system

Abstract

The system according to the embodiment aims to provide appropriate advice for the problem of the person seeking advice and quickly match the person with professional assistance as needed. [Solution] A system according to an embodiment includes an analysis unit, an advice unit, and a matching unit. The analysis unit analyzes the natural language input of the client. The advice unit provides appropriate advice based on the problem analyzed by the analysis unit. The matching unit matches professional assistance when the advice provided by the advice unit is insufficient.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies have had the problem of making it difficult to provide appropriate advice to clients regarding their problems, and are unable to respond quickly when professional assistance is required.

[0005] The system according to the embodiment aims to provide appropriate advice for the problem of the person seeking advice and quickly match the person with professional assistance as needed. [Means for solving the problem]

[0006] The system according to the embodiment includes an analysis unit, an advice unit, and a matching unit. The analysis unit analyzes the natural language input of the client. The advice unit provides appropriate advice based on the problem analyzed by the analysis unit. The matching unit matches professional assistance when the advice provided by the advice unit is insufficient. [Effects of the Invention]

[0007] The system according to the embodiment can provide appropriate advice for the problem of the person seeking advice and can quickly match the person with professional assistance as needed. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) A mental healthcare system according to an embodiment of the present invention analyzes a client's natural language input, provides optimal advice, and matches them with professional assistance as needed. This mental healthcare system begins with the client inputting their problems and concerns in natural language. Next, a generation AI analyzes the input, learns from past cases, and provides optimal advice. For example, a client experiencing stress or anxiety might be offered relaxation and stress management advice. However, the generation AI's natural language processing technology has limitations, and it cannot solve all problems. Therefore, the generation AI also has the ability to match clients with in-person, case-specific professional assistance. For example, a client with serious mental health issues might be recommended to consult with a professional counselor or doctor. This mechanism allows the generation AI to provide prompt and appropriate advice to the client, enabling them to receive professional assistance as needed. This is expected to improve the client's mental health. This allows the mental healthcare system to quickly and appropriately analyze the client's problems, provide optimal advice, and match them with professional assistance as needed.

[0029] A mental health care system according to an embodiment includes an analysis unit, an advice unit, and a matching unit. The analysis unit analyzes a natural language input from a client. The natural language input from a client includes, but is not limited to, text, voice, and chat messages. The analysis unit, for example, uses morphological analysis to segment the input text, performs grammatical analysis, and identifies the client's problems and concerns through semantic analysis. For example, the analysis unit analyzes the text input by the client, "I've been so stressed lately that I can't sleep," to identify stress and sleep problems. The analysis unit can also use speech recognition technology to analyze voice input. For example, if a client verbally inputs, "I'm feeling anxious because of the high pressure at work," the analysis unit converts the voice into text and performs a similar analysis. The advice unit uses a generation AI to provide optimal advice based on the problem analyzed by the analysis unit. The advice unit, for example, learns from past cases and generates appropriate advice for the identified problem. For example, the advice unit provides relaxation techniques for stress management and advice on improving sleep. The advice unit can also use the generation AI to provide specific procedures and reference materials for the problem of the person seeking advice. For example, the advice unit may provide advice on breathing techniques to relieve stress or environmental settings to improve sleep quality. The matching unit matches the person with professional assistance when the advice provided by the advice unit is insufficient. If the matching unit determines that the advice is insufficient based on, for example, the accuracy of the advice or the person's satisfaction, the matching unit recommends face-to-face consultation with a professional counselor or doctor. For example, the matching unit arranges a meeting with a professional counselor for a person with serious mental health issues. The matching unit can also use the generation AI to select a professional best suited to the person's problem. For example, the matching unit matches the person with a stress management expert or a sleep disorder specialist depending on the person's problem. In this way, the mental health care system according to the embodiment can analyze the person's problem, provide optimal advice, and match professional assistance as needed.

[0030] The analysis unit can analyze the client's natural language input and identify their problems and concerns. For example, the analysis unit uses morphological analysis to segment the input text, perform grammatical analysis, and identify the client's problems and concerns through semantic analysis. For example, the analysis unit can analyze the client's input text, "I've been so stressed lately I can't sleep," to identify stress and sleep problems. The analysis unit can also use speech recognition technology to analyze voice input. For example, if the client verbally inputs, "I'm feeling anxious because of the pressure at work," the analysis unit converts the speech into text and performs the same analysis. This allows the client's problems and concerns to be identified and appropriate advice to be provided. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the client's input data into the generation AI and have the generation AI identify the client's problems and concerns.

[0031] The advice unit can learn from past cases and provide appropriate advice based on the identified problem. The advice unit, for example, learns from past cases and generates appropriate advice for the identified problem. For example, the advice unit provides relaxation methods for stress management or advice for improving sleep. The advice unit can also use a generation AI to provide specific procedures and reference materials for the client's problem. For example, the advice unit provides advice on breathing techniques for stress relief or environmental settings for improving sleep quality. This improves the accuracy of advice by learning from past cases. Some or all of the above-mentioned processing in the advice unit may be performed using or without the generation AI. For example, the advice unit can input past case data into the generation AI and cause the generation AI to generate advice.

[0032] The matching unit can match professional assistance when the advice provided by the advising unit is insufficient. The matching unit recommends face-to-face consultation with a professional counselor or doctor when the advice is determined to be insufficient, for example, based on the accuracy of the advice or the client's satisfaction. For example, the matching unit arranges a meeting with a professional counselor for a client with serious mental health issues. The matching unit can also use the generation AI to select a professional best suited to the client's problem. For example, the matching unit matches a stress management expert or a sleep disorder specialist depending on the client's problem. This makes it possible to provide professional assistance when the advice is insufficient. Some or all of the above-mentioned processing in the matching unit may be performed using or without the generation AI. For example, the matching unit can input the accuracy of the advice and the client's satisfaction into the generation AI and have the generation AI select a professional.

[0033] The analysis unit can collect and learn input data from the client. For example, the analysis unit stores the input data from the client in a database and periodically collects data. For example, the analysis unit collects text data and voice data entered by the client and stores it in a database. The analysis unit can also use the collected data to train the generation AI. For example, the analysis unit inputs the collected data into the generation AI, and the generation AI learns from the data, thereby improving the accuracy of the analysis. In this way, the accuracy of the analysis is improved by collecting and learning from the input data from the client. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the collected data into the generation AI and have the generation AI learn from the data.

[0034] The advice unit can improve the quality of advice based on the collected data. The advice unit improves the quality of advice by, for example, using the collected data to train the generation AI. For example, the advice unit inputs the collected data into the generation AI, and the generation AI learns from the data, thereby improving the accuracy of the advice. The advice unit can also collect feedback and set evaluation criteria for advice. For example, the advice unit collects feedback from the client and sets criteria for evaluating the quality of the advice. This makes it possible to provide more appropriate advice by improving the quality of the advice based on the collected data. Some or all of the above-mentioned processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit can input the collected data into the generation AI and cause the generation AI to improve the quality of the advice.

[0035] The analysis unit can analyze the client's past consultation history and select an appropriate analysis method. For example, if the client has previously consulted about a similar problem, the generation AI analyzes that history and selects a similar analysis method. For example, if the client has previously consulted about "not being able to sleep due to work stress," the analysis unit selects a similar analysis method based on that history. Furthermore, if the client has previously consulted about a different problem, the generation AI analyzes that history and selects a different analysis method. For example, if the client has previously consulted about "feeling anxious about family problems," the analysis unit selects a different analysis method based on that history. Furthermore, if the client has previously consulted about multiple problems, the analysis unit analyzes that history and selects the most effective analysis method. For example, if the client has previously consulted about both "work stress" and "family problems," the generation AI selects the optimal analysis method based on that history. In this way, the optimal analysis method can be selected by analyzing the past consultation history. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input past consultation history data into the generation AI and have the generation AI select an analysis method.

[0036] The analysis unit can evaluate the urgency of the problem based on the client's input and determine the priority of analysis. For example, if the client inputs an urgent problem, the generation AI analyzes the content, rates it as highly urgent, and prioritizes its analysis. For example, if the client inputs "I need help right now," the generation AI rates it as highly urgent and prioritizes its analysis. Furthermore, if the client inputs a general problem, the analysis unit analyzes the content, rates it as less urgent, and prioritizes its analysis. For example, if the client inputs "I've been feeling a little stressed lately," the generation AI rates it as less urgent and prioritizes its analysis. Furthermore, if the client inputs multiple problems, the analysis unit analyzes the content, evaluates the urgency of each problem, and determines its priority. For example, if the client inputs "I'm struggling with both work stress and family problems," the generation AI evaluates the urgency of each problem and prioritizes it. This allows for prioritization by evaluating the urgency of the problems, enabling prompt responses. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input the client's input data into the generation AI and have the generation AI evaluate the urgency and determine the priority.

[0037] The analysis unit can analyze region-specific issues by taking into account the geographic location information of the client. For example, if the client lives in a specific region, the generation AI performs the analysis by taking into account the region's specific issues. For example, if the client inputs, "I'm worried because the security situation in my region is bad," the generation AI performs the analysis by taking into account the security information for that region. Furthermore, if the client lives in a different region, the generation AI performs the analysis by taking into account the region's specific issues. For example, if the client inputs, "I'm worried because I moved to a new region," the generation AI performs the analysis by taking into account the region's specific issues. Furthermore, if the client has issues related to multiple regions, the generation AI performs the analysis by taking into account the region's specific issues. For example, if the client inputs, "I'm worried because I travel between multiple regions for work," the generation AI performs the analysis by taking into account the region's specific issues. This analysis of region-specific issues allows for more appropriate advice to be provided. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the geographical location information of the client into the generation AI and have the generation AI perform an analysis of problems specific to the region.

[0038] The analysis unit can analyze the social media activity of the client and identify related problems. For example, the analysis unit uses a generation AI to analyze content posted by the client on social media and identify related problems. For example, if the client posts, "I'm feeling stressed because of slander on social media," the generation AI analyzes the content and identifies the stress issue. The analysis unit can also analyze comments received by the client on social media and identify related problems. For example, if the client posts, "I'm worried because of comments on social media," the generation AI analyzes the comment and identifies the anxiety issue. The analysis unit can also analyze the content of accounts the client follows on social media and identify related problems. For example, if the client posts, "My self-esteem is low because of the accounts I follow on social media," the generation AI analyzes the content of the account and identifies the self-esteem issue. In this way, related problems can be identified by analyzing social media activity. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the client's social media data into the generation AI and have the generation AI identify related issues.

[0039] When providing advice, the advice unit can improve the accuracy of the advice by referring to past case data. For example, the generation AI refers to past case data and provides optimal advice for a similar problem. For example, the advice unit refers to past cases where a person consulted about "not being able to sleep due to work stress" and provides optimal advice for a similar problem. The advice unit can also refer to past case data and provide optimal advice for a different problem. For example, the advice unit refers to past cases where a person consulted about "feeling anxious about family problems" and provides optimal advice for a different problem. Furthermore, the advice unit can also refer to past case data and provide optimal advice for multiple problems. For example, the advice unit refers to past cases where a person consulted about both "work stress" and "family problems" and provides optimal advice for multiple problems. By referring to past case data, the accuracy of the advice can be improved. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit can input past case data into the generation AI and cause the generation AI to improve the accuracy of the advice.

[0040] When providing advice, the advice unit can apply different advice algorithms depending on the category of the client's problem. For example, if the client has a stress management problem, the generation AI of the advice unit applies an advice algorithm specialized for stress management. For example, the advice unit provides breathing techniques and relaxation methods for stress relief. Furthermore, if the client has an anxiety relief problem, the generation AI applies an advice algorithm specialized for anxiety relief. For example, the advice unit provides cognitive behavioral therapy techniques and relaxation techniques for reducing anxiety. Furthermore, if the client has a relaxation problem, the advice unit applies an advice algorithm specialized for relaxation. For example, the advice unit provides meditation techniques and yoga techniques for relaxation. In this way, by applying different advice algorithms depending on the category of the problem, more appropriate advice can be provided. Some or all of the above-mentioned processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit may input the category of the client's problem into the generation AI and cause the generation AI to apply the advice algorithm.

[0041] When providing advice, the advice unit can determine the priority of the advice based on the time of submission by the client. For example, if the client submits an urgent problem, the generation AI prioritizes the advice by taking into account the time of submission. For example, if the client inputs "I need help right now," the generation AI prioritizes the advice by taking into account the time of submission. Furthermore, if the client submits a general problem, the generation AI provides advice at normal priority by taking into account the time of submission. For example, if the client inputs "I've been feeling a little stressed lately," the generation AI provides advice at normal priority by taking into account the time of submission. Furthermore, if the client submits multiple problems, the advice unit determines the priority of each problem by taking into account the time of submission. For example, if the client inputs "I'm struggling with both work stress and family problems," the generation AI determines the priority of each problem by taking into account the time of submission. This enables a rapid response by prioritizing advice based on the time of submission. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit may input the client's submission time data into the generation AI and have the generation AI determine the priority of advice.

[0042] When providing advice, the advice unit can adjust the order of advice based on the relevance of the advice to the client. For example, if the client submits multiple related problems, the generation AI considers the relevance and provides advice in the optimal order. For example, if the client inputs, "I'm struggling with both work stress and family problems," the generation AI considers the relevance and provides advice in the optimal order. Furthermore, if the client submits multiple less related problems, the advice unit can adjust the order by considering the relevance. For example, if the client inputs, "work stress" and "no time for hobbies," the generation AI considers the relevance and adjusts the order. Furthermore, if the client submits multiple highly related problems, the advice unit prioritizes providing advice by considering the relevance. For example, if the client inputs, "work stress" and "interpersonal problems at work," the generation AI considers the relevance and provides advice. This allows for more appropriate advice to be provided by adjusting the order of advice based on relevance. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit can input relevant data about the client's problem to the generation AI and have the generation AI adjust the order of advice.

[0043] When matching, the matching unit can select an appropriate professional by referring to the client's past consultation history. For example, if the client has previously consulted about a similar problem, the generation AI refers to that history and selects the same professional. For example, if the client previously consulted about "not being able to sleep due to work stress," the same stress management expert is selected based on that history. Furthermore, if the client previously consulted about a different problem, the matching unit can select a different professional by referring to that history. For example, if the client previously consulted about "feeling anxious about family issues," the matching unit can select a different expert based on that history. Furthermore, if the client previously consulted about multiple issues, the matching unit can select the most effective professional by referring to that history. For example, if the client previously consulted about both "work stress" and "family issues," the matching unit can select the most appropriate professional based on that history. In this way, the optimal professional can be selected by referring to the past consultation history. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit can input past consultation history data into the generation AI and have the generation AI select a professional.

[0044] The matching unit can determine the matching priority based on the urgency of the client's problem during matching. For example, if the client has an urgent problem, the generation AI evaluates the urgency and prioritizes matching with a professional. For example, if the client inputs, "I need help right now," the generation AI evaluates the urgency as high and prioritizes matching with a professional. Furthermore, if the client has a general problem, the generation AI evaluates the urgency and prioritizes matching with a professional. For example, if the client inputs, "I've been feeling a little stressed lately," the generation AI evaluates the urgency as low and prioritizes matching with a professional. Furthermore, if the client has multiple problems, the matching unit evaluates the urgency of each problem and prioritizes each problem. For example, if the client inputs, "I'm struggling with both work stress and family problems," the generation AI evaluates the urgency of each problem and prioritizes them. This enables a rapid response by prioritizing matching based on the urgency of the problem. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit can input the urgency data of the client's problem into the generation AI and have the generation AI determine the matching priority.

[0045] The matching unit can select the most appropriate professional by taking into account the geographic location information of the client during matching. For example, if the client lives in a specific area, the generation AI prioritizes selecting professionals in that area. For example, if the client inputs, "I'm worried because the security situation in my area is bad," the generation AI selects a professional by taking into account the security information for that area. Furthermore, if the client lives in a different area, the matching unit selects professionals in that area. For example, if the client inputs, "I'm worried because I moved to a new area," the generation AI selects a professional in that area. Furthermore, if the client has issues related to multiple areas, the matching unit selects professionals in each area. For example, if the client inputs, "I'm worried because I travel between multiple areas for work," the generation AI selects professionals in each area. This allows for a more appropriate professional to be selected by taking geographic location information into account. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit may input the client's geographic location information into the generation AI and have the generation AI select a professional.

[0046] The matching unit can analyze the social media activity of the client and identify relevant professionals when matching. For example, the generation AI analyzes the content posted by the client on social media to identify relevant professionals. For example, if the client posts, "I'm feeling stressed because of slander on social media," the generation AI analyzes the content and identifies a stress management specialist. The matching unit can also analyze comments received by the client on social media to identify relevant professionals. For example, if the client posts, "I'm worried because of the comments on social media," the generation AI analyzes the comment and identifies an anxiety relief specialist. The matching unit can also analyze the content of accounts followed by the client on social media to identify relevant professionals. For example, if the client posts, "My self-esteem is low because of the accounts I follow on social media," the generation AI analyzes the content of the accounts and identifies the problem with self-esteem. In this way, relevant professionals can be identified by analyzing social media activity. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit can input the client's social media data into the generation AI and have the generation AI identify relevant professionals.

[0047] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0048] The analysis unit can monitor the client's input data in real time and detect abnormal patterns. For example, if the client consults at a frequency that differs from their usual pattern, the generation AI will detect the abnormality and respond promptly. The analysis unit can also detect abnormal emotional fluctuations based on the client's input. For example, if the client suddenly begins to express more negative emotions, the generation AI will detect the change and provide appropriate advice. The analysis unit can also compare the client's input data with the data of other clients to identify abnormal patterns. For example, if the client shows an abnormally high stress level compared to other clients, the generation AI will identify the abnormality and respond promptly. This enables real-time monitoring and anomaly detection, enabling prompt and appropriate responses.

[0049] The advice unit can collect lifestyle data from the client to improve the accuracy of advice. For example, data is collected from a wearable device used daily by the client, and the generation AI analyzes the data to provide advice. The advice unit can also collect data on the client's diet and exercise to provide health management advice. For example, if the client enters a diet record, the generation AI analyzes the data and provides advice on nutritional balance. Furthermore, the advice unit can collect the client's sleep data to provide advice on improving sleep. For example, if the client records their sleep quality, the generation AI analyzes the data and provides methods for improving their sleep environment. In this way, by utilizing lifestyle data, more specific and effective advice can be provided.

[0050] The matching unit can select the most appropriate professional by taking into account the occupational information of the client. For example, if the client is engaged in a specific occupation, the generation AI will prioritize selecting experts related to that occupation. For example, if the client is a medical professional, the generation AI will match the client with an expert who is knowledgeable about the mental health of medical professionals. The matching unit can also select an appropriate professional by taking into account stress factors related to the client's occupation. For example, if the client is a teacher, the matching unit will match the client with an expert who is knowledgeable about stress in the educational field. Furthermore, the matching unit can select a professional who offers counseling methods tailored to the client's occupation. For example, if the client is an engineer, the matching unit will match the client with an expert who offers stress management methods specific to technical jobs. This makes it possible to select a more appropriate professional by taking into account occupational information.

[0051] The analysis unit can anonymize the data input by the client and perform analysis while protecting data privacy. For example, the analysis unit can delete the client's personal information and have the generation AI analyze the anonymized data. In addition to anonymizing the data, the analysis unit can also encrypt the data. For example, the analysis unit can encrypt the client's input data and have the generation AI analyze the encrypted data. In addition to anonymizing and encrypting the data, the analysis unit can also control access to the data. For example, the analysis unit can allow only users with specific permissions to access the data and have the generation AI analyze the access-controlled data. This allows the client's data to be analyzed safely while protecting data privacy.

[0052] The advice unit can adjust the content of the advice taking into account the cultural background of the person seeking advice. For example, if the person seeking advice belongs to a particular cultural sphere, the generation AI will provide advice appropriate to that culture. For example, if the person seeking advice belongs to an Asian cultural sphere, traditional Asian relaxation techniques will be provided. The advice unit can also adjust the content of the advice taking into account the person's religious background. For example, if the person seeking advice believes in a particular religion, advice appropriate to that religion will be provided. Furthermore, the advice unit can adjust the way the advice is expressed taking into account the person's language background. For example, if the person seeking advice does not have English as their native language, advice will be provided in simple, easy-to-understand language. This makes it possible to provide more appropriate and effective advice by taking cultural background into account.

[0053] The processing flow of the first embodiment will be briefly explained below.

[0054] Step 1: The analysis unit analyzes the client's natural language input. The client's natural language input includes text, voice, chat messages, etc. The analysis unit uses morphological analysis to segment the input text, performs grammatical analysis, and identifies the client's problems and worries through semantic analysis. For example, the analysis unit analyzes the text input by the client, "I've been so stressed lately I can't sleep," to identify stress and sleep problems. Speech recognition technology can also be used to analyze voice input. For example, if the client inputs, "I'm feeling anxious because of the high pressure at work," the analysis unit converts the voice into text and performs the same analysis. Step 2: The advice unit uses the generation AI to provide optimal advice based on the problem analyzed by the analysis unit. The advice unit learns from past cases and generates appropriate advice for the identified problem. For example, it may provide relaxation techniques for stress management or advice on how to improve sleep. The generation AI can also be used to provide specific steps and reference materials for the client's problem. For example, it may provide advice on breathing techniques to relieve stress or environmental settings to improve sleep quality. Step 3: The Matching Department matches professional assistance if the advice provided by the Advice Department is insufficient. If the advice is deemed insufficient based on the accuracy of the advice and the client's satisfaction, the Matching Department recommends face-to-face consultation with a professional counselor or doctor. For example, it arranges a meeting with a professional counselor for a client with serious mental health issues. Generative AI can also be used to select the professional best suited to the client's problem. For example, it can match the client with a stress management expert or a sleep disorder specialist.

[0055] (Example 2) A mental healthcare system according to an embodiment of the present invention analyzes a client's natural language input, provides optimal advice, and matches them with professional assistance as needed. This mental healthcare system begins with the client inputting their problems and concerns in natural language. Next, a generation AI analyzes the input, learns from past cases, and provides optimal advice. For example, a client experiencing stress or anxiety might be offered relaxation and stress management advice. However, the generation AI's natural language processing technology has limitations, and it cannot solve all problems. Therefore, the generation AI also has the ability to match clients with in-person, case-specific professional assistance. For example, a client with serious mental health issues might be recommended to consult with a professional counselor or doctor. This mechanism allows the generation AI to provide prompt and appropriate advice to the client, enabling them to receive professional assistance as needed. This is expected to improve the client's mental health. This allows the mental healthcare system to quickly and appropriately analyze the client's problems, provide optimal advice, and match them with professional assistance as needed.

[0056] A mental health care system according to an embodiment includes an analysis unit, an advice unit, and a matching unit. The analysis unit analyzes a natural language input from a client. The natural language input from a client includes, but is not limited to, text, voice, and chat messages. The analysis unit, for example, uses morphological analysis to segment the input text, performs grammatical analysis, and identifies the client's problems and concerns through semantic analysis. For example, the analysis unit analyzes the text input by the client, "I've been so stressed lately that I can't sleep," to identify stress and sleep problems. The analysis unit can also use speech recognition technology to analyze voice input. For example, if a client verbally inputs, "I'm feeling anxious because of the high pressure at work," the analysis unit converts the voice into text and performs a similar analysis. The advice unit uses a generation AI to provide optimal advice based on the problem analyzed by the analysis unit. The advice unit, for example, learns from past cases and generates appropriate advice for the identified problem. For example, the advice unit provides relaxation techniques for stress management and advice on improving sleep. The advice unit can also use the generation AI to provide specific procedures and reference materials for the problem of the person seeking advice. For example, the advice unit may provide advice on breathing techniques to relieve stress or environmental settings to improve sleep quality. The matching unit matches the person with professional assistance when the advice provided by the advice unit is insufficient. If the matching unit determines that the advice is insufficient based on, for example, the accuracy of the advice or the person's satisfaction, the matching unit recommends face-to-face consultation with a professional counselor or doctor. For example, the matching unit arranges a meeting with a professional counselor for a person with serious mental health issues. The matching unit can also use the generation AI to select a professional best suited to the person's problem. For example, the matching unit matches the person with a stress management expert or a sleep disorder specialist depending on the person's problem. In this way, the mental health care system according to the embodiment can analyze the person's problem, provide optimal advice, and match professional assistance as needed.

[0057] The analysis unit can analyze the client's natural language input and identify their problems and concerns. For example, the analysis unit uses morphological analysis to segment the input text, perform grammatical analysis, and identify the client's problems and concerns through semantic analysis. For example, the analysis unit can analyze the client's input text, "I've been so stressed lately I can't sleep," to identify stress and sleep problems. The analysis unit can also use speech recognition technology to analyze voice input. For example, if the client verbally inputs, "I'm feeling anxious because of the pressure at work," the analysis unit converts the speech into text and performs the same analysis. This allows the client's problems and concerns to be identified and appropriate advice to be provided. Some or all of the above-described processing in the analysis unit may be performed using or without the generation AI. For example, the analysis unit can input the client's input data into the generation AI and have the generation AI identify the client's problems and concerns.

[0058] The advice unit can learn from past cases and provide appropriate advice based on the identified problem. The advice unit, for example, learns from past cases and generates appropriate advice for the identified problem. For example, the advice unit provides relaxation methods for stress management or advice for improving sleep. The advice unit can also use a generation AI to provide specific procedures and reference materials for the client's problem. For example, the advice unit provides advice on breathing techniques for stress relief or environmental settings for improving sleep quality. This improves the accuracy of advice by learning from past cases. Some or all of the above-mentioned processing in the advice unit may be performed using or without the generation AI. For example, the advice unit can input past case data into the generation AI and cause the generation AI to generate advice.

[0059] The matching unit can match professional assistance when the advice provided by the advising unit is insufficient. The matching unit recommends face-to-face consultation with a professional counselor or doctor when the advice is determined to be insufficient, for example, based on the accuracy of the advice or the client's satisfaction. For example, the matching unit arranges a meeting with a professional counselor for a client with serious mental health issues. The matching unit can also use the generation AI to select a professional best suited to the client's problem. For example, the matching unit matches a stress management expert or a sleep disorder specialist depending on the client's problem. This makes it possible to provide professional assistance when the advice is insufficient. Some or all of the above-mentioned processing in the matching unit may be performed using or without the generation AI. For example, the matching unit can input the accuracy of the advice and the client's satisfaction into the generation AI and have the generation AI select a professional.

[0060] The analysis unit can collect and learn input data from the client. For example, the analysis unit stores the input data from the client in a database and periodically collects data. For example, the analysis unit collects text data and voice data entered by the client and stores it in a database. The analysis unit can also use the collected data to train the generation AI. For example, the analysis unit inputs the collected data into the generation AI, and the generation AI learns from the data, thereby improving the accuracy of the analysis. In this way, the accuracy of the analysis is improved by collecting and learning from the input data from the client. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the collected data into the generation AI and have the generation AI learn from the data.

[0061] The advice unit can improve the quality of advice based on the collected data. The advice unit improves the quality of advice by, for example, using the collected data to train the generation AI. For example, the advice unit inputs the collected data into the generation AI, and the generation AI learns from the data, thereby improving the accuracy of the advice. The advice unit can also collect feedback and set evaluation criteria for advice. For example, the advice unit collects feedback from the client and sets criteria for evaluating the quality of the advice. This makes it possible to provide more appropriate advice by improving the quality of the advice based on the collected data. Some or all of the above-mentioned processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit can input the collected data into the generation AI and cause the generation AI to improve the quality of the advice.

[0062] The analysis unit can estimate the client's emotions and adjust the accuracy of the analysis based on the estimated emotions. For example, if the client is feeling highly stressed, the analysis unit uses an emotion engine to estimate the emotion and adds detailed questions to improve the accuracy of the analysis. For example, if the client inputs, "I'm feeling anxious because of the high pressure at work," the analysis unit uses the emotion engine to estimate anxiety and adds questions that provide reassurance. Furthermore, if the client is relaxed, the analysis unit uses the emotion engine to estimate the emotion and adjusts the accuracy of the analysis to provide prompt advice. For example, if the client inputs, "I've been spending more time relaxing recently," the analysis unit estimates relaxation and provides concise advice. This allows for more appropriate analysis by adjusting the accuracy of the analysis based on the client's emotions. The emotion estimation is achieved using an emotion engine or a generation AI, for example, using an emotion estimation function. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input the emotion data of the client to the generation AI and have the generation AI estimate the emotion and adjust the accuracy of the analysis.

[0063] The analysis unit can analyze the client's past consultation history and select an appropriate analysis method. For example, if the client has previously consulted about a similar problem, the generation AI analyzes that history and selects a similar analysis method. For example, if the client has previously consulted about "not being able to sleep due to work stress," the analysis unit selects a similar analysis method based on that history. Furthermore, if the client has previously consulted about a different problem, the generation AI analyzes that history and selects a different analysis method. For example, if the client has previously consulted about "feeling anxious about family problems," the analysis unit selects a different analysis method based on that history. Furthermore, if the client has previously consulted about multiple problems, the analysis unit analyzes that history and selects the most effective analysis method. For example, if the client has previously consulted about both "work stress" and "family problems," the generation AI selects the optimal analysis method based on that history. In this way, the optimal analysis method can be selected by analyzing the past consultation history. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input past consultation history data into the generation AI and have the generation AI select an analysis method.

[0064] The analysis unit can evaluate the urgency of the problem based on the client's input and determine the priority of analysis. For example, if the client inputs an urgent problem, the generation AI analyzes the content, rates it as highly urgent, and prioritizes its analysis. For example, if the client inputs "I need help right now," the generation AI rates it as highly urgent and prioritizes its analysis. Furthermore, if the client inputs a general problem, the analysis unit analyzes the content, rates it as less urgent, and prioritizes its analysis. For example, if the client inputs "I've been feeling a little stressed lately," the generation AI rates it as less urgent and prioritizes its analysis. Furthermore, if the client inputs multiple problems, the analysis unit analyzes the content, evaluates the urgency of each problem, and determines its priority. For example, if the client inputs "I'm struggling with both work stress and family problems," the generation AI evaluates the urgency of each problem and prioritizes it. This allows for prioritization by evaluating the urgency of the problems, enabling prompt responses. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input the client's input data into the generation AI and have the generation AI evaluate the urgency and determine the priority.

[0065] The analysis unit can estimate the client's emotions and adjust the display method of the analysis results based on the estimated client's emotions. For example, if the client is feeling stressed, the generation AI uses the emotion engine to estimate the emotion and displays the analysis results in a simple, easy-to-understand format. For example, if the client inputs, "I'm feeling anxious because of the heavy pressure at work," the generation AI estimates anxiety and displays the analysis results concisely. Furthermore, if the client is feeling relaxed, the generation AI uses the emotion engine to estimate the emotion and displays the analysis results in detail. For example, if the client inputs, "I've been having more time to relax recently," the generation AI estimates relaxation and displays detailed analysis results. Furthermore, if the client is feeling anxious, the analysis unit can estimate the emotion using the emotion engine and display the analysis results in a format that provides a sense of security. For example, if the client inputs, "I'm worried about the future," the generation AI estimates anxiety and displays analysis results that provide a sense of security. This allows for more appropriate display by adjusting the display method of the analysis results based on the client's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-mentioned processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit may input the client's emotion data into the generation AI and have the generation AI adjust the display method of the analysis results.

[0066] The analysis unit can analyze region-specific issues by taking into account the geographic location information of the client. For example, if the client lives in a specific region, the generation AI performs the analysis by taking into account the region's specific issues. For example, if the client inputs, "I'm worried because the security situation in my region is bad," the generation AI performs the analysis by taking into account the security information for that region. Furthermore, if the client lives in a different region, the generation AI performs the analysis by taking into account the region's specific issues. For example, if the client inputs, "I'm worried because I moved to a new region," the generation AI performs the analysis by taking into account the region's specific issues. Furthermore, if the client has issues related to multiple regions, the generation AI performs the analysis by taking into account the region's specific issues. For example, if the client inputs, "I'm worried because I travel between multiple regions for work," the generation AI performs the analysis by taking into account the region's specific issues. This analysis of region-specific issues allows for more appropriate advice to be provided. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the geographical location information of the client into the generation AI and have the generation AI perform an analysis of problems specific to the region.

[0067] The analysis unit can analyze the social media activity of the client and identify related problems. For example, the analysis unit uses a generation AI to analyze content posted by the client on social media and identify related problems. For example, if the client posts, "I'm feeling stressed because of slander on social media," the generation AI analyzes the content and identifies the stress issue. The analysis unit can also analyze comments received by the client on social media and identify related problems. For example, if the client posts, "I'm worried because of comments on social media," the generation AI analyzes the comment and identifies the anxiety issue. The analysis unit can also analyze the content of accounts the client follows on social media and identify related problems. For example, if the client posts, "My self-esteem is low because of the accounts I follow on social media," the generation AI analyzes the content of the account and identifies the self-esteem issue. In this way, related problems can be identified by analyzing social media activity. Some or all of the above-described processing in the analysis unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the analysis unit can input the client's social media data into the generation AI and have the generation AI identify related issues.

[0068] The advice unit can estimate the client's emotions and adjust the way the advice is expressed based on the estimated emotions. For example, if the client is feeling stressed, the generation AI uses an emotion engine to estimate the client's emotions and provide advice in simple, easy-to-understand language. For example, if the client inputs, "I'm feeling anxious because of the high pressure at work," the generation AI estimates anxiety and provides concise advice. Furthermore, if the client is feeling relaxed, the generation AI uses an emotion engine to estimate the client's emotions and provide detailed advice. For example, if the client inputs, "I've been having more time to relax recently," the generation AI estimates relaxation and provides detailed advice. Furthermore, if the client is feeling anxious, the generation AI uses an emotion engine to estimate the client's emotions and provides advice in a way that provides reassurance. For example, if the client inputs, "I'm worried about the future," the generation AI estimates anxiety and provides reassuring advice. This allows the system to provide more appropriate advice by adjusting the way the advice is expressed based on the client's emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or a generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit may input emotional data of the client into the generation AI and have the generation AI adjust the way the advice is expressed.

[0069] When providing advice, the advice unit can improve the accuracy of the advice by referring to past case data. For example, the generation AI refers to past case data and provides optimal advice for a similar problem. For example, the advice unit refers to past cases where a person consulted about "not being able to sleep due to work stress" and provides optimal advice for a similar problem. The advice unit can also refer to past case data and provide optimal advice for a different problem. For example, the advice unit refers to past cases where a person consulted about "feeling anxious about family problems" and provides optimal advice for a different problem. Furthermore, the advice unit can also refer to past case data and provide optimal advice for multiple problems. For example, the advice unit refers to past cases where a person consulted about both "work stress" and "family problems" and provides optimal advice for multiple problems. By referring to past case data, the accuracy of the advice can be improved. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit can input past case data into the generation AI and cause the generation AI to improve the accuracy of the advice.

[0070] When providing advice, the advice unit can apply different advice algorithms depending on the category of the client's problem. For example, if the client has a stress management problem, the generation AI of the advice unit applies an advice algorithm specialized for stress management. For example, the advice unit provides breathing techniques and relaxation methods for stress relief. Furthermore, if the client has an anxiety relief problem, the generation AI applies an advice algorithm specialized for anxiety relief. For example, the advice unit provides cognitive behavioral therapy techniques and relaxation techniques for reducing anxiety. Furthermore, if the client has a relaxation problem, the advice unit applies an advice algorithm specialized for relaxation. For example, the advice unit provides meditation techniques and yoga techniques for relaxation. In this way, by applying different advice algorithms depending on the category of the problem, more appropriate advice can be provided. Some or all of the above-mentioned processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit may input the category of the client's problem into the generation AI and cause the generation AI to apply the advice algorithm.

[0071] The advice unit can estimate the client's emotions and adjust the length of the advice based on the estimated emotions. For example, if the client is feeling stressed, the generation AI uses the emotion engine to estimate the client's emotions and shorten the advice to the point. For example, if the client inputs, "I'm feeling anxious because of the pressure at work," the generation AI estimates anxiety and provides concise advice. Furthermore, if the client is feeling relaxed, the generation AI uses the emotion engine to estimate the client's emotions and provide longer, more detailed advice. For example, if the client inputs, "I've been able to spend more time relaxing recently," the generation AI estimates relaxation and provides detailed advice. Furthermore, if the client is feeling anxious, the generation AI uses the emotion engine to estimate the client's emotions and shorten the advice to provide a sense of security. For example, if the client inputs, "I'm worried about the future," the generation AI estimates anxiety and provides concise, reassuring advice. This allows the length of advice to be adjusted based on the client's emotions, enabling more appropriate advice to be provided. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit may input the client's emotion data into the generation AI and have the generation AI adjust the length of the advice.

[0072] When providing advice, the advice unit can determine the priority of the advice based on the time of submission by the client. For example, if the client submits an urgent problem, the generation AI prioritizes the advice by taking into account the time of submission. For example, if the client inputs "I need help right now," the generation AI prioritizes the advice by taking into account the time of submission. Furthermore, if the client submits a general problem, the generation AI provides advice at normal priority by taking into account the time of submission. For example, if the client inputs "I've been feeling a little stressed lately," the generation AI provides advice at normal priority by taking into account the time of submission. Furthermore, if the client submits multiple problems, the advice unit determines the priority of each problem by taking into account the time of submission. For example, if the client inputs "I'm struggling with both work stress and family problems," the generation AI determines the priority of each problem by taking into account the time of submission. This enables a rapid response by prioritizing advice based on the time of submission. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit may input the client's submission time data into the generation AI and have the generation AI determine the priority of advice.

[0073] When providing advice, the advice unit can adjust the order of advice based on the relevance of the advice to the client. For example, if the client submits multiple related problems, the generation AI considers the relevance and provides advice in the optimal order. For example, if the client inputs, "I'm struggling with both work stress and family problems," the generation AI considers the relevance and provides advice in the optimal order. Furthermore, if the client submits multiple less related problems, the advice unit can adjust the order by considering the relevance. For example, if the client inputs, "work stress" and "no time for hobbies," the generation AI considers the relevance and adjusts the order. Furthermore, if the client submits multiple highly related problems, the advice unit prioritizes providing advice by considering the relevance. For example, if the client inputs, "work stress" and "interpersonal problems at work," the generation AI considers the relevance and provides advice. This allows for more appropriate advice to be provided by adjusting the order of advice based on relevance. Some or all of the above-described processing in the advice unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the advice unit can input relevant data about the client's problem to the generation AI and have the generation AI adjust the order of advice.

[0074] The matching unit can estimate the client's emotions and adjust the matching criteria based on the estimated client's emotions. For example, if the client is feeling stressed, the generation AI uses the emotion engine to estimate the client's emotions and prioritizes matching with a professional specializing in stress management. For example, if the client inputs, "I'm anxious because of the heavy pressure at work," the generation AI estimates anxiety and matches with a stress management specialist. Furthermore, if the client is feeling relaxed, the generation AI uses the emotion engine to estimate the client's emotions and matches with a general professional. For example, if the client inputs, "I've been able to relax more recently," the generation AI estimates relaxation and matches with a general counselor. Furthermore, if the client is feeling anxious, the matching unit can estimate the client's emotions using the emotion engine and prioritize matching with a professional specializing in anxiety relief. For example, if the client inputs, "I'm worried about the future," the generation AI estimates anxiety and matches with an anxiety relief specialist. This allows the matching criteria to be adjusted based on the client's emotions, enabling more appropriate professionals to be matched. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit may input the client's emotion data into the generation AI and have the generation AI adjust the matching criteria.

[0075] When matching, the matching unit can select an appropriate professional by referring to the client's past consultation history. For example, if the client has previously consulted about a similar problem, the generation AI refers to that history and selects the same professional. For example, if the client previously consulted about "not being able to sleep due to work stress," the same stress management expert is selected based on that history. Furthermore, if the client previously consulted about a different problem, the matching unit can select a different professional by referring to that history. For example, if the client previously consulted about "feeling anxious about family issues," the matching unit can select a different expert based on that history. Furthermore, if the client previously consulted about multiple issues, the matching unit can select the most effective professional by referring to that history. For example, if the client previously consulted about both "work stress" and "family issues," the matching unit can select the most appropriate professional based on that history. In this way, the optimal professional can be selected by referring to the past consultation history. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit can input past consultation history data into the generation AI and have the generation AI select a professional.

[0076] The matching unit can determine the matching priority based on the urgency of the client's problem during matching. For example, if the client has an urgent problem, the generation AI evaluates the urgency and prioritizes matching with a professional. For example, if the client inputs, "I need help right now," the generation AI evaluates the urgency as high and prioritizes matching with a professional. Furthermore, if the client has a general problem, the generation AI evaluates the urgency and prioritizes matching with a professional. For example, if the client inputs, "I've been feeling a little stressed lately," the generation AI evaluates the urgency as low and prioritizes matching with a professional. Furthermore, if the client has multiple problems, the matching unit evaluates the urgency of each problem and prioritizes each problem. For example, if the client inputs, "I'm struggling with both work stress and family problems," the generation AI evaluates the urgency of each problem and prioritizes them. This enables a rapid response by prioritizing matching based on the urgency of the problem. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit can input the urgency data of the client's problem into the generation AI and have the generation AI determine the matching priority.

[0077] The matching unit can estimate the client's emotions and adjust the display method of the matching results based on the estimated client's emotions. For example, if the client is feeling stressed, the generation AI uses an emotion engine to estimate the client's emotions and displays the matching results in a simple, easy-to-understand format. For example, if the client inputs, "I'm feeling anxious because of the high pressure at work," the generation AI estimates anxiety and displays a concise matching result. Furthermore, if the client is feeling relaxed, the generation AI uses an emotion engine to estimate the client's emotions and displays detailed matching results. For example, if the client inputs, "I've been able to relax more recently," the generation AI estimates relaxation and displays detailed matching results. Furthermore, if the client is feeling anxious, the matching unit can estimate the client's emotions using an emotion engine and display matching results in a format that provides a sense of security. For example, if the client inputs, "I'm worried about the future," the generation AI estimates anxiety and displays matching results that provide a sense of security. This allows for more appropriate display by adjusting the display method of the matching results based on the client's emotions. Emotion estimation is achieved, for example, using an emotion estimation function with an emotion engine or generation AI. The generation AI may be a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit may input emotional data of the client to the generation AI and cause the generation AI to adjust the display method of the matching results.

[0078] The matching unit can select the most appropriate professional by taking into account the geographic location information of the client during matching. For example, if the client lives in a specific area, the generation AI prioritizes selecting professionals in that area. For example, if the client inputs, "I'm worried because the security situation in my area is bad," the generation AI selects a professional by taking into account the security information for that area. Furthermore, if the client lives in a different area, the matching unit selects professionals in that area. For example, if the client inputs, "I'm worried because I moved to a new area," the generation AI selects a professional in that area. Furthermore, if the client has issues related to multiple areas, the matching unit selects professionals in each area. For example, if the client inputs, "I'm worried because I travel between multiple areas for work," the generation AI selects professionals in each area. This allows for a more appropriate professional to be selected by taking geographic location information into account. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit may input the client's geographic location information into the generation AI and have the generation AI select a professional.

[0079] The matching unit can analyze the social media activity of the client and identify relevant professionals when matching. For example, the generation AI analyzes the content posted by the client on social media to identify relevant professionals. For example, if the client posts, "I'm feeling stressed because of slander on social media," the generation AI analyzes the content and identifies a stress management specialist. The matching unit can also analyze comments received by the client on social media to identify relevant professionals. For example, if the client posts, "I'm worried because of the comments on social media," the generation AI analyzes the comment and identifies an anxiety relief specialist. The matching unit can also analyze the content of accounts followed by the client on social media to identify relevant professionals. For example, if the client posts, "My self-esteem is low because of the accounts I follow on social media," the generation AI analyzes the content of the accounts and identifies the problem with self-esteem. In this way, relevant professionals can be identified by analyzing social media activity. Some or all of the above-described processing in the matching unit may be performed using the generation AI, or may be performed without using the generation AI. For example, the matching unit can input the client's social media data into the generation AI and have the generation AI identify relevant professionals. === Hard Collateral 1-1 === Each of the multiple elements including the above-mentioned analysis unit, advice unit, and matching unit is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart device 14 and analyzes the natural language input of the client. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides optimal advice using a generation AI. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and matches professional assistance. === Hard Collateral 1-2 === Each of the multiple elements including the above-mentioned analysis unit, advice unit, and matching unit is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the smart glasses 214 and analyzes the natural language input of the client. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides optimal advice using a generation AI. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and matches professional assistance. === Hard Collateral 1-3 === Each of the multiple elements including the above-mentioned analysis unit, advice unit, and matching unit is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the headset type terminal 314 and analyzes the natural language input of the client. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides optimal advice using a generation AI. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and matches professional assistance. === Hard Collateral 1-4 === Each of the multiple elements including the above-mentioned analysis unit, advice unit, and matching unit is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the analysis unit is realized by the control unit 46A of the robot 414 and analyzes the natural language input of the client. The advice unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and provides optimal advice using a generation AI. The matching unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and matches professional assistance.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The analysis unit can monitor the client's input data in real time and detect abnormal patterns. For example, if the client consults at a frequency that differs from their usual pattern, the generation AI will detect the abnormality and respond promptly. The analysis unit can also detect abnormal emotional fluctuations based on the client's input. For example, if the client suddenly begins to express more negative emotions, the generation AI will detect the change and provide appropriate advice. The analysis unit can also compare the client's input data with the data of other clients to identify abnormal patterns. For example, if the client shows an abnormally high stress level compared to other clients, the generation AI will identify the abnormality and respond promptly. This enables real-time monitoring and anomaly detection, enabling prompt and appropriate responses.

[0082] The advice unit can collect lifestyle data from the client to improve the accuracy of advice. For example, data is collected from a wearable device used daily by the client, and the generation AI analyzes the data to provide advice. The advice unit can also collect data on the client's diet and exercise to provide health management advice. For example, if the client enters a diet record, the generation AI analyzes the data and provides advice on nutritional balance. Furthermore, the advice unit can collect the client's sleep data to provide advice on improving sleep. For example, if the client records their sleep quality, the generation AI analyzes the data and provides methods for improving their sleep environment. In this way, by utilizing lifestyle data, more specific and effective advice can be provided.

[0083] The matching unit can select the most appropriate professional by taking into account the occupational information of the client. For example, if the client is engaged in a specific occupation, the generation AI will prioritize selecting experts related to that occupation. For example, if the client is a medical professional, the generation AI will match the client with an expert who is knowledgeable about the mental health of medical professionals. The matching unit can also select an appropriate professional by taking into account stress factors related to the client's occupation. For example, if the client is a teacher, the matching unit will match the client with an expert who is knowledgeable about stress in the educational field. Furthermore, the matching unit can select a professional who offers counseling methods tailored to the client's occupation. For example, if the client is an engineer, the matching unit will match the client with an expert who offers stress management methods specific to technical jobs. This makes it possible to select a more appropriate professional by taking into account occupational information.

[0084] The analysis unit can anonymize the data input by the client and perform analysis while protecting data privacy. For example, the analysis unit can delete the client's personal information and have the generation AI analyze the anonymized data. In addition to anonymizing the data, the analysis unit can also encrypt the data. For example, the analysis unit can encrypt the client's input data and have the generation AI analyze the encrypted data. In addition to anonymizing and encrypting the data, the analysis unit can also control access to the data. For example, the analysis unit can allow only users with specific permissions to access the data and have the generation AI analyze the access-controlled data. This allows the client's data to be analyzed safely while protecting data privacy.

[0085] The advice unit can adjust the content of the advice taking into account the cultural background of the person seeking advice. For example, if the person seeking advice belongs to a particular cultural sphere, the generation AI will provide advice appropriate to that culture. For example, if the person seeking advice belongs to an Asian cultural sphere, traditional Asian relaxation techniques will be provided. The advice unit can also adjust the content of the advice taking into account the person's religious background. For example, if the person seeking advice believes in a particular religion, advice appropriate to that religion will be provided. Furthermore, the advice unit can adjust the way the advice is expressed taking into account the person's language background. For example, if the person seeking advice does not have English as their native language, advice will be provided in simple, easy-to-understand language. This makes it possible to provide more appropriate and effective advice by taking cultural background into account.

[0086] The analysis unit can estimate the client's emotions and adjust the analysis priority based on the estimated client's emotions. For example, if the client is feeling highly stressed, the generation AI can use the emotion engine to estimate the client's emotions and prioritize analysis. Alternatively, if the client is relaxed, the analysis unit can use the emotion engine to estimate the client's emotions and prioritize analysis. Furthermore, if the client is experiencing multiple emotions, the analysis unit can use the emotion engine to evaluate the intensity of each emotion and determine the priority. For example, if the client inputs, "I'm suffering from both work stress and family problems," the generation AI can evaluate the intensity of each emotion and determine the priority. This allows for quick and appropriate response by adjusting the analysis priority based on emotions.

[0087] The advice unit can estimate the client's emotions and adjust the timing of advice based on the estimated client's emotions. For example, if the client is feeling highly stressed, the generation AI can use the emotion engine to estimate the client's emotions and provide immediate advice. Furthermore, if the client is relaxed, the advice unit can also estimate the client's emotions using the emotion engine and provide advice at the appropriate time. Furthermore, if the client is experiencing multiple emotions, the generation AI can use the emotion engine to evaluate the intensity of each emotion and provide advice at the optimal time. For example, if the client inputs, "I'm struggling with both work stress and family problems," the generation AI can evaluate the intensity of each emotion and provide advice at the optimal time. This allows for more effective advice to be provided by adjusting the timing of advice based on emotions.

[0088] The matching unit can estimate the client's emotions and adjust the frequency of matching based on the estimated client's emotions. For example, if the client is feeling highly stressed, the generation AI can use the emotion engine to estimate their emotions and frequently match them with professionals. Alternatively, if the client is relaxed, the matching unit can use the emotion engine to estimate their emotions and match them at a normal frequency. Furthermore, if the client is experiencing multiple emotions, the generation AI can use the emotion engine to evaluate the intensity of each emotion and perform matching at the optimal frequency. For example, if the client enters, "I'm suffering from both work stress and family problems," the generation AI can evaluate the intensity of each emotion and perform matching at the optimal frequency. This allows for adjusting the frequency of matching based on emotions, making it possible to match with more appropriate professionals.

[0089] The analysis unit can estimate the client's emotions and adjust the feedback method of the analysis results based on the estimated client's emotions. For example, if the client is feeling highly stressed, the generation AI can use the emotion engine to estimate the client's emotions and provide feedback in a simple, easy-to-understand format. Furthermore, if the client is relaxed, the analysis unit can also use the emotion engine to estimate the client's emotions and provide detailed feedback. Furthermore, if the client is experiencing multiple emotions, the generation AI can use the emotion engine to evaluate the intensity of each emotion and provide the optimal feedback method. For example, if the client enters, "I'm suffering from both work stress and family problems," the generation AI can evaluate the intensity of each emotion and provide the optimal feedback method. This allows for more appropriate feedback by adjusting the feedback method based on emotions.

[0090] The advice unit can estimate the client's emotions and personalize the advice content based on the estimated client's emotions. For example, if the client is feeling highly stressed, the generation AI can use the emotion engine to estimate the client's emotions and provide advice specifically aimed at reducing stress. Furthermore, if the client is feeling relaxed, the generation AI can also use the emotion engine to estimate the client's emotions and provide advice on maintaining relaxation. Furthermore, if the client is experiencing multiple emotions, the generation AI can use the emotion engine to evaluate the intensity of each emotion and provide optimal advice. For example, if the client inputs, "I'm struggling with both work stress and family problems," the generation AI can evaluate the intensity of each emotion and provide optimal advice. This allows for more effective advice to be provided by personalizing the advice content based on emotions.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The analysis unit analyzes the client's natural language input. The client's natural language input includes text, voice, chat messages, etc. The analysis unit uses morphological analysis to segment the input text, performs grammatical analysis, and identifies the client's problems and worries through semantic analysis. For example, the analysis unit analyzes the text input by the client, "I've been so stressed lately I can't sleep," to identify stress and sleep problems. Speech recognition technology can also be used to analyze voice input. For example, if the client inputs, "I'm feeling anxious because of the high pressure at work," the analysis unit converts the voice into text and performs the same analysis. Step 2: The advice unit uses the generation AI to provide optimal advice based on the problem analyzed by the analysis unit. The advice unit learns from past cases and generates appropriate advice for the identified problem. For example, it may provide relaxation techniques for stress management or advice on how to improve sleep. The generation AI can also be used to provide specific steps and reference materials for the client's problem. For example, it may provide advice on breathing techniques to relieve stress or environmental settings to improve sleep quality. Step 3: The Matching Department matches professional assistance if the advice provided by the Advice Department is insufficient. If the advice is deemed insufficient based on the accuracy of the advice and the client's satisfaction, the Matching Department recommends face-to-face consultation with a professional counselor or doctor. For example, it arranges a meeting with a professional counselor for a client with serious mental health issues. Generative AI can also be used to select the professional best suited to the client's problem. For example, it can match the client with a stress management expert or a sleep disorder specialist.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0096] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0097] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0098] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0099] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0100] 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.

[0101] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0102] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0103] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0104] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0105] 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.

[0106] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0107] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0108] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0109] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0110] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0111] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0112] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0113] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0114] 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.

[0115] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0116] 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.

[0117] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0118] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0119] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0120] 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.

[0121] 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.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0123] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0124] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0125] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0127] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0128] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0129] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0130] 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.

[0131] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0132] 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.

[0133] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0134] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0135] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0136] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0137] 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.

[0138] 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.

[0139] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0140] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0141] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0142] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0143] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0144] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0145] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0146] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0147] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0148] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0149] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0150] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0151] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0152] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0153] 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.

[0154] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0155] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[0156] 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.

[0157] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0158] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0159] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0160] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0161] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0162] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0163] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0164] [Explanation of symbols]

[0165] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an analysis unit that analyzes the natural language input of the client; an advice unit that provides appropriate advice based on the problem analyzed by the analysis unit; a matching unit that matches professional assistance when the advice provided by the advising unit is insufficient. A system characterized by:

2. The analysis unit Analyzes the natural language input of the client to identify their problems and concerns The system of claim 1 .

3. The advice unit Learn from past cases and provide appropriate advice based on identified issues The system of claim 1 .

4. The matching unit Matching professional assistance when the advice provided by the Advice Department is insufficient The system of claim 1 .

5. The analysis unit Collects and learns from client input data The system of claim 1 .

6. The advice unit Improve the quality of advice based on collected data The system of claim 1 .

7. The analysis unit Estimate the client's emotions and adjust the accuracy of the analysis based on the estimated emotions. The system of claim 1 .

8. The analysis unit Analyze the client's past consultation history and select the appropriate analysis method The system of claim 1 .

Images