based on the submission time. This allows the priority to be determined based on the submission time of the comment content, and the analysis to be performed efficiently. A part or all of the above-mentioned processing in the analysis unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the analysis unit can input data on the submission time to the generation AI and cause the generation AI to determine the priority of the analysis.

[0096] The analysis unit can adjust the order of analysis based on the relevance of the utterance contents during analysis. The relevance includes, for example, the degree of topic agreement, the co-occurrence of keywords, and the like, but is not limited to such examples. For example, the analysis unit prioritizes the analysis of highly relevant utterance contents. The analysis unit can also postpone the analysis of less relevant utterance contents. Furthermore, the analysis unit can dynamically adjust the order of analysis based on the relevance of the utterance contents. This allows the analysis to be efficiently performed by adjusting the order of analysis based on the relevance of the utterance contents. A part or all of the above-mentioned processing in the analysis unit may be performed, for example, using AI, or may be performed without using AI. For example, the analysis unit can input the relevance data of the utterance contents to the generation AI and cause the generation AI to adjust the order of analysis.

[0097] The suggestion unit can estimate the user's emotion and adjust the expression method of the suggestion based on the estimated user's emotion. The expression method of the suggestion includes, for example, wording, tone, and level of detail, but is not limited to such examples. For example, when the user is stressed, the suggestion unit uses a concise and easy-to-understand expression method. In addition, when the user is relaxed, the suggestion unit can also provide a detailed suggestion. Furthermore, when the user is in a hurry, the suggestion unit can also provide a suggestion that focuses on the main points. This allows the suggestion to be made in an appropriate expression method according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input emotion data to the generation AI and cause the generation AI to execute adjustment of the expression method of the suggestion.

[0098] The suggestion unit can adjust the level of detail of the proposal based on the importance of the relaxation method when making a proposal. The level of importance includes, for example, the user's interest level, urgency, etc., but is not limited to such examples. For example, the suggestion unit makes a detailed proposal for a relaxation method with a high level of importance. The suggestion unit can also make a concise proposal for a relaxation method with a low level of importance. Furthermore, the suggestion unit can dynamically adjust the level of detail of the proposal according to the importance of the relaxation method. This makes it possible to make a proposal with a level of detail according to the importance of the relaxation method. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input importance data of the relaxation method to the generation AI and cause the generation AI to adjust the level of detail of the proposal.

[0099] The suggestion unit can apply different suggestion algorithms according to the category of the relaxation method when making a suggestion. The categories include, for example, topics, themes, genres, and the like, but are not limited to such examples. For example, the suggestion unit applies a deep breathing suggestion algorithm to a relaxation method related to deep breathing. The suggestion unit can also apply a music suggestion algorithm to a relaxation method related to music. Furthermore, the suggestion unit can also apply a meditation suggestion algorithm to a relaxation method related to meditation. This makes it possible to apply an appropriate suggestion algorithm according to the category of the relaxation method. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input category data of the relaxation method to the generation AI and cause the generation AI to apply the suggestion algorithm.

[0100] The suggestion unit can estimate the user's emotion and adjust the length of the suggestion based on the estimated user's emotion. The length includes, for example, the length of the sentence, the level of detail of the suggestion, and the like, but is not limited to such examples. For example, when the user is stressed, the suggestion unit makes a short and to the point suggestion. Also, when the user is relaxed, the suggestion unit can make a detailed suggestion. Furthermore, when the user is in a hurry, the suggestion unit can make a quick suggestion. This allows the suggestion to be made at an appropriate length according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the suggestion unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the suggestion unit can input emotion data to the generation AI and cause the generation AI to adjust the length of the suggestion.

[0101] The suggestion unit can determine the priority of the proposal based on the submission time of the relaxation method at the time of proposal. The submission time includes, but is not limited to, for example, a timestamp, a submission date, etc. The suggestion unit, for example, preferentially proposes a recent relaxation method. The suggestion unit can also preferentially propose a current relaxation method while referring to past relaxation methods. Furthermore, the priority of the proposal can be dynamically adjusted based on the submission time. This allows the priority to be determined based on the submission time of the relaxation method, and the proposal can be made efficiently. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input data on the submission time to the generation AI and cause the generation AI to determine the priority of the proposal.

[0102] The suggestion unit can adjust the order of the suggestions based on the relevance of the relaxation methods when making suggestions. The relevance includes, for example, the degree of matching of topics, co-occurrence of keywords, and the like, but is not limited to such examples. For example, the suggestion unit preferentially suggests relaxation methods with high relevance. The suggestion unit can also postpone relaxation methods with low relevance. Furthermore, the suggestion unit can dynamically adjust the order of the suggestions based on the relevance of the relaxation methods. This allows the order of the suggestions to be adjusted based on the relevance of the relaxation methods, and suggestions can be made efficiently. A part or all of the above-mentioned processing in the suggestion unit may be performed, for example, using AI, or may be performed without using AI. For example, the suggestion unit can input relevance data of the relaxation methods to the generation AI, and cause the generation AI to adjust the order of the suggestions.

[0103] The providing unit can estimate the user's emotion and adjust the method of providing the relaxation method based on the estimated user's emotion. The providing method includes, for example, a notification method, a providing means, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the providing unit provides a simple and easy-to-understand relaxation method. In addition, when the user is relaxed, the providing unit can also provide a detailed relaxation method. Furthermore, when the user is in a hurry, a relaxation method that focuses on the main points can be provided. This makes it possible to provide a relaxation method in an appropriate manner according to the user's emotion. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input emotion data to the generation AI and cause the generation AI to execute the adjustment of the provision method.

[0104] The providing unit can select the optimal providing method by referring to the history of the user's past relaxation methods at the time of providing. The history of the relaxation methods includes, for example, past proposal contents, implementation history, etc., but is not limited to such examples. For example, the providing unit selects the optimal providing method based on the relaxation methods used by the user in the past. The providing unit can also analyze the history of the user's past relaxation methods and provide the most effective method. Furthermore, the providing unit can also suggest a new relaxation method while referring to the history of the user's past relaxation methods. This makes it possible to select the optimal providing method based on the history of the user's past relaxation methods. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input the history data of the relaxation methods to the generating AI and cause the generating AI to select the optimal providing method.

[0105] The providing unit can customize the means for providing the relaxation method based on the user's current living situation at the time of providing. The living situation includes, for example, occupation, home environment, health condition, etc., but is not limited to such examples. For example, when the user is busy, the providing unit provides a relaxation method that can be practiced in a short time. In addition, when the user is relaxed, the providing unit can also provide a detailed relaxation method. Furthermore, the providing unit can customize and provide an optimal relaxation method based on the user's living situation. This makes it possible to provide a relaxation method in an appropriate manner according to the user's living situation. Part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input living situation data to the generating AI and cause the generating AI to execute customization of the providing means.

[0106] The providing unit can estimate the user's emotion and determine the priority of providing the relaxation method based on the estimated emotion of the user. The priority includes, for example, urgency, importance, emotional state, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the providing unit can provide a relaxation method that is effective for reducing stress with priority. In addition, when the user is relaxed, the providing unit can also provide a method for maintaining relaxation with priority. Furthermore, when the user is in a hurry, the providing unit can also provide a relaxation method that can be quickly practiced with priority. This makes it possible to provide a relaxation method with priority according to the emotion of the user. The estimation of the emotion is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the providing unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the providing unit can input emotion data to the generation AI and cause the generation AI to execute the determination of the priority of provision.

[0107] The providing unit can provide an appropriate relaxation method based on the geographical location information of the user at the time of providing. The geographical location information includes, for example, GPS data, address information, and the like, but is not limited to such examples. For example, when the user is at home, the providing unit provides a relaxation method that can be practiced at home. In addition, when the user is out, the providing unit can also provide a relaxation method that can be practiced while out. Furthermore, the providing unit can customize and provide an optimal relaxation method based on the geographical location information of the user. This makes it possible to provide an optimal relaxation method based on the geographical location information of the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input geographical location information data to the generating AI and cause the generating AI to execute the provision of the relaxation method.

[0108] At the time of providing, the providing unit can analyze the social media activity of the user and suggest a means for providing a relaxation method. The social media activity includes, for example, the content of posts, the number of likes, the number of followers, etc., but is not limited to such examples. For example, the providing unit analyzes the social media activity of the user and provides a related relaxation method. The providing unit can also suggest a relaxation method based on keywords frequently used by the user on social media. Furthermore, the providing unit can identify a current interest from the social media activity of the user and provide a related relaxation method. In this way, an appropriate relaxation method can be provided based on the social media activity of the user. A part or all of the above-mentioned processing in the providing unit may be performed, for example, using AI, or may be performed without using AI. For example, the providing unit can input social media activity data to the generating AI and cause the generating AI to execute a suggestion of a means for providing a relaxation method.

[0109] The recommendation unit can estimate the user's emotion and adjust the recommendation method of consulting with an expert based on the estimated user's emotion. The recommendation method includes, for example, a notification method, a recommendation means, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the recommendation unit recommends an expert who is effective in reducing stress. In addition, when the user is relaxed, the recommendation unit can also recommend an expert for maintaining relaxation. Furthermore, when the user is in a hurry, the recommendation unit can also recommend an expert who can respond quickly. This makes it possible to recommend consultation with an expert in an appropriate manner according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the recommendation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recommendation unit can input emotion data to the generation AI and cause the generation AI to execute adjustment of the recommendation method.

[0110] The recommendation unit can select the optimal recommendation method by referring to the user's past consultation history at the time of recommendation. The consultation history includes, for example, past consultation content, implementation history, etc., but is not limited to such examples. For example, the recommendation unit recommends the optimal expert based on experts the user has consulted in the past. The recommendation unit can also analyze the user's past consultation history and recommend the most effective expert. Furthermore, the recommendation unit can also recommend a new expert while referring to the user's past consultation history. This makes it possible to select the optimal recommendation method based on the user's past consultation history. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input consultation history data to the generation AI and cause the generation AI to select the optimal recommendation method.

[0111] The recommendation unit can customize the recommendation means for consulting with an expert based on the user's current living situation at the time of recommendation. The living situation includes, for example, occupation, home environment, health condition, etc., but is not limited to such examples. For example, when the user is busy, the recommendation unit recommends an expert who can be consulted online. In addition, when the user is relaxed, the recommendation unit can also recommend an expert who can be consulted face-to-face. Furthermore, the recommendation unit can customize and recommend an optimal expert based on the living situation of the user. This makes it possible to recommend consultation with an expert in an appropriate manner according to the living situation of the user. Part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input living situation data to the generation AI and cause the generation AI to execute customization of the recommendation means.

[0112] The recommendation unit can estimate the user's emotion and determine the priority of the recommendation of consultation with an expert based on the estimated user's emotion. The priority includes, for example, urgency, importance, emotional state, and the like, but is not limited to such examples. For example, when the user is feeling stressed, the recommendation unit preferentially recommends an expert who is effective in reducing stress. In addition, when the user is relaxed, the recommendation unit can also preferentially recommend an expert who helps the user to maintain relaxation. Furthermore, when the user is in a hurry, the recommendation unit can also preferentially recommend an expert who can respond quickly. This makes it possible to recommend consultation with an expert in a priority order according to the user's emotion. The emotion estimation is realized using an emotion estimation function using, for example, an emotion engine or a generation AI. The generation AI is, for example, a text generation AI (for example, LLM) or a multimodal generation AI, but is not limited to such examples. A part or all of the above-mentioned processing in the recommendation unit may be performed using, for example, an AI, or may be performed without using an AI. For example, the recommendation unit can input emotion data to the generation AI and cause the generation AI to execute the determination of the recommendation priority order.

[0113] The recommendation unit can recommend an optimal expert by considering the geographical location information of the user at the time of recommendation. The geographical location information includes, for example, GPS data, address information, and the like, but is not limited to such examples. For example, when the user is at home, the recommendation unit recommends an expert near the user's home. In addition, when the user is out, the recommendation unit can also recommend an expert who can be consulted while out. Furthermore, the recommendation unit can customize and recommend an optimal expert based on the geographical location information of the user. This makes it possible to recommend an optimal expert based on the geographical location information of the user. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI, or may be performed without using AI. For example, the recommendation unit can input geographical location information data to the generation AI and cause the generation AI to execute the recommendation of an expert.

[0114] At the time of recommendation, the recommendation unit can analyze the user's social media activity and suggest a recommended means of consulting an expert. The social media activity includes, but is not limited to, for example, the content of posts, the number of likes, the number of followers, etc. The recommendation unit, for example, analyzes the user's social media activity and recommends a related expert. The recommendation unit can also recommend an expert based on keywords frequently used by the user on social media. Furthermore, the recommendation unit can identify a current interest from the user's social media activity and recommend a related expert. This makes it possible to recommend an appropriate expert based on the user's social media activity. A part or all of the above-mentioned processing in the recommendation unit may be performed, for example, using AI or may be performed without using AI. For example, the recommendation unit can input social media activity data to the generation AI and cause the generation AI to execute a suggestion of a recommended means of an expert.

[0115] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0116] When analyzing the content of a user's statement, the analysis unit can improve the accuracy of the analysis by referring to the user's past statement history. For example, if a user has previously stated that "I'm busy at work," the analysis unit can more accurately analyze the current content of the statement by taking that history into account. Also, if a user has previously stated that "listening to music helps me relax," the analysis unit can optimize suggestions of relaxation methods based on that information. Furthermore, if a user has previously stated that "I would like to consult an expert," the analysis unit can recommend consulting an expert based on that history. This makes it possible to perform more accurate analysis and suggestions by utilizing the user's past statement history.

[0117] When sending a notification of a relaxation method to the user's smartphone, the providing unit can adjust the timing of the notification in consideration of the user's current activity status. For example, if the user is exercising, the providing unit can send the notification after the user finishes exercising. If the user is in a meeting, the providing unit can also send the notification after the meeting ends. Furthermore, if the user is sleeping, the providing unit can also send the notification after the user wakes up. This makes it possible to provide a notification of a relaxation method at an appropriate timing according to the user's activity status.

[0118] When making recommendations based on the evaluations and reviews of experts, the recommendation unit can filter experts based on the individual needs and preferences of the user. For example, if the user desires an expert in a specific field, experts specializing in that field are recommended with priority. In addition, if the user desires an expert of a specific gender or age, experts who meet those conditions can be recommended. Furthermore, experts to whom the user has given good evaluations in the past can be recommended with priority. In this way, experts according to the individual needs and preferences of the user can be recommended.

[0119] When adjusting the timing of recommending a consultation with a specialist based on the user's stress level, the recommendation unit can optimize the recommendation timing by taking into consideration the user's life rhythm and schedule. For example, if the user is prone to feeling stressed at night, the recommendation unit can recommend a consultation with a specialist at night. Also, if the user is prone to relaxing on weekends, the recommendation unit can recommend a consultation with a specialist on weekends. Furthermore, the recommendation unit can recommend a consultation with a specialist in between work by taking into consideration the user's work schedule. This makes it possible to recommend a consultation with a specialist at an appropriate timing according to the user's life rhythm and schedule.

[0120] When the providing unit cooperates with the user's smart home device to prepare a relaxing environment, the providing unit can set the optimal environment in consideration of the user's preferences and past usage history. For example, if the user liked to listen to a particular piece of music in the past, that music can be played. Also, if the user liked a particular lighting setting in the past, that setting can be applied. Furthermore, if the user liked a particular temperature setting in the past, the temperature can be adjusted to that temperature. This makes it possible to provide an optimal relaxing environment based on the user's preferences and past usage history.

[0121] When suggesting interaction with the user's pet as a relaxation method, the suggestion unit can suggest an optimal interaction method based on the type and personality of the user's pet. For example, if the user has a dog, walking or playing can be suggested. Also, if the user has a cat, petting or brushing can be suggested. Furthermore, if the user has a bird, talking to it or feeding it can be suggested. In this way, it is possible to suggest an optimal interaction method according to the type and personality of the user's pet.

[0122] The reception unit can estimate the user's emotions and adjust the timing of receiving the utterance content based on the estimated user's emotions. For example, if the user is feeling stressed, the reception unit can immediately receive the utterance content and respond quickly. Also, if the user is relaxed, the reception unit can receive the utterance content after a suitable interval. Furthermore, if the user is in a hurry, the reception unit can immediately receive the utterance content and start analyzing it quickly. This makes it possible to receive the utterance content at an appropriate timing according to the user's emotions.

[0123] The analysis unit can estimate the user's emotions and adjust the way the analysis is expressed based on the estimated user's emotions. For example, if the user is feeling stressed, a simple and easy-to-understand expression method is used. If the user is relaxed, detailed analysis results can be provided. Furthermore, if the user is in a hurry, analysis results that focus on the main points can be provided. This makes it possible to provide analysis results in an appropriate expression method according to the user's emotions.

[0124] The suggestion unit can estimate the user's emotion and adjust the way of expressing the suggestion based on the estimated user's emotion. For example, if the user is stressed, a concise and easy-to-understand expression is used. If the user is relaxed, a detailed suggestion can be provided. Furthermore, if the user is in a hurry, a suggestion that focuses on the main points can be provided. In this way, the suggestion can be made in an appropriate expression according to the user's emotion.

[0125] The providing unit can estimate the user's emotions and adjust the method of providing the relaxation method based on the estimated user's emotions. For example, if the user is feeling stressed, a simple and easy-to-understand relaxation method can be provided. Also, if the user is relaxed, a detailed relaxation method can be provided. Furthermore, if the user is in a hurry, a relaxation method that focuses on the main points can be provided. In this way, a relaxation method can be provided in an appropriate manner according to the user's emotions.

[0126] The process flow of the second embodiment will be briefly described below.

[0127] Step 1: The reception unit receives the user's utterance. The user's utterance includes, for example, text, voice, and emotional expressions. The reception unit converts the user's utterance into text data using voice recognition technology. The reception unit can also receive text input and can be equipped with a sensor for analyzing emotional expressions. For example, the user's facial expression is captured by a camera, and the emotion is estimated using an emotion estimation algorithm. Step 2: The analysis unit uses AI to analyze the content of the comments received by the reception unit. The analysis is performed using natural language processing technology and sentiment analysis technology. For example, keywords are extracted from the user's comments to identify the cause of stress. Sentiment analysis technology can also be used to understand the user's emotional state. Step 3: The suggestion unit suggests a relaxation method based on the analysis results obtained by the analysis unit. The relaxation methods include deep breathing, meditation, music therapy, etc. For example, if the user says "I want to relax," deep breathing is suggested. Also, if the user says "I want to listen to music," music therapy can be suggested. Step 4: The providing unit provides the user with the relaxation method proposed by the suggesting unit. The providing method includes a notification to a smartphone, guidance by a voice assistant, and cooperation with a smart home device. For example, a notification of the relaxation method is sent to the user's smartphone. Also, the relaxation method can be guided using a voice assistant. Furthermore, a relaxing environment can be created by cooperation with a smart home device. Step 5: The recommendation unit recommends consulting an expert based on the analysis results obtained by the analysis unit. Recommendation methods include a method of taking into account the evaluation and reviews of experts, a method of prioritizing experts in the user's area, and a method of adjusting the recommendation timing based on the user's stress level. For example, a highly reliable expert is recommended based on the evaluation and reviews of experts. It is also possible to give priority to the recommendation of experts in the user's area. Furthermore, it is also possible to adjust the recommendation timing of consulting an expert based on the user's stress level.

[0128] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0129] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. 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 a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) are input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may also be an AI agent. In addition, when the processes of each of the above-mentioned parts are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples.In addition, processing performed by AI including the generation AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI including the generation AI.

[0130] Furthermore, the above-described processing by the data processing system 10 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 required for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information required for processing from the data processing device 12 or an external device.

[0131] For example, the reception unit is realized by the reception device 38 of the smart device 14 and receives the user's utterance contents. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the utterance contents received by the reception unit. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and proposes a relaxation method based on the analysis result. For example, the provision unit is realized by the output device 40 of the smart device 14 and provides the proposed relaxation method to the user. For example, the recommendation unit is realized by the specific processing unit 290 of the data processing device 12 and recommends consulting a specialist based on the analysis result. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0132] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0133] 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.

[0134] 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, the RAM 30, and the 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.

[0135] 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.

[0136] 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 the voice according to instructions from the processor 46.

[0137] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0138] 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 performed in a secure state.

[0139] Fig. 4 shows an example of 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.

[0140] 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.

[0141] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0142] In the smart glasses 214, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. 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 glasses 214 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 also perform processing similar to that of the specific processing unit 290 using these models.

[0143] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0144] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[0145] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0146] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, 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, and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device.

[0147] For example, the reception unit is realized by the microphone 238 of the smart glasses 214 and receives the user's utterance. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the utterance received by the reception unit. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and proposes a relaxation method based on the analysis result. For example, the provision unit is realized by the speaker 240 of the smart glasses 214 and provides the proposed relaxation method to the user. For example, the recommendation unit is realized by the specific processing unit 290 of the data processing device 12 and recommends consulting an expert based on the analysis result. The correspondence between each unit and the device or control unit is not limited to the above-mentioned example, and various changes are possible.

[0148] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0149] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0150] 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, the RAM 30, and the 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.

[0151] 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.

[0152] 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 the voice according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0154] 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 performed in a secure state.

[0155] 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.

[0156] 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.

[0157] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0158] In the headset type terminal 314, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50, and executes the read specific 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 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.

[0159] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0160] 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 voice indicating a user input for 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.

[0161] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0162] 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 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. In addition, 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, and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device.

[0163] For example, the reception unit is realized by the microphone 238 of the headset type terminal 314 and receives the contents of the user's speech. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the contents of the speech received by the reception unit. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and proposes a relaxation method based on the analysis result. For example, the provision unit is realized by the speaker 240 of the headset type terminal 314 and provides the proposed relaxation method to the user. For example, the recommendation unit is realized by the specific processing unit 290 of the data processing device 12 and recommends consulting a specialist based on the analysis result. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0164] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0165] 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.

[0166] 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, the RAM 30, and the 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.

[0167] 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.

[0168] 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 the voice according to instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of a typical healthy person).

[0170] 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 performed in a secure state.

[0171] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and legs. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, and legs. 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.

[0172] 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.

[0173] 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.

[0174] 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 the emotion of the user using the emotion identification model 59 and perform identification processing using the user's emotion. In the emotion estimation function (emotion identification function) using the emotion identification model 59, various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, are performed, but are not limited to such examples. In addition, the estimation and prediction of the emotion also include, for example, analysis of the emotion.

[0175] In the robot 414, the specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads out the specific program 60 from the storage 50, and executes the specific 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 program 60 executed on the RAM 48. The robot 414 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.

[0176] 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 obtains a processing result (such as a prediction result) using the data generation model 58 by communicating with the server device having the data generation model 58. In addition, the data processing device 12 may be a server device, or may be a terminal device (such as a mobile phone, a robot, or a home appliance) owned by a user.

[0177] 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 a voice indicating a user input for 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.

[0178] 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. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image (e.g., still image data or video data) is input. The data generation model 58 infers the input inference data according to the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, and image data. The data generation model 58 includes, for example, a text generation AI, an image generation AI, and a multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing while 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, and in this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. In the data processing device 12 and the like, the data generation model 58 includes a plurality of types, and the data generation model 58 includes an AI other than the generation AI. The AI ​​other than the generation AI is, for example, a linear regression, a logistic regression, a decision tree, a random forest, a support vector machine (SVM), a k-means clustering, a convolutional neural network (CNN), a recurrent neural network (RNN), a generative adversarial network (GAN), or a naive Bayes, and can perform various processes, but is not limited to such examples. The AI ​​may be an AI agent. In addition, when the processes of each part described above are performed by an AI, the processes are performed in part or in whole by the AI, but are not limited to such examples. In addition, the processes performed by the AI ​​including the generation AI may be replaced with rule-based processes, and the rule-based processes may be replaced with processes performed by the AI ​​including the generation AI.

[0179] 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 be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, 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.

[0180] For example, the reception unit is realized by the microphone 238 of the robot 414 and receives the contents of the user's speech. For example, the analysis unit is realized by the specific processing unit 290 of the data processing device 12 and analyzes the contents of the speech received by the reception unit. For example, the suggestion unit is realized by the specific processing unit 290 of the data processing device 12 and suggests a relaxation method based on the analysis result. For example, the provision unit is realized by the speaker 240 of the robot 414 and provides the suggested relaxation method to the user. For example, the recommendation unit is realized by the specific processing unit 290 of the data processing device 12 and recommends consulting a specialist based on the analysis result. The correspondence between each unit and the device or control unit is not limited to the above example, and various changes are possible.

[0181] The emotion identification model 59 as an emotion engine may determine the emotion of the user according to a specific mapping. Specifically, the emotion identification model 59 may determine the emotion of the user according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the emotion of the robot, and the identification processing unit 290 may perform identification processing using the emotion of the robot.

[0182] FIG. 9 is a diagram showing 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. The closer to the center of the concentric circles, the more primitive emotions are arranged. The more outside the concentric circles, the more emotions that represent states and actions that arise from a state of mind are arranged. Emotions are a concept that includes emotions and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions that occur in the brain are arranged. On the right side of the concentric circles, emotions that are generally induced by situational judgment are arranged. On the upper and lower sides of the concentric circles, emotions that are generally generated from reactions that occur in the brain and are induced by situational judgment are arranged. In addition, on the upper side of the concentric circles, emotions of "pleasure" are arranged, and on the lower side, emotions of "discomfort" are arranged. In this way, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0183] These emotions are distributed in the 3 o'clock direction of emotion map 400 and usually 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.

[0184] The inside of emotion map 400 represents what is going on inside one's mind, and the outside of emotion map 400 represents behavior, so the further out you go on emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0185] Here, human emotions are based on various balances such as posture and blood sugar level, and when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. Emotions can also be created for robots, cars, motorcycles, etc., based on various balances such as posture and battery level, so that when these balances are far from the ideal, it indicates an unpleasant state, and when they are close to the ideal, it indicates a pleasant state. The emotion map may be generated, for example, based on the emotion map of Dr. Mitsuyoshi (Research on speech emotion recognition and emotion brain physiological signal analysis system, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). On the left half of the emotion map, emotions belonging to an area called "reaction" where sensation is dominant are lined up. On the right half of the emotion map, emotions belonging to an area called "situation" where situation recognition is dominant are lined up.

[0186] The emotion map defines two emotions that promote learning. The first is the negative emotion around the middle of "repentance" or "remorse" on the situation side. In other words, this is 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 the positive emotion around "desire" on the response side. In other words, this is when the robot has positive feelings such as "I want more" or "I want to know more."

[0187] The emotion identification model 59 inputs the user input to a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the emotion of the user. This neural network is pre-trained based on multiple learning data that are combinations of the 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, "relief," "calm," and "encouraging," have similar emotion values.

[0188] 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.

[0189] 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 Universal Serial Bus (USB) 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.

[0190] In addition, 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 upon request from the data processing device 12.

[0191] 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.

[0192] As the hardware resource for executing the specific process, various processors as shown below can be used. An example of the processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing the specific process by executing software, i.e., a program. Another example of the processor is a dedicated electric circuit, which is a processor having a circuit configuration designed exclusively for executing a specific process, such as a Field-Programmable Gate Array (FPGA), a Programmable Logic Device (PLD), or an Application Specific Integrated Circuit (ASIC). Each processor has a built-in or connected memory, and each processor executes the specific process by using the memory.

[0193] The hardware resource that executes the specific process may be one of these various processors, or may be 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.

[0194] As an example of a configuration using one 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 configuration using a processor that realizes the functions of the 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.

[0195] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements. The specific processes described above are merely examples. It goes without saying that unnecessary steps may be deleted, new steps may be added, or the order of processes may be changed without departing from the spirit of the invention.

[0196] In the above example, the first to fourth embodiments are described separately, but some or all of these embodiments may be combined. The smart device 14, the smart glasses 214, the headset terminal 314, and the robot 414 are only examples, and they may be combined with each other, or may be other devices. In the above example, the first and second embodiments are described separately, but they may be combined.

[0197] The above description and illustrations are detailed descriptions 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, function, action, and effect is an example of the configuration, function, action, and effect 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 replaced with respect to the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. In addition, in order to avoid confusion and to facilitate understanding of the parts related to the technology of the present disclosure, the description and illustrations shown above omit explanations of technical common sense that do not require particular explanation in enabling the implementation of the technology of the present disclosure.

[0198] All publications, patent applications, and standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, and standard was specifically and individually indicated to be incorporated by reference.

[0199] (Appendix 1) A reception unit that receives the contents of a user's comment; an analysis unit that analyzes the content of the statement received by the reception unit; a suggestion unit that suggests a relaxation method based on the analysis result obtained by the analysis unit; a providing unit that provides a user with the relaxation method suggested by the suggestion unit; A recommendation unit that recommends consultation with an expert based on the analysis result obtained by the analysis unit. A system characterized by: (Appendix 2) The providing unit is Sending relaxation tips to the user's smartphone 2. The system of claim 1, (Appendix 3) The recommendation unit, Make recommendations based on expert ratings and reviews 2. The system of claim 1, (Appendix 4) The recommendation unit, Adjusting the timing of recommendations for consultation based on the user's stress level 2. The system of claim 1, (Appendix 5) The providing unit is Linking with the user's smart home devices to create a relaxing environment 2. The system of claim 1, (Appendix 6) The suggestion unit, Proposes that users interact with their pets as a way to relax 2. The system of claim 1, (Appendix 7) The recommendation unit, Prioritize recommendations of experts in the user's area 2. The system of claim 1, (Appendix 8) The analysis unit is Analyze the user's genetic information, The suggestion unit, Suggest relaxation methods based on the user's genetic stress factors 2. The system of claim 1, (Appendix 9) The reception unit is Estimate the user's emotions and adjust the timing of accepting utterances based on the estimated user emotions 2. The system of claim 1, (Appendix 10) The reception unit is Analyze the user's past speech history and select the appropriate reception method 2. The system of claim 1, (Appendix 11) The reception unit is When comments are received, they are filtered based on the user's current life situation and areas of interest. 2. The system of claim 1, (Appendix 12) The reception unit is Estimate the user's emotions and determine the priority of the utterances to be accepted based on the estimated user emotions. 2. The system of claim 1, (Appendix 13) The reception unit is When accepting comments, the system prioritizes comments that are highly relevant based on the user's geographic location information. 2. The system of claim 1, (Appendix 14) The reception unit is When receiving a comment, analyze the user's social media activity and receive related comments. 2. The system of claim 1, (Appendix 15) The analysis unit is Infer user emotions and adjust the presentation of analytics based on the inferred user emotions 2. The system of claim 1, (Appendix 16) The analysis unit is During analysis, adjust the level of detail of the analysis based on the importance of the content of the statement 2. The system of claim 1, (Appendix 17) The analysis unit is During analysis, different analysis algorithms are applied depending on the category of the speech content. 2. The system of claim 1, (Appendix 18) The analysis unit is Infer user sentiment and adjust the length of the analysis based on the inferred user sentiment 2. The system of claim 1, (Appendix 19) The analysis unit is During analysis, prioritize analysis based on when comments were submitted 2. The system of claim 1, (Appendix 20) The analysis unit is During analysis, adjust the order of analysis based on the relevance of what is being said 2. The system of claim 1, (Appendix 21) The suggestion unit, Infer user emotions and adjust the presentation of suggestions based on the inferred user emotions 2. The system of claim 1, (Appendix 22) The suggestion unit, When making suggestions, adjust the detail of the suggestions based on the importance of the relaxation method 2. The system of claim 1, (Appendix 23) The suggestion unit, When making suggestions, different suggestion algorithms are applied depending on the category of relaxation method. 2. The system of claim 1, (Appendix 24) The suggestion unit, Infer user sentiment and adjust the length of suggestions based on the estimated user sentiment 2. The system of claim 1, (Appendix 25) The suggestion unit, When making a proposal, prioritize the proposal based on when the relaxation method was submitted 2. The system of claim 1, (Appendix 26) The suggestion unit, During suggestions, adjust the order of suggestions based on the relevance of relaxation methods 2. The system of claim 1, (Appendix 27) The providing unit is To estimate a user's emotion and adjust a method of providing a relaxation method based on the estimated user's emotion. 2. The system of claim 1, (Appendix 28) The providing unit is When providing the service, the system selects the optimal method by referring to the user's past relaxation method history. 2. The system of claim 1, (Appendix 29) The providing unit is At the time of delivery, the means of providing relaxation methods is customized based on the user's current life situation. 2. The system of claim 1, (Appendix 30) The providing unit is A user's emotion is estimated, and a priority order for providing relaxation methods is determined based on the estimated user's emotion. 2. The system of claim 1, (Appendix 31) The providing unit is When provided, the system provides appropriate relaxation techniques based on the user's geographic location. 2. The system of claim 1, (Appendix 32) The providing unit is At the time of provision, the service analyzes the user's social media activity to suggest ways to provide relaxation methods. 2. The system of claim 1, (Appendix 33) The recommendation unit, To estimate a user's emotion and adjust a method of recommending a consultation with an expert based on the estimated user's emotion. 2. The system of claim 1, (Appendix 34) The recommendation unit, When making a recommendation, the system selects the optimal recommendation method by referring to the user's past consultation history. 2. The system of claim 1, (Appendix 35) The recommendation unit, At the time of recommendation, customize the expert consultation recommendation method based on the user's current life situation. 2. The system of claim 1, (Appendix 36) The recommendation unit, To estimate a user's emotion and determine a priority order for recommending consultations with an expert based on the estimated user's emotion. 2. The system of claim 1, (Appendix 37) The recommendation unit, When making recommendations, the system considers the user's geographic location to recommend the most suitable expert. 2. The system of claim 1, (Appendix 38) The recommendation unit, At the time of recommendation, the system analyzes the user's social media activity to suggest expert consultation recommendations. 2. The system of claim 1, [Explanation of symbols]

[0200] 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 contents of a user's comment; an analysis unit that analyzes the content of the statement received by the reception unit; a suggestion unit that suggests a relaxation method based on the analysis result obtained by the analysis unit; a providing unit that provides a user with the relaxation method suggested by the suggestion unit; A recommendation unit that recommends consultation with an expert based on the analysis result obtained by the analysis unit. A system characterized by:

2. The providing unit is Sending relaxation tips to the user's smartphone 2. The system of claim 1 .

3. The recommendation unit, Make recommendations based on expert ratings and reviews 2. The system of claim 1 .

4. The recommendation unit, Adjusting the timing of recommendations for consultation based on the user's stress level 2. The system of claim 1 .

5. The providing unit is Linking with the user's smart home devices to create a relaxing environment 2. The system of claim 1 .

6. The suggestion unit, Proposes that users interact with their pets as a way to relax 2. The system of claim 1 .

7. The recommendation unit, Prioritize recommendations of experts in the user's area 2. The system of claim 1 .

8. The analysis unit is Analyze the user's genetic information, The suggestion unit, Suggest relaxation methods based on the user's genetic stress factors 2. The system of claim 1 .

9. The reception unit is Estimate the user's emotions and adjust the timing of accepting utterances based on the estimated user emotions 2. The system of claim 1 .

10. The reception unit is Analyze the user's past speech history and select the appropriate reception method 2. The system of claim 1 .

Images