System

Abstract

A system is provided.SOLUTION: The system includes means for collecting vital data and behavior pattern data from a user, means for analyzing the collected data and evaluating the mental health state of the user, means for generating personalized counseling contents based on the evaluation result, means for performing counseling with the user in an interactive manner, and means for continuously monitoring the data of the user even after the counseling.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] The number of people suffering from mental health problems is increasing year by year, and many of them have difficulty accessing medical examinations and counseling due to a decline in their mental health and motivation. Furthermore, a shortage of mental health treatment personnel poses a challenge, meaning many people are unable to receive appropriate care. If this situation continues, it could lead to social problems such as a decline in labor productivity. To address these issues, the present invention aims to provide an AI counselor service that can be used anytime, anywhere, thereby improving access to mental health care. [Means for solving the problem]

[0005] The present invention is a system that includes the following means: means for collecting vital data and behavioral pattern data from a user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, and means for continuously monitoring the user's data even after counseling. The system may also include means for cleaning and standardizing the collected data, and means for generating warnings and feedback to the user. This allows users to easily receive counseling 24 hours a day, even if they are feeling depressed or unmotivated, thereby reducing the burden of mental health care.

[0006] "User" refers to an individual who uses this system and receives mental health care.

[0007] "Vital data" refers to data that indicates the physiological condition of a user, such as heart rate, blood pressure, and body temperature.

[0008] "Behavioral pattern data" refers to data related to the user's daily behavior, such as sleep time, activity level, and exercise time.

[0009] "Means of collection" refers to the mechanism for obtaining data through devices such as smartphones and smartwatches.

[0010] "Means of analysis" refers to a mechanism for analyzing collected data using statistical or machine learning techniques and extracting information.

[0011] "Means for evaluation" refers to a mechanism for determining the user's mental health state based on the analysis results.

[0012] "Means for generating" refers to a mechanism for creating appropriate counseling content and advice for users based on the evaluation results.

[0013] "Means for conducting interactive counseling" refers to a mechanism that allows two-way communication between the user and the AI ​​counselor.

[0014] "Monitoring measures" refers to a system for continuously observing user data even after counseling and taking additional measures as necessary.

[0015] "Cleaning and standardization procedures" refers to the process of preparing collected data in a format that is easy to analyze.

[0016] "Means for generating warnings and feedback" refers to a mechanism for providing warnings and suggestions for improvement based on the user's status. [Brief explanation of the drawings]

[0017] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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, a 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), and an APU (Accelerated Processing Unit).

[0021] 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.

[0022] 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.

[0023] 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), Bluetooth (registered trademark), etc.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] 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.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] This invention is an AI counselor system to support users' mental health care. The system collects data from users via devices such as smartphones and smartwatches, analyzes and evaluates that data, and provides personalized counseling.

[0039] Specifically, the server, the terminal, or the user operates as follows.

[0040] First, a user uses a smartphone or smartwatch to carry out daily activities. For example, the smartwatch collects sleep data while the user is sleeping, and records heart rate and activity level while exercising. In this way, vital data and behavioral pattern data are collected.

[0041] The device then sends the collected data to a server, which transfers it over the internet and analyzes it.

[0042] The server first cleans the received data to remove outliers and incomplete data. Next, it standardizes the data and converts it into a format that is easy to analyze. It then uses statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other factors. Based on the results of this analysis, the server evaluates the user's mental health status. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0043] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0044] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0045] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0046] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0047] The processing flow will be explained below.

[0048] Step 1:

[0049] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0050] Step 2:

[0051] The device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[0052] Step 3:

[0053] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[0054] Step 4:

[0055] The server cleans the data it receives, removing outliers and incomplete data, during which the data is checked for integrity and converted into a format suitable for analysis.

[0056] Step 5:

[0057] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to assess the user's heart rate variability, sleep patterns, and more.

[0058] Step 6:

[0059] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, it will determine that the user is feeling stressed.

[0060] Step 7:

[0061] The server generates personalized counseling content for the user based on the evaluation results, using a large-scale language model (LLM) to create advice and feedback that is appropriate for the user.

[0062] Step 8:

[0063] The user opens a counseling app on their smartphone and is connected to an AI counselor through the app.

[0064] Step 9:

[0065] The AI ​​counselor on the server conducts counseling by presenting questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[0066] Step 10:

[0067] The user answers the AI ​​counselor's questions, which allows the AI ​​counselor to understand the user's condition and the problems they are experiencing.

[0068] Step 11:

[0069] The server analyzes the user's answers and determines the next question and specific advice. For example, it might suggest, "Deep breathing has a relaxing effect. Please try it."

[0070] Step 12:

[0071] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor their mental health, providing additional counseling or warnings as needed to support ongoing care.

[0072] Example 1

[0073] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0074] Mental health problems such as stress and anxiety are on the rise in modern society, creating a need for rapid and accurate responses. However, traditional mental health care relies mainly on face-to-face counseling by experts, which poses challenges such as time and location constraints and a shortage of experts. Furthermore, a lack of a personalized approach for individual users makes effective care difficult. Given these circumstances, there is a need for a system that can monitor users' mental health status in real time and respond quickly.

[0075] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0076] In this invention, the server includes means for collecting physiological data and behavioral pattern data from a user, means for transmitting the collected data to the server via a network, means for cleaning and standardizing the received data, means for analyzing the cleaned data and evaluating the user's psychological health state, means for generating personalized counseling content based on the evaluation results, means for providing feedback and advice to the user using a generative AI model, means for conducting counseling with the user in an interactive format, and means for continuously monitoring the user's data even after counseling. This makes it possible to monitor the user's mental health state in real time and provide prompt and personalized counseling.

[0077] "User" refers to an individual who provides physiological data and behavioral pattern data and uses the system.

[0078] "Physiological data" refers to data relating to a user's physical condition, such as heart rate, sleep data, body temperature, blood pressure, etc.

[0079] "Behavior pattern data" refers to data related to the user's behavior, such as the number of steps taken, amount of exercise, and duration of activity.

[0080] "Terminal" refers to a device, such as a smartphone or smartwatch, that a user uses to collect physiological data and behavioral pattern data.

[0081] "Server" refers to a computer system that receives, cleans, standardizes, and analyzes data sent by users and generates counseling content.

[0082] "Cleaning" refers to the process of removing outliers and incomplete information from collected data and preparing the data so that accurate analysis can be performed.

[0083] "Standardization" refers to the process of unifying the format of data collected from different devices and sensors, making it easier to analyze.

[0084] "Analysis" refers to the process of using cleaned and standardized data to assess a user's psychological well-being using statistical models and machine learning algorithms.

[0085] A "generative AI model" refers to an algorithm that uses a large-scale language model to generate feedback and advice tailored to the user's condition.

[0086] "Counseling content" refers to information including feedback and advice generated based on the analysis results.

[0087] "Dialogue-based counseling" refers to an interactive counseling process, such as a question-and-answer format, conducted between the user and the AI ​​counselor.

[0088] "Monitoring" refers to the process of continuing to collect and analyze user data and monitor their mental health status even after counseling.

[0089] This invention is an AI counselor system to support users' mental health care. The system collects physiological data and behavioral pattern data using devices such as smartphones and smartwatches, analyzes and evaluates the data, and provides personalized counseling.

[0090] Data collection

[0091] Users use smartphones or smartwatches to collect daily activity data, including physiological data such as heart rate, sleep data, and activity level, as well as behavioral pattern data. For example, when a user goes running, the smartwatch records their heart rate and distance, and automatically collects sleep data at night.

[0092] Data transmission

[0093] The device sends the collected data to a server over the Internet, specifically, the user's smartphone uploads the data to the server via Wi-Fi or mobile data network.

[0094] Data Cleaning and Standardization

[0095] The server cleans the data it receives, removing outliers and incomplete data, then standardizes it and converts it into a format that's easier to analyze, for example by standardizing the timestamp format and scaling it so that data from different devices can be handled at the same scale.

[0096] Data analysis

[0097] The server analyzes the cleaned and standardized data using statistical models and machine learning algorithms. Specifically, it uses programming languages ​​such as Python to run machine learning algorithms (e.g., random forests) to assess the user's psychological well-being. This analysis allows it to understand the user's stress level and mental health status from heart rate variability and sleep patterns.

[0098] Counseling content generation

[0099] The server uses a generative AI model (large-scale language model) to generate personalized counseling content based on the evaluation results. For example, if the user is evaluated as feeling stressed, the server generates feedback and advice suggesting ways to relax. Specific examples of prompts for the generative AI model are as follows:

[0100] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[0101] Providing counseling

[0102] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will present the next question, "Is that something you're worried about?"

[0103] Follow-up and monitoring

[0104] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, the server can send another counseling notification.

[0105] This system allows users to receive counseling 24 hours a day even if they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, thereby contributing to improving labor productivity in society.

[0106] As described above, the present invention provides specific means for realizing more efficient and effective mental health care for users.

[0107] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0108] Step 1:

[0109] A user uses a smartphone or smartwatch to collect physiological data and behavioral pattern data. Specifically, the user wears the smartwatch and goes about their daily activities. During this time, their heart rate, sleep data, and activity level are recorded. Input data includes a heart rate log, sleep log, and exercise log, which are raw data obtained from the smartwatch. The output is the collected physiological data and behavioral pattern data.

[0110] Step 2:

[0111] The device sends the collected data to the server. Specifically, the user's smartphone uses Wi-Fi or mobile data network to obtain data from the smartwatch and uploads it to the server. The input is the data obtained from the smartwatch, and the output is the data sent to the server.

[0112] Step 3:

[0113] The server cleans the received data. Specifically, the server removes outliers and incomplete data from the received data. The input is the raw data sent from the device, and the output is the cleaned data. For example, outliers such as a heart rate of 0 or an extremely high heart rate are filtered out.

[0114] Step 4:

[0115] The server standardizes the cleaned data. Specifically, it standardizes the data format so that data from different devices can be analyzed at the same scale. The input is cleaned data, and the output is standardized data. For example, it standardizes the timestamp format from different devices.

[0116] Step 5:

[0117] The server analyzes the standardized data. Specifically, it uses a machine learning algorithm to assess the user's psychological health. This algorithm uses a programming language such as Python. The input is the standardized data, and the output is a psychological health assessment as an analysis result. For example, a random forest algorithm is used to assess the user's stress level based on sleep patterns and heart rate fluctuations.

[0118] Step 6:

[0119] The server generates counseling content based on the analysis results. Specifically, it uses a large-scale language model (LLM) to generate feedback and advice appropriate for the user. The input is the analysis results, and the output is the generated counseling content. For example, if the user is feeling stressed, it generates content suggesting ways to relax. An example of a prompt sentence for the generative AI model is as follows:

[0120] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[0121] Step 7:

[0122] The device provides counseling. Specifically, when a user opens the app on their smartphone, the device connects the user to an AI counselor on the server. The input is the generated counseling content, and the output is feedback and advice provided to the user. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will pose the next question, "Is that something you're worried about?"

[0123] Step 8:

[0124] The server continues to monitor the user's data. Specifically, it collects data even after the counseling session ends and monitors the user's mental health status based on the new data. The input is the continuously collected data, and the output is an updated mental health assessment and, if necessary, a re-counseling notification. For example, if an abnormality such as a re-elevated heart rate is detected, the server will send another counseling notification.

[0125] (Application example 1)

[0126] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0127] Conventional mental healthcare systems assess a user's mental health status and provide counseling based on the collection and analysis of their physiological and behavioral pattern data. However, no systems have taken into account the impact of a user's psychological state on purchasing behavior. This has made it difficult to improve the customer experience in virtual stores. Therefore, there has been a need for a system that can link a user's mental health status with their purchasing behavior and make appropriate product recommendations.

[0128] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0129] In this invention, the server includes means for collecting vital data and behavioral pattern data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, means for collecting and analyzing user purchasing behavior data, and means for generating product proposals that link the user's psychological state with their purchasing behavior, thereby enabling personalized product proposals that take the user's psychological state into consideration.

[0130] "User" means an individual or group of people who use the system.

[0131] "Vital data" refers to physiological data including biosignals such as heart rate, blood pressure, and body temperature.

[0132] "Behavior pattern data" refers to data relating to the user's daily activities, sleep data, amount of exercise, and other behavioral data.

[0133] "Analysis" means evaluating collected data using statistical methods and machine learning algorithms.

[0134] "Mental health status" refers to a user's mental health and psychological balance.

[0135] "Counseling" means the process of providing advice and feedback to support a user's mental health.

[0136] "Continuous monitoring" means collecting data about a user over a long period of time and monitoring their condition.

[0137] "Purchasing behavior data" refers to behavioral data related to purchasing, such as a user's shopping history and product browsing history.

[0138] "Product suggestion" means analyzing the user's psychological state and purchasing behavior to recommend appropriate products.

[0139] This invention relates to a system for supporting users' mental health care and improving customer experience in virtual stores. This system collects vital data and behavioral pattern data from users, analyzes them, and evaluates the user's mental health state. It then generates personalized counseling content based on the collected data and provides counseling in an interactive format. It also collects data on the user's purchasing behavior and has the function of suggesting products linked to the user's psychological state.

[0140] 1. Program Generation

[0141] The program of this system is configured as follows:

[0142] 2. Explain the program's processing in natural language

[0143] When users use their smartphones or smartwatches to carry out activities, these devices collect vital data such as heart rate and sleep data. When users shop in virtual stores, purchasing behavior data is also collected. This data is sent to a server via the Internet.

[0144] The server cleans and standardizes the collected data, removing outliers and incomplete data. It then analyzes the data using statistical models and machine learning algorithms (e.g., scikit-learn) to assess the user's mental health status. Based on the assessment results, the server generates personalized counseling content. It uses large-scale language models (LLMs) to provide feedback and advice tailored to the user's condition.

[0145] 3. Add specific examples to the description

[0146] For example, suppose a user is enjoying a long shopping session in a virtual store. The smartwatch collects the user's heart rate and sleep data, which are then analyzed by the server. The results show that the user's heart rate is higher than usual and that they have not been getting enough sleep recently. Based on this assessment, the server generates advice such as "Try some light exercise to relax."

[0147] Furthermore, by analyzing user purchasing behavior data, it is possible to recommend relaxation goods or massage equipment to users who are feeling stressed or tired, allowing users to receive product suggestions that take their psychological state into consideration.

[0148] Prompt Sentence Examples

[0149] Below is an example of a prompt sentence to input to a large-scale language model (LLM).

[0150] Create a program that predicts a user's stress level based on their heart rate and sleep data, and generates personalized counseling content.

[0151] Heart rate data: [75, 80, 72, 78, 77]

[0152] Sleep data: [6, 7, 5, 8, 6]

[0153] Stress Level: [3, 4, 2, 5, 3]

[0154] Current data to predict: Heart rate 79, sleep quality 6, stress level 4

[0155] Output: Personalized advice based on stress level

[0156] This system allows users to receive product suggestions that take their psychological state into account even in virtual stores, enabling them to enjoy a comfortable shopping experience.

[0157] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0158] Step 1:

[0159] Users use smartphones or smartwatches to collect vital data and behavioral pattern data.

[0160] How it works: The smartwatch records your heart rate and sleep data, and your smartphone receives this data via an app.

[0161] Input: Heart rate data, sleep data.

[0162] Output: Collected heart rate and sleep data.

[0163] Step 2:

[0164] The terminal transmits the collected data to the server.

[0165] Specific operation: The smartphone uploads the collected data to the server via the Internet.

[0166] Input: Collected heart rate and sleep data.

[0167] Output: Data transfer to the server.

[0168] Step 3:

[0169] The server cleans and standardizes the received data.

[0170] What it does: It uses data cleaning techniques to remove outliers and incomplete data, and standardization techniques to convert data into a consistent format.

[0171] Input: Collected heart rate and sleep data.

[0172] Output: Cleaned and standardized data.

[0173] Step 4:

[0174] The server analyzes the cleaned and standardized data to assess the user's mental health status.

[0175] What it does: Analyzes heart rate and sleep patterns using statistical models and machine learning algorithms (e.g., scikit-learn).

[0176] Input: Cleaned and standardized data.

[0177] Output: The user's mental health assessment results.

[0178] Step 5:

[0179] The server generates personalized counseling content based on the evaluation results.

[0180] Specific operation: Uses a large-scale language model (LLM) to create counseling content appropriate for the user's condition.

[0181] Input: User's mental health assessment results.

[0182] Output: Personalized counseling content.

[0183] Step 6:

[0184] The server conducts interactive counseling with the user.

[0185] Specific operation: Through a smartphone app, questions are presented to the user and the next action is determined based on the user's answer.

[0186] Input: personalized counseling content.

[0187] Output: Answers from the user and the interaction history.

[0188] Step 7:

[0189] The server continues to monitor the user's data even after the counseling session.

[0190] Specific operation: Continuously collects and analyzes data from smartwatches and smartphones.

[0191] Input: Data from smartwatch and smartphone.

[0192] Output: Continuously updated mental health assessment results for the user.

[0193] Step 8:

[0194] The server also collects and analyzes user purchasing behavior data.

[0195] Specific operations: Record and analyze shopping history and product browsing history in virtual stores.

[0196] Input: Purchasing behavior data.

[0197] Output: Parsed purchasing behavior data.

[0198] Step 9:

[0199] The server generates product proposals that link the user's psychological state with their purchasing behavior.

[0200] Specific operation: Based on the user's mental health assessment results and purchasing behavior data, product suggestions are created using a large-scale language model (LLM).

[0201] Input: User's mental health assessment results and purchasing behavior data.

[0202] Output: Personalized product suggestions.

[0203] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0204] This invention is an AI counselor system for supporting users' mental health care, and combines an emotion engine that recognizes the user's emotional state. The system aims to collect data from users via devices such as smartphones and smartwatches, analyze and evaluate that data, and provide personalized counseling.

[0205] Specifically, the server, the terminal, or the user operates as follows.

[0206] First, the user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily life.

[0207] Next, the device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[0208] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[0209] The data received by the server is first cleaned to remove outliers and incomplete data. Next, the data is standardized and converted into a format that is easy to analyze. Statistical models and machine learning algorithms are then used to analyze the user's heart rate fluctuations, sleep patterns, and other factors. Based on the results of this analysis, the user's mental health status is assessed. For example, if the heart rate is higher than normal and the user is not getting enough sleep, the server will assess that the user is feeling stressed.

[0210] Furthermore, this invention uses an emotion engine. The device (smartphone) collects the user's facial expressions and voice and analyzes them through the emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time. Voice analysis detects changes in emotion from the tone and speed of the user's voice. This emotion data is also sent to the server and integrated with other vital data and behavioral pattern data.

[0211] The server can then factor in emotional data to further assess the user's mental health. For example, if the user's heart rate is high and their voice tone is depressed, the server may assess that the user is likely depressed.

[0212] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0213] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0214] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0215] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0216] The processing flow will be explained below.

[0217] Step 1:

[0218] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0219] Step 2:

[0220] The vital data and behavioral pattern data collected by the device (smartwatch) are transferred to a smartphone in real time via wireless communication.

[0221] Step 3:

[0222] The device (smartphone) periodically sends the received data to the server. The data is encrypted and sent over the Internet.

[0223] Step 4:

[0224] The server cleans the incoming data, removing outliers and incomplete data, checks the data for integrity, and converts it into a format suitable for analysis.

[0225] Step 5:

[0226] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to analyze the user's heart rate variability and sleep patterns.

[0227] Step 6:

[0228] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0229] Step 7:

[0230] The device (smartphone) collects the user's facial expressions and voice data, and the collected emotion data is sent to the emotion engine.

[0231] Step 8:

[0232] The emotion engine on the server analyzes the user's facial expressions and evaluates emotions such as joy, sadness, anger, etc. in real time. It also analyzes voice data and recognizes the user's emotional state from the tone and speed of the voice.

[0233] Step 9:

[0234] The server then combines the emotion data with other vital and behavioral data to provide a more detailed assessment of the user's mental health. For example, if the facial expression indicates sadness and the voice is depressed, it may determine that the user is likely depressed.

[0235] Step 10:

[0236] The server generates personalized counseling content based on the evaluation results, using a large-scale language model (LLM) to generate advice and feedback tailored to the user's condition.

[0237] Step 11:

[0238] When a user opens a counseling app on their smartphone, they are connected to an AI counselor through the app.

[0239] Step 12:

[0240] The AI ​​counselor on the server presents questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[0241] Step 13:

[0242] The user answers the questions of the AI ​​counselor. The answers are sent to the server, and the AI ​​counselor decides the next question or advice.

[0243] Step 14:

[0244] The server analyzes the user's answers and provides next steps and specific advice, such as "Try taking deep breaths, they'll help you relax."

[0245] Step 15:

[0246] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor the user's mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, another counseling notification can be sent.

[0247] Example 2

[0248] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0249] Conventional mental healthcare systems have limitations in assessing a user's emotional state based solely on physiological and behavioral data. It is difficult to grasp the user's emotional state in detail. In particular, because fluctuations in mental health are also reflected in facial expressions and voice, assessments that do not take these data into account are insufficient, resulting in a problem of reduced accuracy in personalized advice.

[0250] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting physiological data and behavioral data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized advice content based on the evaluation results, means for providing advice to the user in an interactive format, means for continuously monitoring the user's data even after the advice is provided, means for collecting the user's facial expression data and voice data and analyzing the emotional state, and means for evaluating the user's mental health state in detail based on the analysis results. This makes it possible to evaluate the user's mental health state in detail based on the user's facial expression and voice data in addition to the user's physiological data, thereby enabling the generation and provision of highly accurate personalized advice content.

[0251] "Physiological data" refers to data relating to the internal state of the user's body, such as heart rate, blood pressure, body temperature, and breathing patterns.

[0252] "Behavioral data" refers to data such as the user's movements and activity levels in daily life, sleep patterns, and exercise levels.

[0253] "Mental health status" refers to a state related to mental health, such as a user's stress level, emotional state, psychological stability, and mood.

[0254] "Personalized advice" refers to feedback and advice that is customized based on each user's individual mental health status and characteristics.

[0255] "Dialogue-based advice" is advice provided through an interactive exchange with the user, often in a conversational format and involving a question-and-answer process.

[0256] "Monitoring" is a means of continuously tracking a user's status and data and responding if anything deviates from the normal range.

[0257] "Facial expression data" refers to data relating to the user's emotional or mood state, which can be obtained from facial expressions, such as smiles, anger, sadness, etc.

[0258] "Voice data" refers to data relating to the emotions and mental state of a user that can be obtained from the tone, pitch, speed, strength, etc. of the voice uttered by the user.

[0259] "Analysis" is the process of evaluating collected data using statistical models and machine learning algorithms to derive meaningful information.

[0260] The present invention provides a system for providing a detailed assessment of a user's mental health status and providing personalized advice. The system collects data from a device worn by the user and analyzes the data to assess the user's health status. Specific embodiments for implementing the present invention will be described below.

[0261] First, the user wears a device such as a smartwatch or smartphone. The smartwatch collects physiological data such as heart rate, blood pressure, body temperature, and sleep patterns, as well as behavioral data such as activity levels, on a daily basis. The smartphone also collects the user's emotional state using facial and voice recognition technologies.

[0262] The collected data is transferred from the device (smartwatch) to a smartphone via wireless communication (e.g., Bluetooth), where it is encrypted and securely transmitted to a server via the Internet.

[0263] The server cleans the received data, removes outliers, and standardizes it. It then analyzes the data using statistical models and machine learning algorithms. This analysis assesses the user's mental health based on heart rate variability and sleep patterns. It also includes an emotion engine that analyzes facial expressions and voice data, allowing it to assess the user's emotional state.

[0264] For example, if the user's heart rate is higher than normal and the tone of their voice is depressed, the server can assess that the user is feeling stressed.

[0265] The server then uses a large-scale language model (LLM) to generate personalized advice that provides feedback and advice tailored to the user's condition. The generated advice is then provided to the user through a smartphone app. The app interactively presents questions to the user and determines the next action based on the user's answers.

[0266] Examples of specific prompts include the following:

[0267] "Evaluate whether the user is experiencing stress based on recent heart rate and sleep pattern data."

[0268] "When a user asks about recent mood changes, generate a recommendation based on their answer, suggesting the next course of action."

[0269] Finally, the server continues to collect user data after the advice is implemented to continuously monitor the user's mental health, providing additional advice or warnings as needed to help the user receive effective mental health care.

[0270] This system allows users to manage their own mental health 24 hours a day and receive timely and accurate feedback. It also makes up for the shortage of medical resources and contributes to improving the mental health of society as a whole.

[0271] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0272] Step 1: Collect user data

[0273] A user puts on a smartwatch. The smartwatch automatically collects physiological and behavioral data, such as heart rate, sleep patterns, and activity levels. For example, the smartwatch starts measuring heart rate the moment the user wakes up in the morning and puts it on. The input data is about the user's physiological state and behavior, and the output is vital data stored on the device.

[0274] Step 2: Transferring data

[0275] The device (smartwatch) transmits collected vital data and behavioral pattern data to a smartphone in real time using wireless communication (such as Bluetooth). For example, after a user finishes jogging, the device automatically transmits heart rate and calorie consumption data to the smartphone. The input data is the vital data stored in the smartwatch, and the output is the data transferred to the smartphone.

[0276] Step 3: Sending data

[0277] The device (smartphone) periodically sends the received data to a server. The data is encrypted and sent securely over the Internet without delay. The input data is vital and behavioral data stored on the smartphone, and the output is encrypted data sent to the server.

[0278] Step 4: Process the data

[0279] The data received by the server is first cleaned to remove outliers and incomplete data. Then, a standardization process is performed to convert the data into a format that is easier to analyze. The input data is the encrypted data sent to the server, and the output is the cleaned and standardized data. Specifically, heart rate data from people who are active late at night is removed as an outlier, and the remaining data is standardized.

[0280] Step 5: Mental health assessment

[0281] The server evaluates the user's mental health based on the analyzed data. This evaluation is performed using statistical models and machine learning algorithms. The input data is cleaned and standardized data, and the output is the user's mental health assessment result. Specifically, if a high heart rate and lack of sleep are detected, the server evaluates the user as being in a stressed state.

[0282] Step 6: Collect and analyze emotion data

[0283] The device (smartphone) collects the user's facial expressions and voice and analyzes them through an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects changes in emotion from the tone and speed of voice. The input data is facial expression data and voice data, and the output is emotional data analyzed in real time.

[0284] Step 7: Sending Emotion Data

[0285] The device (smartphone) sends the collected emotional data to a server, which then integrates this data with other vital data. The input data is emotional data analyzed in real time, and the output is the emotional data sent to the server.

[0286] Step 8: Detailed Mental Health Assessment

[0287] The server integrates the emotional data and vital data to provide a more detailed assessment of the user's mental health. The input data is the integrated emotional and vital data, and the output is a detailed mental health assessment result. Specifically, if the heart rate is high and the voice tone is depressed, the server assesses that the user is likely to be depressed.

[0288] Step 9: Creating counseling content

[0289] The server generates personalized advice based on the user's mental health assessment using a large-scale language model (LLM). The input data is the detailed mental health assessment results, and the output is customized advice. For example, specific advice such as "Try deep breathing and relaxing music" as relaxation techniques to reduce stress is generated.

[0290] Step 10: Conducting counseling

[0291] When a user opens the app on their smartphone, the device connects them to an AI counselor. The AI ​​counselor presents questions to the user in a dialogue format and determines the next action based on the user's answers. The input data is customized advice, and the output is consultation and feedback provided to the user. Specifically, if the user answers "I haven't been able to sleep lately," the AI ​​counselor will present the next question: "Is that something you're worried about?"

[0292] Step 11: Continuous monitoring and feedback

[0293] The server continues to collect data on the user and continuously monitors their mental health. It provides additional counseling or warnings as needed. The input data is continuously collected vital and emotional data, and the output is additional advice or warnings. Specifically, if the user's heart rate again shows abnormal values, another counseling notification is sent.

[0294] (Application example 2)

[0295] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0296] Currently, many people need mental health support, but it is difficult to receive professional counseling. Furthermore, there is a lack of systems that can detect mental health problems such as stress and anxiety early and implement appropriate measures. In particular, there is a need for systems that provide real-time mental health care in daily life and provide appropriate content for relaxation and learning. A system that analyzes a user's emotional state and provides personalized counseling and content tailored to that state would be extremely useful in improving mental health, but such systems have not yet been fully implemented.

[0297] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0298] In this invention, the server includes means for collecting vital data and behavioral pattern data from a user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, and means for analyzing the user's emotional state and recommending mental health care content based on the emotional data. This allows the user to receive mental health care while being provided with personalized content such as relaxing music, meditation guides, stretching videos, and learning content in real time, tailored to their mental health state.

[0299] "Vital data" refers to physiological data such as a user's heart rate, sleep patterns, and activity level.

[0300] "Behavioral pattern data" refers to data related to the user's behavior and activities in their daily lives.

[0301] "Emotional data" refers to data relating to the emotional state of a user that is analyzed from their facial expressions and voice.

[0302] "Analysis" refers to the process of evaluating collected data using statistical models and machine learning algorithms to derive results.

[0303] "Mental health status" refers to the psychological and emotional well-being of a user.

[0304] "Personalized counseling content" refers to counseling advice and feedback that is optimized based on the individual user's mental health status.

[0305] "Dialogue-based counseling" refers to interactive counseling conducted between the user and the AI ​​counselor through questions and answers.

[0306] "Monitoring" refers to the process of continuously watching user data to detect fluctuations and anomalies.

[0307] "Content" refers to relaxing music, meditation guides, stretching videos, learning content, etc. provided to support users' mental health care.

[0308] "Recommendation method" refers to the process of selecting and providing optimal content to the user based on the user's emotional state and vital data.

[0309] This invention is a comprehensive AI counselor system to support users' mental health care. It collects and analyzes vital data, behavioral pattern data, and emotional data, and provides optimal counseling and content based on the results.

[0310] This system consists of three main components: a server, a terminal (such as a smartphone or smartwatch), and a user.

[0311] First, the user wears a smartwatch and collects vital data such as heart rate, sleep patterns, and activity levels during daily activities. The device then transfers this collected data in real time to a smartphone, which then transmits the data to a server.

[0312] The server receives the data via a secure internet connection, first cleaning it to remove outliers and incomplete data, then standardizing and converting it into an easy-to-analyze format, and using statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other data to assess their mental health.

[0313] In addition, the user's smartphone collects facial expressions and voice data and analyzes the emotional data using an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects emotional changes from the tone and speed of the voice. This emotional data is also sent to a server and integrated with other vital data and behavioral pattern data.

[0314] The server uses this integrated data to perform a detailed assessment of the user's mental health status, and based on the assessment results, generates personalized counseling content and optimal content (relaxing music, meditation guides, stretching videos, learning content, etc.). The generated content is delivered to the user's smartphone, allowing the user to receive interactive counseling or view recommended content.

[0315] Here's a specific example: If a user feels like they want to relax, their heart rate will rise and their tone of voice will indicate they are feeling stressed. In this case, the system will provide relaxing music and deep breathing guidance. For example, the system might say, "Your heart rate has been high for some time. We recommend some relaxing music (classical, nature sounds, etc.)."

[0316] In this way, this system is a powerful tool for supporting users' mental health care and improving the quality of their daily lives. Users can always receive the optimal support for their condition in real time.

[0317] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0318] Step 1:

[0319] The user wears a smartwatch to collect vital data such as heart rate, sleep patterns, and activity level. The input is the user's physiological information, and the output is vital data. This data is recorded in real time by the smartwatch.

[0320] Step 2:

[0321] The terminal (smartwatch) transfers the vital data collected to the smartphone. The input is the vital data collected by the smartwatch, and the output is the data transferred to the smartphone. The data is transmitted in real time via wireless communication.

[0322] Step 3:

[0323] The data received by the device (smartphone) is periodically sent to the server. The input is the vital data transferred to the smartphone, and the output is the data sent to the server. The data is encrypted and sent without delay over the Internet.

[0324] Step 4:

[0325] The server cleans the data it receives, removing outliers and incomplete data. The input is the vital data sent to the server, and the output is the cleaned data. At this stage, the data is standardized and converted into a format that is easy to analyze.

[0326] Step 5:

[0327] The server uses statistical models and machine learning algorithms to analyze the user's heart rate fluctuations and sleep patterns. The input is cleaned vital data, and the output is the analysis results (the user's mental health status). The data analysis evaluates whether the user is feeling stressed.

[0328] Step 6:

[0329] The device (smartphone) collects the user's facial expressions and voice and analyzes them using an emotion engine. The input is the user's facial expression image and voice clip, and the output is the analyzed emotion data. Emotions such as sadness, anger, and joy are recognized from facial expressions, and emotional changes are recognized in real time from the tone and speed of voice.

[0330] Step 7:

[0331] The emotional data collected by the device is sent to a server and integrated with other vital data and behavioral pattern data. The input is the analyzed emotional data, and the output is an integrated dataset. Based on the integrated data, a more detailed mental health status is assessed.

[0332] Step 8:

[0333] The server generates personalized counseling and content for the user's mental health care based on the evaluation results. The input is the integrated dataset, and the output is the generated counseling and recommended content. Specifically, it uses a large-scale language model (LLM) to create feedback and advice, and recommends relaxing music, meditation guides, stretching videos, learning content, and other items that are optimal for the user's current state.

[0334] Step 9:

[0335] When a user opens a smartphone app to receive counseling, the device connects the user with an AI counselor. The input is the user's counseling request, and the output is an interactive counseling session. The AI ​​counselor on the server presents questions to the user and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?"

[0336] Step 10:

[0337] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. The input is continuously collected vital and emotional data, and the output is an updated mental health assessment. If necessary, the server provides additional counseling or warnings. Specifically, if an abnormality such as a recurring high heart rate is detected, the server sends another counseling notification.

[0338] 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.

[0339] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0340] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0341] [Second embodiment]

[0342] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0343] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0344] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0345] 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.

[0346] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0347] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0348] 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.

[0349] 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.

[0350] 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 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.

[0351] 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.

[0352] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0353] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0354] This invention is an AI counselor system to support users' mental health care. The system collects data from users via devices such as smartphones and smartwatches, analyzes and evaluates that data, and provides personalized counseling.

[0355] Specifically, the server, the terminal, or the user operates as follows.

[0356] First, a user uses a smartphone or smartwatch to carry out daily activities. For example, the smartwatch collects sleep data while the user is sleeping, and records heart rate and activity level while exercising. In this way, vital data and behavioral pattern data are collected.

[0357] The device then sends the collected data to a server, which transfers it over the internet and analyzes it.

[0358] The server first cleans the received data to remove outliers and incomplete data. Next, it standardizes the data and converts it into a format that is easy to analyze. It then uses statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other factors. Based on the results of this analysis, the server evaluates the user's mental health status. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0359] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0360] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0361] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0362] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0363] The processing flow will be explained below.

[0364] Step 1:

[0365] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0366] Step 2:

[0367] The device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[0368] Step 3:

[0369] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[0370] Step 4:

[0371] The server cleans the data it receives, removing outliers and incomplete data, during which the data is checked for integrity and converted into a format suitable for analysis.

[0372] Step 5:

[0373] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to assess the user's heart rate variability, sleep patterns, and more.

[0374] Step 6:

[0375] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, it will determine that the user is feeling stressed.

[0376] Step 7:

[0377] The server generates personalized counseling content for the user based on the evaluation results, using a large-scale language model (LLM) to create advice and feedback that is appropriate for the user.

[0378] Step 8:

[0379] The user opens a counseling app on their smartphone and is connected to an AI counselor through the app.

[0380] Step 9:

[0381] The AI ​​counselor on the server conducts counseling by presenting questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[0382] Step 10:

[0383] The user answers the AI ​​counselor's questions, which allows the AI ​​counselor to understand the user's condition and the problems they are experiencing.

[0384] Step 11:

[0385] The server analyzes the user's answers and determines the next question and specific advice. For example, it might suggest, "Deep breathing has a relaxing effect. Please try it."

[0386] Step 12:

[0387] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor their mental health, providing additional counseling or warnings as needed to support ongoing care.

[0388] Example 1

[0389] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0390] Mental health problems such as stress and anxiety are on the rise in modern society, creating a need for rapid and accurate responses. However, traditional mental health care relies mainly on face-to-face counseling by experts, which poses challenges such as time and location constraints and a shortage of experts. Furthermore, a lack of a personalized approach for individual users makes effective care difficult. Given these circumstances, there is a need for a system that can monitor users' mental health status in real time and respond quickly.

[0391] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0392] In this invention, the server includes means for collecting physiological data and behavioral pattern data from a user, means for transmitting the collected data to the server via a network, means for cleaning and standardizing the received data, means for analyzing the cleaned data and evaluating the user's psychological health state, means for generating personalized counseling content based on the evaluation results, means for providing feedback and advice to the user using a generative AI model, means for conducting counseling with the user in an interactive format, and means for continuously monitoring the user's data even after counseling. This makes it possible to monitor the user's mental health state in real time and provide prompt and personalized counseling.

[0393] "User" refers to an individual who provides physiological data and behavioral pattern data and uses the system.

[0394] "Physiological data" refers to data relating to a user's physical condition, such as heart rate, sleep data, body temperature, blood pressure, etc.

[0395] "Behavior pattern data" refers to data related to the user's behavior, such as the number of steps taken, amount of exercise, and duration of activity.

[0396] "Terminal" refers to a device, such as a smartphone or smartwatch, that a user uses to collect physiological data and behavioral pattern data.

[0397] "Server" refers to a computer system that receives, cleans, standardizes, and analyzes data sent by users and generates counseling content.

[0398] "Cleaning" refers to the process of removing outliers and incomplete information from collected data and preparing the data so that accurate analysis can be performed.

[0399] "Standardization" refers to the process of unifying the format of data collected from different devices and sensors, making it easier to analyze.

[0400] "Analysis" refers to the process of using cleaned and standardized data to assess a user's psychological well-being using statistical models and machine learning algorithms.

[0401] A "generative AI model" refers to an algorithm that uses a large-scale language model to generate feedback and advice tailored to the user's condition.

[0402] "Counseling content" refers to information including feedback and advice generated based on the analysis results.

[0403] "Dialogue-based counseling" refers to an interactive counseling process, such as a question-and-answer format, conducted between the user and the AI ​​counselor.

[0404] "Monitoring" refers to the process of continuing to collect and analyze user data and monitor their mental health status even after counseling.

[0405] This invention is an AI counselor system to support users' mental health care. The system collects physiological data and behavioral pattern data using devices such as smartphones and smartwatches, analyzes and evaluates the data, and provides personalized counseling.

[0406] Data collection

[0407] Users use smartphones or smartwatches to collect daily activity data, including physiological data such as heart rate, sleep data, and activity level, as well as behavioral pattern data. For example, when a user goes running, the smartwatch records their heart rate and distance, and automatically collects sleep data at night.

[0408] Data transmission

[0409] The device sends the collected data to a server over the Internet, specifically, the user's smartphone uploads the data to the server via Wi-Fi or mobile data network.

[0410] Data Cleaning and Standardization

[0411] The server cleans the data it receives, removing outliers and incomplete data, then standardizes it and converts it into a format that's easier to analyze, for example by standardizing the timestamp format and scaling it so that data from different devices can be handled at the same scale.

[0412] Data analysis

[0413] The server analyzes the cleaned and standardized data using statistical models and machine learning algorithms. Specifically, it uses programming languages ​​such as Python to run machine learning algorithms (e.g., random forests) to assess the user's psychological well-being. This analysis allows it to understand the user's stress level and mental health status from heart rate variability and sleep patterns.

[0414] Counseling content generation

[0415] The server uses a generative AI model (large-scale language model) to generate personalized counseling content based on the evaluation results. For example, if the user is evaluated as feeling stressed, the server generates feedback and advice suggesting ways to relax. Specific examples of prompts for the generative AI model are as follows:

[0416] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[0417] Providing counseling

[0418] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will present the next question, "Is that something you're worried about?"

[0419] Follow-up and monitoring

[0420] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, the server can send another counseling notification.

[0421] This system allows users to receive counseling 24 hours a day even if they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, thereby contributing to improving labor productivity in society.

[0422] As described above, the present invention provides specific means for realizing more efficient and effective mental health care for users.

[0423] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0424] Step 1:

[0425] A user uses a smartphone or smartwatch to collect physiological data and behavioral pattern data. Specifically, the user wears the smartwatch and goes about their daily activities. During this time, their heart rate, sleep data, and activity level are recorded. Input data includes a heart rate log, sleep log, and exercise log, which are raw data obtained from the smartwatch. The output is the collected physiological data and behavioral pattern data.

[0426] Step 2:

[0427] The device sends the collected data to the server. Specifically, the user's smartphone uses Wi-Fi or mobile data network to obtain data from the smartwatch and uploads it to the server. The input is the data obtained from the smartwatch, and the output is the data sent to the server.

[0428] Step 3:

[0429] The server cleans the received data. Specifically, the server removes outliers and incomplete data from the received data. The input is the raw data sent from the device, and the output is the cleaned data. For example, outliers such as a heart rate of 0 or an extremely high heart rate are filtered out.

[0430] Step 4:

[0431] The server standardizes the cleaned data. Specifically, it standardizes the data format so that data from different devices can be analyzed at the same scale. The input is cleaned data, and the output is standardized data. For example, it standardizes the timestamp format from different devices.

[0432] Step 5:

[0433] The server analyzes the standardized data. Specifically, it uses a machine learning algorithm to assess the user's psychological health. This algorithm uses a programming language such as Python. The input is the standardized data, and the output is a psychological health assessment as an analysis result. For example, a random forest algorithm is used to assess the user's stress level based on sleep patterns and heart rate fluctuations.

[0434] Step 6:

[0435] The server generates counseling content based on the analysis results. Specifically, it uses a large-scale language model (LLM) to generate feedback and advice appropriate for the user. The input is the analysis results, and the output is the generated counseling content. For example, if the user is feeling stressed, it generates content suggesting ways to relax. An example of a prompt sentence for the generative AI model is as follows:

[0436] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[0437] Step 7:

[0438] The device provides counseling. Specifically, when a user opens the app on their smartphone, the device connects the user to an AI counselor on the server. The input is the generated counseling content, and the output is feedback and advice provided to the user. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will pose the next question, "Is that something you're worried about?"

[0439] Step 8:

[0440] The server continues to monitor the user's data. Specifically, it collects data even after the counseling session ends and monitors the user's mental health status based on the new data. The input is the continuously collected data, and the output is an updated mental health assessment and, if necessary, a re-counseling notification. For example, if an abnormality such as a re-elevated heart rate is detected, the server will send another counseling notification.

[0441] (Application example 1)

[0442] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0443] Conventional mental healthcare systems assess a user's mental health status and provide counseling based on the collection and analysis of their physiological and behavioral pattern data. However, no systems have taken into account the impact of a user's psychological state on purchasing behavior. This has made it difficult to improve the customer experience in virtual stores. Therefore, there has been a need for a system that can link a user's mental health status with their purchasing behavior and make appropriate product recommendations.

[0444] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0445] In this invention, the server includes means for collecting vital data and behavioral pattern data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, means for collecting and analyzing user purchasing behavior data, and means for generating product proposals that link the user's psychological state with their purchasing behavior, thereby enabling personalized product proposals that take the user's psychological state into consideration.

[0446] "User" means an individual or group of people who use the system.

[0447] "Vital data" refers to physiological data including biosignals such as heart rate, blood pressure, and body temperature.

[0448] "Behavior pattern data" refers to data relating to the user's daily activities, sleep data, amount of exercise, and other behavioral data.

[0449] "Analysis" means evaluating collected data using statistical methods and machine learning algorithms.

[0450] "Mental health status" refers to a user's mental health and psychological balance.

[0451] "Counseling" means the process of providing advice and feedback to support a user's mental health.

[0452] "Continuous monitoring" means collecting data about a user over a long period of time and monitoring their condition.

[0453] "Purchasing behavior data" refers to behavioral data related to purchasing, such as a user's shopping history and product browsing history.

[0454] "Product suggestion" means analyzing the user's psychological state and purchasing behavior to recommend appropriate products.

[0455] This invention relates to a system for supporting users' mental health care and improving customer experience in virtual stores. This system collects vital data and behavioral pattern data from users, analyzes them, and evaluates the user's mental health state. It then generates personalized counseling content based on the collected data and provides counseling in an interactive format. It also collects data on the user's purchasing behavior and has the function of suggesting products linked to the user's psychological state.

[0456] 1. Program Generation

[0457] The program of this system is configured as follows:

[0458] 2. Explain the program's processing in natural language

[0459] When users use their smartphones or smartwatches to carry out activities, these devices collect vital data such as heart rate and sleep data. When users shop in virtual stores, purchasing behavior data is also collected. This data is sent to a server via the Internet.

[0460] The server cleans and standardizes the collected data, removing outliers and incomplete data. It then analyzes the data using statistical models and machine learning algorithms (e.g., scikit-learn) to assess the user's mental health status. Based on the assessment results, the server generates personalized counseling content. It uses large-scale language models (LLMs) to provide feedback and advice tailored to the user's condition.

[0461] 3. Add specific examples to the description

[0462] For example, suppose a user is enjoying a long shopping session in a virtual store. The smartwatch collects the user's heart rate and sleep data, which are then analyzed by the server. The results show that the user's heart rate is higher than usual and that they have not been getting enough sleep recently. Based on this assessment, the server generates advice such as "Try some light exercise to relax."

[0463] Furthermore, by analyzing user purchasing behavior data, it is possible to recommend relaxation goods or massage equipment to users who are feeling stressed or tired, allowing users to receive product suggestions that take their psychological state into consideration.

[0464] Prompt Sentence Examples

[0465] Below is an example of a prompt sentence to input to a large-scale language model (LLM).

[0466] Create a program that predicts a user's stress level based on their heart rate and sleep data, and generates personalized counseling content.

[0467] Heart rate data: [75, 80, 72, 78, 77]

[0468] Sleep data: [6, 7, 5, 8, 6]

[0469] Stress Level: [3, 4, 2, 5, 3]

[0470] Current data to predict: Heart rate 79, sleep quality 6, stress level 4

[0471] Output: Personalized advice based on stress level

[0472] This system allows users to receive product suggestions that take their psychological state into account even in virtual stores, enabling them to enjoy a comfortable shopping experience.

[0473] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0474] Step 1:

[0475] Users use smartphones or smartwatches to collect vital data and behavioral pattern data.

[0476] How it works: The smartwatch records your heart rate and sleep data, and your smartphone receives this data via an app.

[0477] Input: Heart rate data, sleep data.

[0478] Output: Collected heart rate and sleep data.

[0479] Step 2:

[0480] The terminal transmits the collected data to the server.

[0481] Specific operation: The smartphone uploads the collected data to the server via the Internet.

[0482] Input: Collected heart rate and sleep data.

[0483] Output: Data transfer to the server.

[0484] Step 3:

[0485] The server cleans and standardizes the received data.

[0486] What it does: It uses data cleaning techniques to remove outliers and incomplete data, and standardization techniques to convert data into a consistent format.

[0487] Input: Collected heart rate and sleep data.

[0488] Output: Cleaned and standardized data.

[0489] Step 4:

[0490] The server analyzes the cleaned and standardized data to assess the user's mental health status.

[0491] What it does: Analyzes heart rate and sleep patterns using statistical models and machine learning algorithms (e.g., scikit-learn).

[0492] Input: Cleaned and standardized data.

[0493] Output: The user's mental health assessment results.

[0494] Step 5:

[0495] The server generates personalized counseling content based on the evaluation results.

[0496] Specific operation: Uses a large-scale language model (LLM) to create counseling content appropriate for the user's condition.

[0497] Input: User's mental health assessment results.

[0498] Output: Personalized counseling content.

[0499] Step 6:

[0500] The server conducts interactive counseling with the user.

[0501] Specific operation: Through a smartphone app, questions are presented to the user and the next action is determined based on the user's answer.

[0502] Input: personalized counseling content.

[0503] Output: Answers from the user and the interaction history.

[0504] Step 7:

[0505] The server continues to monitor the user's data even after the counseling session.

[0506] Specific operation: Continuously collects and analyzes data from smartwatches and smartphones.

[0507] Input: Data from smartwatch and smartphone.

[0508] Output: Continuously updated mental health assessment results for the user.

[0509] Step 8:

[0510] The server also collects and analyzes user purchasing behavior data.

[0511] Specific operations: Record and analyze shopping history and product browsing history in virtual stores.

[0512] Input: Purchasing behavior data.

[0513] Output: Parsed purchasing behavior data.

[0514] Step 9:

[0515] The server generates product proposals that link the user's psychological state with their purchasing behavior.

[0516] Specific operation: Based on the user's mental health assessment results and purchasing behavior data, product suggestions are created using a large-scale language model (LLM).

[0517] Input: User's mental health assessment results and purchasing behavior data.

[0518] Output: Personalized product suggestions.

[0519] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0520] This invention is an AI counselor system for supporting users' mental health care, and combines an emotion engine that recognizes the user's emotional state. The system aims to collect data from users via devices such as smartphones and smartwatches, analyze and evaluate that data, and provide personalized counseling.

[0521] Specifically, the server, the terminal, or the user operates as follows.

[0522] First, the user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily life.

[0523] Next, the device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[0524] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[0525] The data received by the server is first cleaned to remove outliers and incomplete data. Next, the data is standardized and converted into a format that is easy to analyze. Statistical models and machine learning algorithms are then used to analyze the user's heart rate fluctuations, sleep patterns, and other factors. Based on the results of this analysis, the user's mental health status is assessed. For example, if the heart rate is higher than normal and the user is not getting enough sleep, the server will assess that the user is feeling stressed.

[0526] Furthermore, this invention uses an emotion engine. The device (smartphone) collects the user's facial expressions and voice and analyzes them through the emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time. Voice analysis detects changes in emotion from the tone and speed of the user's voice. This emotion data is also sent to the server and integrated with other vital data and behavioral pattern data.

[0527] The server can then factor in emotional data to further assess the user's mental health. For example, if the user's heart rate is high and their voice tone is depressed, the server may assess that the user is likely depressed.

[0528] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0529] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0530] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0531] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0532] The processing flow will be explained below.

[0533] Step 1:

[0534] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0535] Step 2:

[0536] The vital data and behavioral pattern data collected by the device (smartwatch) are transferred to a smartphone in real time via wireless communication.

[0537] Step 3:

[0538] The device (smartphone) periodically sends the received data to the server. The data is encrypted and sent over the Internet.

[0539] Step 4:

[0540] The server cleans the incoming data, removing outliers and incomplete data, checks the data for integrity, and converts it into a format suitable for analysis.

[0541] Step 5:

[0542] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to analyze the user's heart rate variability and sleep patterns.

[0543] Step 6:

[0544] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0545] Step 7:

[0546] The device (smartphone) collects the user's facial expressions and voice data, and the collected emotion data is sent to the emotion engine.

[0547] Step 8:

[0548] The emotion engine on the server analyzes the user's facial expressions and evaluates emotions such as joy, sadness, anger, etc. in real time. It also analyzes voice data and recognizes the user's emotional state from the tone and speed of the voice.

[0549] Step 9:

[0550] The server then combines the emotion data with other vital and behavioral data to provide a more detailed assessment of the user's mental health. For example, if the facial expression indicates sadness and the voice is depressed, it may determine that the user is likely depressed.

[0551] Step 10:

[0552] The server generates personalized counseling content based on the evaluation results, using a large-scale language model (LLM) to generate advice and feedback tailored to the user's condition.

[0553] Step 11:

[0554] When a user opens a counseling app on their smartphone, they are connected to an AI counselor through the app.

[0555] Step 12:

[0556] The AI ​​counselor on the server presents questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[0557] Step 13:

[0558] The user answers the questions of the AI ​​counselor. The answers are sent to the server, and the AI ​​counselor decides the next question or advice.

[0559] Step 14:

[0560] The server analyzes the user's answers and provides next steps and specific advice, such as "Try taking deep breaths, they'll help you relax."

[0561] Step 15:

[0562] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor the user's mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, another counseling notification can be sent.

[0563] Example 2

[0564] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0565] Conventional mental healthcare systems have limitations in assessing a user's emotional state based solely on physiological and behavioral data. It is difficult to grasp the user's emotional state in detail. In particular, because fluctuations in mental health are also reflected in facial expressions and voice, assessments that do not take these data into account are insufficient, resulting in a problem of reduced accuracy in personalized advice.

[0566] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting physiological data and behavioral data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized advice content based on the evaluation results, means for providing advice to the user in an interactive format, means for continuously monitoring the user's data even after the advice is provided, means for collecting the user's facial expression data and voice data and analyzing the emotional state, and means for evaluating the user's mental health state in detail based on the analysis results. This makes it possible to evaluate the user's mental health state in detail based on the user's facial expression and voice data in addition to the user's physiological data, thereby enabling the generation and provision of highly accurate personalized advice content.

[0567] "Physiological data" refers to data relating to the internal state of the user's body, such as heart rate, blood pressure, body temperature, and breathing patterns.

[0568] "Behavioral data" refers to data such as the user's movements and activity levels in daily life, sleep patterns, and exercise levels.

[0569] "Mental health status" refers to a state related to mental health, such as a user's stress level, emotional state, psychological stability, and mood.

[0570] "Personalized advice" refers to feedback and advice that is customized based on each user's individual mental health status and characteristics.

[0571] "Dialogue-based advice" is advice provided through an interactive exchange with the user, often in a conversational format and involving a question-and-answer process.

[0572] "Monitoring" is a means of continuously tracking a user's status and data and responding if anything deviates from the normal range.

[0573] "Facial expression data" refers to data relating to the user's emotional or mood state, which can be obtained from facial expressions, such as smiles, anger, sadness, etc.

[0574] "Voice data" refers to data relating to the emotions and mental state of a user that can be obtained from the tone, pitch, speed, strength, etc. of the voice uttered by the user.

[0575] "Analysis" is the process of evaluating collected data using statistical models and machine learning algorithms to derive meaningful information.

[0576] The present invention provides a system for providing a detailed assessment of a user's mental health status and providing personalized advice. The system collects data from a device worn by the user and analyzes the data to assess the user's health status. Specific embodiments for implementing the present invention will be described below.

[0577] First, the user wears a device such as a smartwatch or smartphone. The smartwatch collects physiological data such as heart rate, blood pressure, body temperature, and sleep patterns, as well as behavioral data such as activity levels, on a daily basis. The smartphone also collects the user's emotional state using facial and voice recognition technologies.

[0578] The collected data is transferred from the device (smartwatch) to a smartphone via wireless communication (e.g., Bluetooth), where it is encrypted and securely transmitted to a server via the Internet.

[0579] The server cleans the received data, removes outliers, and standardizes it. It then analyzes the data using statistical models and machine learning algorithms. This analysis assesses the user's mental health based on heart rate variability and sleep patterns. It also includes an emotion engine that analyzes facial expressions and voice data, allowing it to assess the user's emotional state.

[0580] For example, if the user's heart rate is higher than normal and the tone of their voice is depressed, the server can assess that the user is feeling stressed.

[0581] The server then uses a large-scale language model (LLM) to generate personalized advice that provides feedback and advice tailored to the user's condition. The generated advice is then provided to the user through a smartphone app. The app interactively presents questions to the user and determines the next action based on the user's answers.

[0582] Examples of specific prompts include the following:

[0583] "Evaluate whether the user is experiencing stress based on recent heart rate and sleep pattern data."

[0584] "When a user asks about recent mood changes, generate a recommendation based on their answer, suggesting the next course of action."

[0585] Finally, the server continues to collect user data after the advice is implemented to continuously monitor the user's mental health, providing additional advice or warnings as needed to help the user receive effective mental health care.

[0586] This system allows users to manage their own mental health 24 hours a day and receive timely and accurate feedback. It also makes up for the shortage of medical resources and contributes to improving the mental health of society as a whole.

[0587] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0588] Step 1: Collect user data

[0589] A user puts on a smartwatch. The smartwatch automatically collects physiological and behavioral data, such as heart rate, sleep patterns, and activity levels. For example, the smartwatch starts measuring heart rate the moment the user wakes up in the morning and puts it on. The input data is about the user's physiological state and behavior, and the output is vital data stored on the device.

[0590] Step 2: Transferring data

[0591] The device (smartwatch) transmits collected vital data and behavioral pattern data to a smartphone in real time using wireless communication (such as Bluetooth). For example, after a user finishes jogging, the device automatically transmits heart rate and calorie consumption data to the smartphone. The input data is the vital data stored in the smartwatch, and the output is the data transferred to the smartphone.

[0592] Step 3: Sending data

[0593] The device (smartphone) periodically sends the received data to a server. The data is encrypted and sent securely over the Internet without delay. The input data is vital and behavioral data stored on the smartphone, and the output is encrypted data sent to the server.

[0594] Step 4: Process the data

[0595] The data received by the server is first cleaned to remove outliers and incomplete data. Then, a standardization process is performed to convert the data into a format that is easier to analyze. The input data is the encrypted data sent to the server, and the output is the cleaned and standardized data. Specifically, heart rate data from people who are active late at night is removed as an outlier, and the remaining data is standardized.

[0596] Step 5: Mental health assessment

[0597] The server evaluates the user's mental health based on the analyzed data. This evaluation is performed using statistical models and machine learning algorithms. The input data is cleaned and standardized data, and the output is the user's mental health assessment result. Specifically, if a high heart rate and lack of sleep are detected, the server evaluates the user as being in a stressed state.

[0598] Step 6: Collect and analyze emotion data

[0599] The device (smartphone) collects the user's facial expressions and voice and analyzes them through an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects changes in emotion from the tone and speed of voice. The input data is facial expression data and voice data, and the output is emotional data analyzed in real time.

[0600] Step 7: Sending Emotion Data

[0601] The device (smartphone) sends the collected emotional data to a server, which then integrates this data with other vital data. The input data is emotional data analyzed in real time, and the output is the emotional data sent to the server.

[0602] Step 8: Detailed Mental Health Assessment

[0603] The server integrates the emotional data and vital data to provide a more detailed assessment of the user's mental health. The input data is the integrated emotional and vital data, and the output is a detailed mental health assessment result. Specifically, if the heart rate is high and the voice tone is depressed, the server assesses that the user is likely to be depressed.

[0604] Step 9: Creating counseling content

[0605] The server generates personalized advice based on the user's mental health assessment using a large-scale language model (LLM). The input data is the detailed mental health assessment results, and the output is customized advice. For example, specific advice such as "Try deep breathing and relaxing music" as relaxation techniques to reduce stress is generated.

[0606] Step 10: Conducting counseling

[0607] When a user opens the app on their smartphone, the device connects them to an AI counselor. The AI ​​counselor presents questions to the user in a dialogue format and determines the next action based on the user's answers. The input data is customized advice, and the output is consultation and feedback provided to the user. Specifically, if the user answers "I haven't been able to sleep lately," the AI ​​counselor will present the next question: "Is that something you're worried about?"

[0608] Step 11: Continuous monitoring and feedback

[0609] The server continues to collect data on the user and continuously monitors their mental health. It provides additional counseling or warnings as needed. The input data is continuously collected vital and emotional data, and the output is additional advice or warnings. Specifically, if the user's heart rate again shows abnormal values, another counseling notification is sent.

[0610] (Application example 2)

[0611] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0612] Currently, many people need mental health support, but it is difficult to receive professional counseling. Furthermore, there is a lack of systems that can detect mental health problems such as stress and anxiety early and implement appropriate measures. In particular, there is a need for systems that provide real-time mental health care in daily life and provide appropriate content for relaxation and learning. A system that analyzes a user's emotional state and provides personalized counseling and content tailored to that state would be extremely useful in improving mental health, but such systems have not yet been fully implemented.

[0613] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0614] In this invention, the server includes means for collecting vital data and behavioral pattern data from a user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, and means for analyzing the user's emotional state and recommending mental health care content based on the emotional data. This allows the user to receive mental health care while being provided with personalized content such as relaxing music, meditation guides, stretching videos, and learning content in real time, tailored to their mental health state.

[0615] "Vital data" refers to physiological data such as a user's heart rate, sleep patterns, and activity level.

[0616] "Behavioral pattern data" refers to data related to the user's behavior and activities in their daily lives.

[0617] "Emotional data" refers to data relating to the emotional state of a user that is analyzed from their facial expressions and voice.

[0618] "Analysis" refers to the process of evaluating collected data using statistical models and machine learning algorithms to derive results.

[0619] "Mental health status" refers to the psychological and emotional well-being of a user.

[0620] "Personalized counseling content" refers to counseling advice and feedback that is optimized based on the individual user's mental health status.

[0621] "Dialogue-based counseling" refers to interactive counseling conducted between the user and the AI ​​counselor through questions and answers.

[0622] "Monitoring" refers to the process of continuously watching user data to detect fluctuations and anomalies.

[0623] "Content" refers to relaxing music, meditation guides, stretching videos, learning content, etc. provided to support users' mental health care.

[0624] "Recommendation method" refers to the process of selecting and providing optimal content to the user based on the user's emotional state and vital data.

[0625] This invention is a comprehensive AI counselor system to support users' mental health care. It collects and analyzes vital data, behavioral pattern data, and emotional data, and provides optimal counseling and content based on the results.

[0626] This system consists of three main components: a server, a terminal (such as a smartphone or smartwatch), and a user.

[0627] First, the user wears a smartwatch and collects vital data such as heart rate, sleep patterns, and activity levels during daily activities. The device then transfers this collected data in real time to a smartphone, which then transmits the data to a server.

[0628] The server receives the data via a secure internet connection, first cleaning it to remove outliers and incomplete data, then standardizing and converting it into an easy-to-analyze format, and using statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other data to assess their mental health.

[0629] In addition, the user's smartphone collects facial expressions and voice data and analyzes the emotional data using an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects emotional changes from the tone and speed of the voice. This emotional data is also sent to a server and integrated with other vital data and behavioral pattern data.

[0630] The server uses this integrated data to perform a detailed assessment of the user's mental health status, and based on the assessment results, generates personalized counseling content and optimal content (relaxing music, meditation guides, stretching videos, learning content, etc.). The generated content is delivered to the user's smartphone, allowing the user to receive interactive counseling or view recommended content.

[0631] Here's a specific example: If a user feels like they want to relax, their heart rate will rise and their tone of voice will indicate they are feeling stressed. In this case, the system will provide relaxing music and deep breathing guidance. For example, the system might say, "Your heart rate has been high for some time. We recommend some relaxing music (classical, nature sounds, etc.)."

[0632] In this way, this system is a powerful tool for supporting users' mental health care and improving the quality of their daily lives. Users can always receive the optimal support for their condition in real time.

[0633] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0634] Step 1:

[0635] The user wears a smartwatch to collect vital data such as heart rate, sleep patterns, and activity level. The input is the user's physiological information, and the output is vital data. This data is recorded in real time by the smartwatch.

[0636] Step 2:

[0637] The terminal (smartwatch) transfers the vital data collected to the smartphone. The input is the vital data collected by the smartwatch, and the output is the data transferred to the smartphone. The data is transmitted in real time via wireless communication.

[0638] Step 3:

[0639] The data received by the device (smartphone) is periodically sent to the server. The input is the vital data transferred to the smartphone, and the output is the data sent to the server. The data is encrypted and sent without delay over the Internet.

[0640] Step 4:

[0641] The server cleans the data it receives, removing outliers and incomplete data. The input is the vital data sent to the server, and the output is the cleaned data. At this stage, the data is standardized and converted into a format that is easy to analyze.

[0642] Step 5:

[0643] The server uses statistical models and machine learning algorithms to analyze the user's heart rate fluctuations and sleep patterns. The input is cleaned vital data, and the output is the analysis results (the user's mental health status). The data analysis evaluates whether the user is feeling stressed.

[0644] Step 6:

[0645] The device (smartphone) collects the user's facial expressions and voice and analyzes them using an emotion engine. The input is the user's facial expression image and voice clip, and the output is the analyzed emotion data. Emotions such as sadness, anger, and joy are recognized from facial expressions, and emotional changes are recognized in real time from the tone and speed of voice.

[0646] Step 7:

[0647] The emotional data collected by the device is sent to a server and integrated with other vital data and behavioral pattern data. The input is the analyzed emotional data, and the output is an integrated dataset. Based on the integrated data, a more detailed mental health status is assessed.

[0648] Step 8:

[0649] The server generates personalized counseling and content for the user's mental health care based on the evaluation results. The input is the integrated dataset, and the output is the generated counseling and recommended content. Specifically, it uses a large-scale language model (LLM) to create feedback and advice, and recommends relaxing music, meditation guides, stretching videos, learning content, and other items that are optimal for the user's current state.

[0650] Step 9:

[0651] When a user opens a smartphone app to receive counseling, the device connects the user with an AI counselor. The input is the user's counseling request, and the output is an interactive counseling session. The AI ​​counselor on the server presents questions to the user and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?"

[0652] Step 10:

[0653] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. The input is continuously collected vital and emotional data, and the output is an updated mental health assessment. If necessary, the server provides additional counseling or warnings. Specifically, if an abnormality such as a recurring high heart rate is detected, the server sends another counseling notification.

[0654] 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.

[0655] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0656] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0657] [Third embodiment]

[0658] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0659] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0660] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0661] 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.

[0662] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0663] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0664] 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.

[0665] 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.

[0666] 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 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.

[0667] 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.

[0668] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0669] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0670] This invention is an AI counselor system to support users' mental health care. The system collects data from users via devices such as smartphones and smartwatches, analyzes and evaluates that data, and provides personalized counseling.

[0671] Specifically, the server, the terminal, or the user operates as follows.

[0672] First, a user uses a smartphone or smartwatch to carry out daily activities. For example, the smartwatch collects sleep data while the user is sleeping, and records heart rate and activity level while exercising. In this way, vital data and behavioral pattern data are collected.

[0673] The device then sends the collected data to a server, which transfers it over the internet and analyzes it.

[0674] The server first cleans the received data to remove outliers and incomplete data. Next, it standardizes the data and converts it into a format that is easy to analyze. It then uses statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other factors. Based on the results of this analysis, the server evaluates the user's mental health status. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0675] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0676] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0677] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0678] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0679] The processing flow will be explained below.

[0680] Step 1:

[0681] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0682] Step 2:

[0683] The device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[0684] Step 3:

[0685] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[0686] Step 4:

[0687] The server cleans the data it receives, removing outliers and incomplete data, during which the data is checked for integrity and converted into a format suitable for analysis.

[0688] Step 5:

[0689] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to assess the user's heart rate variability, sleep patterns, and more.

[0690] Step 6:

[0691] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, it will determine that the user is feeling stressed.

[0692] Step 7:

[0693] The server generates personalized counseling content for the user based on the evaluation results, using a large-scale language model (LLM) to create advice and feedback that is appropriate for the user.

[0694] Step 8:

[0695] The user opens a counseling app on their smartphone and is connected to an AI counselor through the app.

[0696] Step 9:

[0697] The AI ​​counselor on the server conducts counseling by presenting questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[0698] Step 10:

[0699] The user answers the AI ​​counselor's questions, which allows the AI ​​counselor to understand the user's condition and the problems they are experiencing.

[0700] Step 11:

[0701] The server analyzes the user's answers and determines the next question and specific advice. For example, it might suggest, "Deep breathing has a relaxing effect. Please try it."

[0702] Step 12:

[0703] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor their mental health, providing additional counseling or warnings as needed to support ongoing care.

[0704] Example 1

[0705] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0706] Mental health problems such as stress and anxiety are on the rise in modern society, creating a need for rapid and accurate responses. However, traditional mental health care relies mainly on face-to-face counseling by experts, which poses challenges such as time and location constraints and a shortage of experts. Furthermore, a lack of a personalized approach for individual users makes effective care difficult. Given these circumstances, there is a need for a system that can monitor users' mental health status in real time and respond quickly.

[0707] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0708] In this invention, the server includes means for collecting physiological data and behavioral pattern data from a user, means for transmitting the collected data to the server via a network, means for cleaning and standardizing the received data, means for analyzing the cleaned data and evaluating the user's psychological health state, means for generating personalized counseling content based on the evaluation results, means for providing feedback and advice to the user using a generative AI model, means for conducting counseling with the user in an interactive format, and means for continuously monitoring the user's data even after counseling. This makes it possible to monitor the user's mental health state in real time and provide prompt and personalized counseling.

[0709] "User" refers to an individual who provides physiological data and behavioral pattern data and uses the system.

[0710] "Physiological data" refers to data relating to a user's physical condition, such as heart rate, sleep data, body temperature, blood pressure, etc.

[0711] "Behavior pattern data" refers to data related to the user's behavior, such as the number of steps taken, amount of exercise, and duration of activity.

[0712] "Terminal" refers to a device, such as a smartphone or smartwatch, that a user uses to collect physiological data and behavioral pattern data.

[0713] "Server" refers to a computer system that receives, cleans, standardizes, and analyzes data sent by users and generates counseling content.

[0714] "Cleaning" refers to the process of removing outliers and incomplete information from collected data and preparing the data so that accurate analysis can be performed.

[0715] "Standardization" refers to the process of unifying the format of data collected from different devices and sensors, making it easier to analyze.

[0716] "Analysis" refers to the process of using cleaned and standardized data to assess a user's psychological well-being using statistical models and machine learning algorithms.

[0717] A "generative AI model" refers to an algorithm that uses a large-scale language model to generate feedback and advice tailored to the user's condition.

[0718] "Counseling content" refers to information including feedback and advice generated based on the analysis results.

[0719] "Dialogue-based counseling" refers to an interactive counseling process, such as a question-and-answer format, conducted between the user and the AI ​​counselor.

[0720] "Monitoring" refers to the process of continuing to collect and analyze user data and monitor their mental health status even after counseling.

[0721] This invention is an AI counselor system to support users' mental health care. The system collects physiological data and behavioral pattern data using devices such as smartphones and smartwatches, analyzes and evaluates the data, and provides personalized counseling.

[0722] Data collection

[0723] Users use smartphones or smartwatches to collect daily activity data, including physiological data such as heart rate, sleep data, and activity level, as well as behavioral pattern data. For example, when a user goes running, the smartwatch records their heart rate and distance, and automatically collects sleep data at night.

[0724] Data transmission

[0725] The device sends the collected data to a server over the Internet, specifically, the user's smartphone uploads the data to the server via Wi-Fi or mobile data network.

[0726] Data Cleaning and Standardization

[0727] The server cleans the data it receives, removing outliers and incomplete data, then standardizes it and converts it into a format that's easier to analyze, for example by standardizing the timestamp format and scaling it so that data from different devices can be handled at the same scale.

[0728] Data analysis

[0729] The server analyzes the cleaned and standardized data using statistical models and machine learning algorithms. Specifically, it uses programming languages ​​such as Python to run machine learning algorithms (e.g., random forests) to assess the user's psychological well-being. This analysis allows it to understand the user's stress level and mental health status from heart rate variability and sleep patterns.

[0730] Counseling content generation

[0731] The server uses a generative AI model (large-scale language model) to generate personalized counseling content based on the evaluation results. For example, if the user is evaluated as feeling stressed, the server generates feedback and advice suggesting ways to relax. Specific examples of prompts for the generative AI model are as follows:

[0732] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[0733] Providing counseling

[0734] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will present the next question, "Is that something you're worried about?"

[0735] Follow-up and monitoring

[0736] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, the server can send another counseling notification.

[0737] This system allows users to receive counseling 24 hours a day even if they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, thereby contributing to improving labor productivity in society.

[0738] As described above, the present invention provides specific means for realizing more efficient and effective mental health care for users.

[0739] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0740] Step 1:

[0741] A user uses a smartphone or smartwatch to collect physiological data and behavioral pattern data. Specifically, the user wears the smartwatch and goes about their daily activities. During this time, their heart rate, sleep data, and activity level are recorded. Input data includes a heart rate log, sleep log, and exercise log, which are raw data obtained from the smartwatch. The output is the collected physiological data and behavioral pattern data.

[0742] Step 2:

[0743] The device sends the collected data to the server. Specifically, the user's smartphone uses Wi-Fi or mobile data network to obtain data from the smartwatch and uploads it to the server. The input is the data obtained from the smartwatch, and the output is the data sent to the server.

[0744] Step 3:

[0745] The server cleans the received data. Specifically, the server removes outliers and incomplete data from the received data. The input is the raw data sent from the device, and the output is the cleaned data. For example, outliers such as a heart rate of 0 or an extremely high heart rate are filtered out.

[0746] Step 4:

[0747] The server standardizes the cleaned data. Specifically, it standardizes the data format so that data from different devices can be analyzed at the same scale. The input is cleaned data, and the output is standardized data. For example, it standardizes the timestamp format from different devices.

[0748] Step 5:

[0749] The server analyzes the standardized data. Specifically, it uses a machine learning algorithm to assess the user's psychological health. This algorithm uses a programming language such as Python. The input is the standardized data, and the output is a psychological health assessment as an analysis result. For example, a random forest algorithm is used to assess the user's stress level based on sleep patterns and heart rate fluctuations.

[0750] Step 6:

[0751] The server generates counseling content based on the analysis results. Specifically, it uses a large-scale language model (LLM) to generate feedback and advice appropriate for the user. The input is the analysis results, and the output is the generated counseling content. For example, if the user is feeling stressed, it generates content suggesting ways to relax. An example of a prompt sentence for the generative AI model is as follows:

[0752] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[0753] Step 7:

[0754] The device provides counseling. Specifically, when a user opens the app on their smartphone, the device connects the user to an AI counselor on the server. The input is the generated counseling content, and the output is feedback and advice provided to the user. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will pose the next question, "Is that something you're worried about?"

[0755] Step 8:

[0756] The server continues to monitor the user's data. Specifically, it collects data even after the counseling session ends and monitors the user's mental health status based on the new data. The input is the continuously collected data, and the output is an updated mental health assessment and, if necessary, a re-counseling notification. For example, if an abnormality such as a re-elevated heart rate is detected, the server will send another counseling notification.

[0757] (Application example 1)

[0758] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0759] Conventional mental healthcare systems assess a user's mental health status and provide counseling based on the collection and analysis of their physiological and behavioral pattern data. However, no systems have taken into account the impact of a user's psychological state on purchasing behavior. This has made it difficult to improve the customer experience in virtual stores. Therefore, there has been a need for a system that can link a user's mental health status with their purchasing behavior and make appropriate product recommendations.

[0760] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0761] In this invention, the server includes means for collecting vital data and behavioral pattern data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, means for collecting and analyzing user purchasing behavior data, and means for generating product proposals that link the user's psychological state with their purchasing behavior, thereby enabling personalized product proposals that take the user's psychological state into consideration.

[0762] "User" means an individual or group of people who use the system.

[0763] "Vital data" refers to physiological data including biosignals such as heart rate, blood pressure, and body temperature.

[0764] "Behavior pattern data" refers to data relating to the user's daily activities, sleep data, amount of exercise, and other behavioral data.

[0765] "Analysis" means evaluating collected data using statistical methods and machine learning algorithms.

[0766] "Mental health status" refers to a user's mental health and psychological balance.

[0767] "Counseling" means the process of providing advice and feedback to support a user's mental health.

[0768] "Continuous monitoring" means collecting data about a user over a long period of time and monitoring their condition.

[0769] "Purchasing behavior data" refers to behavioral data related to purchasing, such as a user's shopping history and product browsing history.

[0770] "Product suggestion" means analyzing the user's psychological state and purchasing behavior to recommend appropriate products.

[0771] This invention relates to a system for supporting users' mental health care and improving customer experience in virtual stores. This system collects vital data and behavioral pattern data from users, analyzes them, and evaluates the user's mental health state. It then generates personalized counseling content based on the collected data and provides counseling in an interactive format. It also collects data on the user's purchasing behavior and has the function of suggesting products linked to the user's psychological state.

[0772] 1. Program Generation

[0773] The program of this system is configured as follows:

[0774] 2. Explain the program's processing in natural language

[0775] When users use their smartphones or smartwatches to carry out activities, these devices collect vital data such as heart rate and sleep data. When users shop in virtual stores, purchasing behavior data is also collected. This data is sent to a server via the Internet.

[0776] The server cleans and standardizes the collected data, removing outliers and incomplete data. It then analyzes the data using statistical models and machine learning algorithms (e.g., scikit-learn) to assess the user's mental health status. Based on the assessment results, the server generates personalized counseling content. It uses large-scale language models (LLMs) to provide feedback and advice tailored to the user's condition.

[0777] 3. Add specific examples to the description

[0778] For example, suppose a user is enjoying a long shopping session in a virtual store. The smartwatch collects the user's heart rate and sleep data, which are then analyzed by the server. The results show that the user's heart rate is higher than usual and that they have not been getting enough sleep recently. Based on this assessment, the server generates advice such as "Try some light exercise to relax."

[0779] Furthermore, by analyzing user purchasing behavior data, it is possible to recommend relaxation goods or massage equipment to users who are feeling stressed or tired, allowing users to receive product suggestions that take their psychological state into consideration.

[0780] Prompt Sentence Examples

[0781] Below is an example of a prompt sentence to input to a large-scale language model (LLM).

[0782] Create a program that predicts a user's stress level based on their heart rate and sleep data, and generates personalized counseling content.

[0783] Heart rate data: [75, 80, 72, 78, 77]

[0784] Sleep data: [6, 7, 5, 8, 6]

[0785] Stress Level: [3, 4, 2, 5, 3]

[0786] Current data to predict: Heart rate 79, sleep quality 6, stress level 4

[0787] Output: Personalized advice based on stress level

[0788] This system allows users to receive product suggestions that take their psychological state into account even in virtual stores, enabling them to enjoy a comfortable shopping experience.

[0789] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0790] Step 1:

[0791] Users use smartphones or smartwatches to collect vital data and behavioral pattern data.

[0792] How it works: The smartwatch records your heart rate and sleep data, and your smartphone receives this data via an app.

[0793] Input: Heart rate data, sleep data.

[0794] Output: Collected heart rate and sleep data.

[0795] Step 2:

[0796] The terminal transmits the collected data to the server.

[0797] Specific operation: The smartphone uploads the collected data to the server via the Internet.

[0798] Input: Collected heart rate and sleep data.

[0799] Output: Data transfer to the server.

[0800] Step 3:

[0801] The server cleans and standardizes the received data.

[0802] What it does: It uses data cleaning techniques to remove outliers and incomplete data, and standardization techniques to convert data into a consistent format.

[0803] Input: Collected heart rate and sleep data.

[0804] Output: Cleaned and standardized data.

[0805] Step 4:

[0806] The server analyzes the cleaned and standardized data to assess the user's mental health status.

[0807] What it does: Analyzes heart rate and sleep patterns using statistical models and machine learning algorithms (e.g., scikit-learn).

[0808] Input: Cleaned and standardized data.

[0809] Output: The user's mental health assessment results.

[0810] Step 5:

[0811] The server generates personalized counseling content based on the evaluation results.

[0812] Specific operation: Uses a large-scale language model (LLM) to create counseling content appropriate for the user's condition.

[0813] Input: User's mental health assessment results.

[0814] Output: Personalized counseling content.

[0815] Step 6:

[0816] The server conducts interactive counseling with the user.

[0817] Specific operation: Through a smartphone app, questions are presented to the user and the next action is determined based on the user's answer.

[0818] Input: personalized counseling content.

[0819] Output: Answers from the user and the interaction history.

[0820] Step 7:

[0821] The server continues to monitor the user's data even after the counseling session.

[0822] Specific operation: Continuously collects and analyzes data from smartwatches and smartphones.

[0823] Input: Data from smartwatch and smartphone.

[0824] Output: Continuously updated mental health assessment results for the user.

[0825] Step 8:

[0826] The server also collects and analyzes user purchasing behavior data.

[0827] Specific operations: Record and analyze shopping history and product browsing history in virtual stores.

[0828] Input: Purchasing behavior data.

[0829] Output: Parsed purchasing behavior data.

[0830] Step 9:

[0831] The server generates product proposals that link the user's psychological state with their purchasing behavior.

[0832] Specific operation: Based on the user's mental health assessment results and purchasing behavior data, product suggestions are created using a large-scale language model (LLM).

[0833] Input: User's mental health assessment results and purchasing behavior data.

[0834] Output: Personalized product suggestions.

[0835] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0836] This invention is an AI counselor system for supporting users' mental health care, and combines an emotion engine that recognizes the user's emotional state. The system aims to collect data from users via devices such as smartphones and smartwatches, analyze and evaluate that data, and provide personalized counseling.

[0837] Specifically, the server, the terminal, or the user operates as follows.

[0838] First, the user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily life.

[0839] Next, the device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[0840] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[0841] The data received by the server is first cleaned to remove outliers and incomplete data. Next, the data is standardized and converted into a format that is easy to analyze. Statistical models and machine learning algorithms are then used to analyze the user's heart rate fluctuations, sleep patterns, and other factors. Based on the results of this analysis, the user's mental health status is assessed. For example, if the heart rate is higher than normal and the user is not getting enough sleep, the server will assess that the user is feeling stressed.

[0842] Furthermore, this invention uses an emotion engine. The device (smartphone) collects the user's facial expressions and voice and analyzes them through the emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time. Voice analysis detects changes in emotion from the tone and speed of the user's voice. This emotion data is also sent to the server and integrated with other vital data and behavioral pattern data.

[0843] The server can then factor in emotional data to further assess the user's mental health. For example, if the user's heart rate is high and their voice tone is depressed, the server may assess that the user is likely depressed.

[0844] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0845] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0846] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0847] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0848] The processing flow will be explained below.

[0849] Step 1:

[0850] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0851] Step 2:

[0852] The vital data and behavioral pattern data collected by the device (smartwatch) are transferred to a smartphone in real time via wireless communication.

[0853] Step 3:

[0854] The device (smartphone) periodically sends the received data to the server. The data is encrypted and sent over the Internet.

[0855] Step 4:

[0856] The server cleans the incoming data, removing outliers and incomplete data, checks the data for integrity, and converts it into a format suitable for analysis.

[0857] Step 5:

[0858] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to analyze the user's heart rate variability and sleep patterns.

[0859] Step 6:

[0860] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0861] Step 7:

[0862] The device (smartphone) collects the user's facial expressions and voice data, and the collected emotion data is sent to the emotion engine.

[0863] Step 8:

[0864] The emotion engine on the server analyzes the user's facial expressions and evaluates emotions such as joy, sadness, anger, etc. in real time. It also analyzes voice data and recognizes the user's emotional state from the tone and speed of the voice.

[0865] Step 9:

[0866] The server then combines the emotion data with other vital and behavioral data to provide a more detailed assessment of the user's mental health. For example, if the facial expression indicates sadness and the voice is depressed, it may determine that the user is likely depressed.

[0867] Step 10:

[0868] The server generates personalized counseling content based on the evaluation results, using a large-scale language model (LLM) to generate advice and feedback tailored to the user's condition.

[0869] Step 11:

[0870] When a user opens a counseling app on their smartphone, they are connected to an AI counselor through the app.

[0871] Step 12:

[0872] The AI ​​counselor on the server presents questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[0873] Step 13:

[0874] The user answers the questions of the AI ​​counselor. The answers are sent to the server, and the AI ​​counselor decides the next question or advice.

[0875] Step 14:

[0876] The server analyzes the user's answers and provides next steps and specific advice, such as "Try taking deep breaths, they'll help you relax."

[0877] Step 15:

[0878] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor the user's mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, another counseling notification can be sent.

[0879] Example 2

[0880] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0881] Conventional mental healthcare systems have limitations in assessing a user's emotional state based solely on physiological and behavioral data. It is difficult to grasp the user's emotional state in detail. In particular, because fluctuations in mental health are also reflected in facial expressions and voice, assessments that do not take these data into account are insufficient, resulting in a problem of reduced accuracy in personalized advice.

[0882] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting physiological data and behavioral data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized advice content based on the evaluation results, means for providing advice to the user in an interactive format, means for continuously monitoring the user's data even after the advice is provided, means for collecting the user's facial expression data and voice data and analyzing the emotional state, and means for evaluating the user's mental health state in detail based on the analysis results. This makes it possible to evaluate the user's mental health state in detail based on the user's facial expression and voice data in addition to the user's physiological data, thereby enabling the generation and provision of highly accurate personalized advice content.

[0883] "Physiological data" refers to data relating to the internal state of the user's body, such as heart rate, blood pressure, body temperature, and breathing patterns.

[0884] "Behavioral data" refers to data such as the user's movements and activity levels in daily life, sleep patterns, and exercise levels.

[0885] "Mental health status" refers to a state related to mental health, such as a user's stress level, emotional state, psychological stability, and mood.

[0886] "Personalized advice" refers to feedback and advice that is customized based on each user's individual mental health status and characteristics.

[0887] "Dialogue-based advice" is advice provided through an interactive exchange with the user, often in a conversational format and involving a question-and-answer process.

[0888] "Monitoring" is a means of continuously tracking a user's status and data and responding if anything deviates from the normal range.

[0889] "Facial expression data" refers to data relating to the user's emotional or mood state, which can be obtained from facial expressions, such as smiles, anger, sadness, etc.

[0890] "Voice data" refers to data relating to the emotions and mental state of a user that can be obtained from the tone, pitch, speed, strength, etc. of the voice uttered by the user.

[0891] "Analysis" is the process of evaluating collected data using statistical models and machine learning algorithms to derive meaningful information.

[0892] The present invention provides a system for providing a detailed assessment of a user's mental health status and providing personalized advice. The system collects data from a device worn by the user and analyzes the data to assess the user's health status. Specific embodiments for implementing the present invention will be described below.

[0893] First, the user wears a device such as a smartwatch or smartphone. The smartwatch collects physiological data such as heart rate, blood pressure, body temperature, and sleep patterns, as well as behavioral data such as activity levels, on a daily basis. The smartphone also collects the user's emotional state using facial and voice recognition technologies.

[0894] The collected data is transferred from the device (smartwatch) to a smartphone via wireless communication (e.g., Bluetooth), where it is encrypted and securely transmitted to a server via the Internet.

[0895] The server cleans the received data, removes outliers, and standardizes it. It then analyzes the data using statistical models and machine learning algorithms. This analysis assesses the user's mental health based on heart rate variability and sleep patterns. It also includes an emotion engine that analyzes facial expressions and voice data, allowing it to assess the user's emotional state.

[0896] For example, if the user's heart rate is higher than normal and the tone of their voice is depressed, the server can assess that the user is feeling stressed.

[0897] The server then uses a large-scale language model (LLM) to generate personalized advice that provides feedback and advice tailored to the user's condition. The generated advice is then provided to the user through a smartphone app. The app interactively presents questions to the user and determines the next action based on the user's answers.

[0898] Examples of specific prompts include the following:

[0899] "Evaluate whether the user is experiencing stress based on recent heart rate and sleep pattern data."

[0900] "When a user asks about recent mood changes, generate a recommendation based on their answer, suggesting the next course of action."

[0901] Finally, the server continues to collect user data after the advice is implemented to continuously monitor the user's mental health, providing additional advice or warnings as needed to help the user receive effective mental health care.

[0902] This system allows users to manage their own mental health 24 hours a day and receive timely and accurate feedback. It also makes up for the shortage of medical resources and contributes to improving the mental health of society as a whole.

[0903] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0904] Step 1: Collect user data

[0905] A user puts on a smartwatch. The smartwatch automatically collects physiological and behavioral data, such as heart rate, sleep patterns, and activity levels. For example, the smartwatch starts measuring heart rate the moment the user wakes up in the morning and puts it on. The input data is about the user's physiological state and behavior, and the output is vital data stored on the device.

[0906] Step 2: Transferring data

[0907] The device (smartwatch) transmits collected vital data and behavioral pattern data to a smartphone in real time using wireless communication (such as Bluetooth). For example, after a user finishes jogging, the device automatically transmits heart rate and calorie consumption data to the smartphone. The input data is the vital data stored in the smartwatch, and the output is the data transferred to the smartphone.

[0908] Step 3: Sending data

[0909] The device (smartphone) periodically sends the received data to a server. The data is encrypted and sent securely over the Internet without delay. The input data is vital and behavioral data stored on the smartphone, and the output is encrypted data sent to the server.

[0910] Step 4: Process the data

[0911] The data received by the server is first cleaned to remove outliers and incomplete data. Then, a standardization process is performed to convert the data into a format that is easier to analyze. The input data is the encrypted data sent to the server, and the output is the cleaned and standardized data. Specifically, heart rate data from people who are active late at night is removed as an outlier, and the remaining data is standardized.

[0912] Step 5: Mental health assessment

[0913] The server evaluates the user's mental health based on the analyzed data. This evaluation is performed using statistical models and machine learning algorithms. The input data is cleaned and standardized data, and the output is the user's mental health assessment result. Specifically, if a high heart rate and lack of sleep are detected, the server evaluates the user as being in a stressed state.

[0914] Step 6: Collect and analyze emotion data

[0915] The device (smartphone) collects the user's facial expressions and voice and analyzes them through an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects changes in emotion from the tone and speed of voice. The input data is facial expression data and voice data, and the output is emotional data analyzed in real time.

[0916] Step 7: Sending Emotion Data

[0917] The device (smartphone) sends the collected emotional data to a server, which then integrates this data with other vital data. The input data is emotional data analyzed in real time, and the output is the emotional data sent to the server.

[0918] Step 8: Detailed Mental Health Assessment

[0919] The server integrates the emotional data and vital data to provide a more detailed assessment of the user's mental health. The input data is the integrated emotional and vital data, and the output is a detailed mental health assessment result. Specifically, if the heart rate is high and the voice tone is depressed, the server assesses that the user is likely to be depressed.

[0920] Step 9: Creating counseling content

[0921] The server generates personalized advice based on the user's mental health assessment using a large-scale language model (LLM). The input data is the detailed mental health assessment results, and the output is customized advice. For example, specific advice such as "Try deep breathing and relaxing music" as relaxation techniques to reduce stress is generated.

[0922] Step 10: Conducting counseling

[0923] When a user opens the app on their smartphone, the device connects them to an AI counselor. The AI ​​counselor presents questions to the user in a dialogue format and determines the next action based on the user's answers. The input data is customized advice, and the output is consultation and feedback provided to the user. Specifically, if the user answers "I haven't been able to sleep lately," the AI ​​counselor will present the next question: "Is that something you're worried about?"

[0924] Step 11: Continuous monitoring and feedback

[0925] The server continues to collect data on the user and continuously monitors their mental health. It provides additional counseling or warnings as needed. The input data is continuously collected vital and emotional data, and the output is additional advice or warnings. Specifically, if the user's heart rate again shows abnormal values, another counseling notification is sent.

[0926] (Application example 2)

[0927] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0928] Currently, many people need mental health support, but it is difficult to receive professional counseling. Furthermore, there is a lack of systems that can detect mental health problems such as stress and anxiety early and implement appropriate measures. In particular, there is a need for systems that provide real-time mental health care in daily life and provide appropriate content for relaxation and learning. A system that analyzes a user's emotional state and provides personalized counseling and content tailored to that state would be extremely useful in improving mental health, but such systems have not yet been fully implemented.

[0929] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0930] In this invention, the server includes means for collecting vital data and behavioral pattern data from a user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, and means for analyzing the user's emotional state and recommending mental health care content based on the emotional data. This allows the user to receive mental health care while being provided with personalized content such as relaxing music, meditation guides, stretching videos, and learning content in real time, tailored to their mental health state.

[0931] "Vital data" refers to physiological data such as a user's heart rate, sleep patterns, and activity level.

[0932] "Behavioral pattern data" refers to data related to the user's behavior and activities in their daily lives.

[0933] "Emotional data" refers to data relating to the emotional state of a user that is analyzed from their facial expressions and voice.

[0934] "Analysis" refers to the process of evaluating collected data using statistical models and machine learning algorithms to derive results.

[0935] "Mental health status" refers to the psychological and emotional well-being of a user.

[0936] "Personalized counseling content" refers to counseling advice and feedback that is optimized based on the individual user's mental health status.

[0937] "Dialogue-based counseling" refers to interactive counseling conducted between the user and the AI ​​counselor through questions and answers.

[0938] "Monitoring" refers to the process of continuously watching user data to detect fluctuations and anomalies.

[0939] "Content" refers to relaxing music, meditation guides, stretching videos, learning content, etc. provided to support users' mental health care.

[0940] "Recommendation method" refers to the process of selecting and providing optimal content to the user based on the user's emotional state and vital data.

[0941] This invention is a comprehensive AI counselor system to support users' mental health care. It collects and analyzes vital data, behavioral pattern data, and emotional data, and provides optimal counseling and content based on the results.

[0942] This system consists of three main components: a server, a terminal (such as a smartphone or smartwatch), and a user.

[0943] First, the user wears a smartwatch and collects vital data such as heart rate, sleep patterns, and activity levels during daily activities. The device then transfers this collected data in real time to a smartphone, which then transmits the data to a server.

[0944] The server receives the data via a secure internet connection, first cleaning it to remove outliers and incomplete data, then standardizing and converting it into an easy-to-analyze format, and using statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other data to assess their mental health.

[0945] In addition, the user's smartphone collects facial expressions and voice data and analyzes the emotional data using an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects emotional changes from the tone and speed of the voice. This emotional data is also sent to a server and integrated with other vital data and behavioral pattern data.

[0946] The server uses this integrated data to perform a detailed assessment of the user's mental health status, and based on the assessment results, generates personalized counseling content and optimal content (relaxing music, meditation guides, stretching videos, learning content, etc.). The generated content is delivered to the user's smartphone, allowing the user to receive interactive counseling or view recommended content.

[0947] Here's a specific example: If a user feels like they want to relax, their heart rate will rise and their tone of voice will indicate they are feeling stressed. In this case, the system will provide relaxing music and deep breathing guidance. For example, the system might say, "Your heart rate has been high for some time. We recommend some relaxing music (classical, nature sounds, etc.)."

[0948] In this way, this system is a powerful tool for supporting users' mental health care and improving the quality of their daily lives. Users can always receive the optimal support for their condition in real time.

[0949] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0950] Step 1:

[0951] The user wears a smartwatch to collect vital data such as heart rate, sleep patterns, and activity level. The input is the user's physiological information, and the output is vital data. This data is recorded in real time by the smartwatch.

[0952] Step 2:

[0953] The terminal (smartwatch) transfers the vital data collected to the smartphone. The input is the vital data collected by the smartwatch, and the output is the data transferred to the smartphone. The data is transmitted in real time via wireless communication.

[0954] Step 3:

[0955] The data received by the device (smartphone) is periodically sent to the server. The input is the vital data transferred to the smartphone, and the output is the data sent to the server. The data is encrypted and sent without delay over the Internet.

[0956] Step 4:

[0957] The server cleans the data it receives, removing outliers and incomplete data. The input is the vital data sent to the server, and the output is the cleaned data. At this stage, the data is standardized and converted into a format that is easy to analyze.

[0958] Step 5:

[0959] The server uses statistical models and machine learning algorithms to analyze the user's heart rate fluctuations and sleep patterns. The input is cleaned vital data, and the output is the analysis results (the user's mental health status). The data analysis evaluates whether the user is feeling stressed.

[0960] Step 6:

[0961] The device (smartphone) collects the user's facial expressions and voice and analyzes them using an emotion engine. The input is the user's facial expression image and voice clip, and the output is the analyzed emotion data. Emotions such as sadness, anger, and joy are recognized from facial expressions, and emotional changes are recognized in real time from the tone and speed of voice.

[0962] Step 7:

[0963] The emotional data collected by the device is sent to a server and integrated with other vital data and behavioral pattern data. The input is the analyzed emotional data, and the output is an integrated dataset. Based on the integrated data, a more detailed mental health status is assessed.

[0964] Step 8:

[0965] The server generates personalized counseling and content for the user's mental health care based on the evaluation results. The input is the integrated dataset, and the output is the generated counseling and recommended content. Specifically, it uses a large-scale language model (LLM) to create feedback and advice, and recommends relaxing music, meditation guides, stretching videos, learning content, and other items that are optimal for the user's current state.

[0966] Step 9:

[0967] When a user opens a smartphone app to receive counseling, the device connects the user with an AI counselor. The input is the user's counseling request, and the output is an interactive counseling session. The AI ​​counselor on the server presents questions to the user and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?"

[0968] Step 10:

[0969] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. The input is continuously collected vital and emotional data, and the output is an updated mental health assessment. If necessary, the server provides additional counseling or warnings. Specifically, if an abnormality such as a recurring high heart rate is detected, the server sends another counseling notification.

[0970] 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.

[0971] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0972] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0973] [Fourth embodiment]

[0974] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0975] 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.

[0976] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0977] 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.

[0978] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0979] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0980] 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.

[0981] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[0982] 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.

[0983] 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 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.

[0984] 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.

[0985] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0986] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0987] This invention is an AI counselor system to support users' mental health care. The system collects data from users via devices such as smartphones and smartwatches, analyzes and evaluates that data, and provides personalized counseling.

[0988] Specifically, the server, the terminal, or the user operates as follows.

[0989] First, a user uses a smartphone or smartwatch to carry out daily activities. For example, the smartwatch collects sleep data while the user is sleeping, and records heart rate and activity level while exercising. In this way, vital data and behavioral pattern data are collected.

[0990] The device then sends the collected data to a server, which transfers it over the internet and analyzes it.

[0991] The server first cleans the received data to remove outliers and incomplete data. Next, it standardizes the data and converts it into a format that is easy to analyze. It then uses statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other factors. Based on the results of this analysis, the server evaluates the user's mental health status. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[0992] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[0993] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[0994] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[0995] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[0996] The processing flow will be explained below.

[0997] Step 1:

[0998] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[0999] Step 2:

[1000] The device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[1001] Step 3:

[1002] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[1003] Step 4:

[1004] The server cleans the data it receives, removing outliers and incomplete data, during which the data is checked for integrity and converted into a format suitable for analysis.

[1005] Step 5:

[1006] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to assess the user's heart rate variability, sleep patterns, and more.

[1007] Step 6:

[1008] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, it will determine that the user is feeling stressed.

[1009] Step 7:

[1010] The server generates personalized counseling content for the user based on the evaluation results, using a large-scale language model (LLM) to create advice and feedback that is appropriate for the user.

[1011] Step 8:

[1012] The user opens a counseling app on their smartphone and is connected to an AI counselor through the app.

[1013] Step 9:

[1014] The AI ​​counselor on the server conducts counseling by presenting questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[1015] Step 10:

[1016] The user answers the AI ​​counselor's questions, which allows the AI ​​counselor to understand the user's condition and the problems they are experiencing.

[1017] Step 11:

[1018] The server analyzes the user's answers and determines the next question and specific advice. For example, it might suggest, "Deep breathing has a relaxing effect. Please try it."

[1019] Step 12:

[1020] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor their mental health, providing additional counseling or warnings as needed to support ongoing care.

[1021] Example 1

[1022] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1023] Mental health problems such as stress and anxiety are on the rise in modern society, creating a need for rapid and accurate responses. However, traditional mental health care relies mainly on face-to-face counseling by experts, which poses challenges such as time and location constraints and a shortage of experts. Furthermore, a lack of a personalized approach for individual users makes effective care difficult. Given these circumstances, there is a need for a system that can monitor users' mental health status in real time and respond quickly.

[1024] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1025] In this invention, the server includes means for collecting physiological data and behavioral pattern data from a user, means for transmitting the collected data to the server via a network, means for cleaning and standardizing the received data, means for analyzing the cleaned data and evaluating the user's psychological health state, means for generating personalized counseling content based on the evaluation results, means for providing feedback and advice to the user using a generative AI model, means for conducting counseling with the user in an interactive format, and means for continuously monitoring the user's data even after counseling. This makes it possible to monitor the user's mental health state in real time and provide prompt and personalized counseling.

[1026] "User" refers to an individual who provides physiological data and behavioral pattern data and uses the system.

[1027] "Physiological data" refers to data relating to a user's physical condition, such as heart rate, sleep data, body temperature, blood pressure, etc.

[1028] "Behavior pattern data" refers to data related to the user's behavior, such as the number of steps taken, amount of exercise, and duration of activity.

[1029] "Terminal" refers to a device, such as a smartphone or smartwatch, that a user uses to collect physiological data and behavioral pattern data.

[1030] "Server" refers to a computer system that receives, cleans, standardizes, and analyzes data sent by users and generates counseling content.

[1031] "Cleaning" refers to the process of removing outliers and incomplete information from collected data and preparing the data so that accurate analysis can be performed.

[1032] "Standardization" refers to the process of unifying the format of data collected from different devices and sensors, making it easier to analyze.

[1033] "Analysis" refers to the process of using cleaned and standardized data to assess a user's psychological well-being using statistical models and machine learning algorithms.

[1034] A "generative AI model" refers to an algorithm that uses a large-scale language model to generate feedback and advice tailored to the user's condition.

[1035] "Counseling content" refers to information including feedback and advice generated based on the analysis results.

[1036] "Dialogue-based counseling" refers to an interactive counseling process, such as a question-and-answer format, conducted between the user and the AI ​​counselor.

[1037] "Monitoring" refers to the process of continuing to collect and analyze user data and monitor their mental health status even after counseling.

[1038] This invention is an AI counselor system to support users' mental health care. The system collects physiological data and behavioral pattern data using devices such as smartphones and smartwatches, analyzes and evaluates the data, and provides personalized counseling.

[1039] Data collection

[1040] Users use smartphones or smartwatches to collect daily activity data, including physiological data such as heart rate, sleep data, and activity level, as well as behavioral pattern data. For example, when a user goes running, the smartwatch records their heart rate and distance, and automatically collects sleep data at night.

[1041] Data transmission

[1042] The device sends the collected data to a server over the Internet, specifically, the user's smartphone uploads the data to the server via Wi-Fi or mobile data network.

[1043] Data Cleaning and Standardization

[1044] The server cleans the data it receives, removing outliers and incomplete data, then standardizes it and converts it into a format that's easier to analyze, for example by standardizing the timestamp format and scaling it so that data from different devices can be handled at the same scale.

[1045] Data analysis

[1046] The server analyzes the cleaned and standardized data using statistical models and machine learning algorithms. Specifically, it uses programming languages ​​such as Python to run machine learning algorithms (e.g., random forests) to assess the user's psychological well-being. This analysis allows it to understand the user's stress level and mental health status from heart rate variability and sleep patterns.

[1047] Counseling content generation

[1048] The server uses a generative AI model (large-scale language model) to generate personalized counseling content based on the evaluation results. For example, if the user is evaluated as feeling stressed, the server generates feedback and advice suggesting ways to relax. Specific examples of prompts for the generative AI model are as follows:

[1049] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[1050] Providing counseling

[1051] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will present the next question, "Is that something you're worried about?"

[1052] Follow-up and monitoring

[1053] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, the server can send another counseling notification.

[1054] This system allows users to receive counseling 24 hours a day even if they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, thereby contributing to improving labor productivity in society.

[1055] As described above, the present invention provides specific means for realizing more efficient and effective mental health care for users.

[1056] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1057] Step 1:

[1058] A user uses a smartphone or smartwatch to collect physiological data and behavioral pattern data. Specifically, the user wears the smartwatch and goes about their daily activities. During this time, their heart rate, sleep data, and activity level are recorded. Input data includes a heart rate log, sleep log, and exercise log, which are raw data obtained from the smartwatch. The output is the collected physiological data and behavioral pattern data.

[1059] Step 2:

[1060] The device sends the collected data to the server. Specifically, the user's smartphone uses Wi-Fi or mobile data network to obtain data from the smartwatch and uploads it to the server. The input is the data obtained from the smartwatch, and the output is the data sent to the server.

[1061] Step 3:

[1062] The server cleans the received data. Specifically, the server removes outliers and incomplete data from the received data. The input is the raw data sent from the device, and the output is the cleaned data. For example, outliers such as a heart rate of 0 or an extremely high heart rate are filtered out.

[1063] Step 4:

[1064] The server standardizes the cleaned data. Specifically, it standardizes the data format so that data from different devices can be analyzed at the same scale. The input is cleaned data, and the output is standardized data. For example, it standardizes the timestamp format from different devices.

[1065] Step 5:

[1066] The server analyzes the standardized data. Specifically, it uses a machine learning algorithm to assess the user's psychological health. This algorithm uses a programming language such as Python. The input is the standardized data, and the output is a psychological health assessment as an analysis result. For example, a random forest algorithm is used to assess the user's stress level based on sleep patterns and heart rate fluctuations.

[1067] Step 6:

[1068] The server generates counseling content based on the analysis results. Specifically, it uses a large-scale language model (LLM) to generate feedback and advice appropriate for the user. The input is the analysis results, and the output is the generated counseling content. For example, if the user is feeling stressed, it generates content suggesting ways to relax. An example of a prompt sentence for the generative AI model is as follows:

[1069] Please enter the user's mental health data (heart rate, high, sleep, lack of sleep). If the user's heart rate is higher than usual and sleep is lacking, they are rated as stressed. Please suggest ways to relax.

[1070] Step 7:

[1071] The device provides counseling. Specifically, when a user opens the app on their smartphone, the device connects the user to an AI counselor on the server. The input is the generated counseling content, and the output is feedback and advice provided to the user. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will pose the next question, "Is that something you're worried about?"

[1072] Step 8:

[1073] The server continues to monitor the user's data. Specifically, it collects data even after the counseling session ends and monitors the user's mental health status based on the new data. The input is the continuously collected data, and the output is an updated mental health assessment and, if necessary, a re-counseling notification. For example, if an abnormality such as a re-elevated heart rate is detected, the server will send another counseling notification.

[1074] (Application example 1)

[1075] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1076] Conventional mental healthcare systems assess a user's mental health status and provide counseling based on the collection and analysis of their physiological and behavioral pattern data. However, no systems have taken into account the impact of a user's psychological state on purchasing behavior. This has made it difficult to improve the customer experience in virtual stores. Therefore, there has been a need for a system that can link a user's mental health status with their purchasing behavior and make appropriate product recommendations.

[1077] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1078] In this invention, the server includes means for collecting vital data and behavioral pattern data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, means for collecting and analyzing user purchasing behavior data, and means for generating product proposals that link the user's psychological state with their purchasing behavior, thereby enabling personalized product proposals that take the user's psychological state into consideration.

[1079] "User" means an individual or group of people who use the system.

[1080] "Vital data" refers to physiological data including biosignals such as heart rate, blood pressure, and body temperature.

[1081] "Behavior pattern data" refers to data relating to the user's daily activities, sleep data, amount of exercise, and other behavioral data.

[1082] "Analysis" means evaluating collected data using statistical methods and machine learning algorithms.

[1083] "Mental health status" refers to a user's mental health and psychological balance.

[1084] "Counseling" means the process of providing advice and feedback to support a user's mental health.

[1085] "Continuous monitoring" means collecting data about a user over a long period of time and monitoring their condition.

[1086] "Purchasing behavior data" refers to behavioral data related to purchasing, such as a user's shopping history and product browsing history.

[1087] "Product suggestion" means analyzing the user's psychological state and purchasing behavior to recommend appropriate products.

[1088] This invention relates to a system for supporting users' mental health care and improving customer experience in virtual stores. This system collects vital data and behavioral pattern data from users, analyzes them, and evaluates the user's mental health state. It then generates personalized counseling content based on the collected data and provides counseling in an interactive format. It also collects data on the user's purchasing behavior and has the function of suggesting products linked to the user's psychological state.

[1089] 1. Program Generation

[1090] The program of this system is configured as follows:

[1091] 2. Explain the program's processing in natural language

[1092] When users use their smartphones or smartwatches to carry out activities, these devices collect vital data such as heart rate and sleep data. When users shop in virtual stores, purchasing behavior data is also collected. This data is sent to a server via the Internet.

[1093] The server cleans and standardizes the collected data, removing outliers and incomplete data. It then analyzes the data using statistical models and machine learning algorithms (e.g., scikit-learn) to assess the user's mental health status. Based on the assessment results, the server generates personalized counseling content. It uses large-scale language models (LLMs) to provide feedback and advice tailored to the user's condition.

[1094] 3. Add specific examples to the description

[1095] For example, suppose a user is enjoying a long shopping session in a virtual store. The smartwatch collects the user's heart rate and sleep data, which are then analyzed by the server. The results show that the user's heart rate is higher than usual and that they have not been getting enough sleep recently. Based on this assessment, the server generates advice such as "Try some light exercise to relax."

[1096] Furthermore, by analyzing user purchasing behavior data, it is possible to recommend relaxation goods or massage equipment to users who are feeling stressed or tired, allowing users to receive product suggestions that take their psychological state into consideration.

[1097] Prompt Sentence Examples

[1098] Below is an example of a prompt sentence to input to a large-scale language model (LLM).

[1099] Create a program that predicts a user's stress level based on their heart rate and sleep data, and generates personalized counseling content.

[1100] Heart rate data: [75, 80, 72, 78, 77]

[1101] Sleep data: [6, 7, 5, 8, 6]

[1102] Stress Level: [3, 4, 2, 5, 3]

[1103] Current data to predict: Heart rate 79, sleep quality 6, stress level 4

[1104] Output: Personalized advice based on stress level

[1105] This system allows users to receive product suggestions that take their psychological state into account even in virtual stores, enabling them to enjoy a comfortable shopping experience.

[1106] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1107] Step 1:

[1108] Users use smartphones or smartwatches to collect vital data and behavioral pattern data.

[1109] How it works: The smartwatch records your heart rate and sleep data, and your smartphone receives this data via an app.

[1110] Input: Heart rate data, sleep data.

[1111] Output: Collected heart rate and sleep data.

[1112] Step 2:

[1113] The terminal transmits the collected data to the server.

[1114] Specific operation: The smartphone uploads the collected data to the server via the Internet.

[1115] Input: Collected heart rate and sleep data.

[1116] Output: Data transfer to the server.

[1117] Step 3:

[1118] The server cleans and standardizes the received data.

[1119] What it does: It uses data cleaning techniques to remove outliers and incomplete data, and standardization techniques to convert data into a consistent format.

[1120] Input: Collected heart rate and sleep data.

[1121] Output: Cleaned and standardized data.

[1122] Step 4:

[1123] The server analyzes the cleaned and standardized data to assess the user's mental health status.

[1124] What it does: Analyzes heart rate and sleep patterns using statistical models and machine learning algorithms (e.g., scikit-learn).

[1125] Input: Cleaned and standardized data.

[1126] Output: The user's mental health assessment results.

[1127] Step 5:

[1128] The server generates personalized counseling content based on the evaluation results.

[1129] Specific operation: Uses a large-scale language model (LLM) to create counseling content appropriate for the user's condition.

[1130] Input: User's mental health assessment results.

[1131] Output: Personalized counseling content.

[1132] Step 6:

[1133] The server conducts interactive counseling with the user.

[1134] Specific operation: Through a smartphone app, questions are presented to the user and the next action is determined based on the user's answer.

[1135] Input: personalized counseling content.

[1136] Output: Answers from the user and the interaction history.

[1137] Step 7:

[1138] The server continues to monitor the user's data even after the counseling session.

[1139] Specific operation: Continuously collects and analyzes data from smartwatches and smartphones.

[1140] Input: Data from smartwatch and smartphone.

[1141] Output: Continuously updated mental health assessment results for the user.

[1142] Step 8:

[1143] The server also collects and analyzes user purchasing behavior data.

[1144] Specific operations: Record and analyze shopping history and product browsing history in virtual stores.

[1145] Input: Purchasing behavior data.

[1146] Output: Parsed purchasing behavior data.

[1147] Step 9:

[1148] The server generates product proposals that link the user's psychological state with their purchasing behavior.

[1149] Specific operation: Based on the user's mental health assessment results and purchasing behavior data, product suggestions are created using a large-scale language model (LLM).

[1150] Input: User's mental health assessment results and purchasing behavior data.

[1151] Output: Personalized product suggestions.

[1152] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1153] This invention is an AI counselor system for supporting users' mental health care, and combines an emotion engine that recognizes the user's emotional state. The system aims to collect data from users via devices such as smartphones and smartwatches, analyze and evaluate that data, and provide personalized counseling.

[1154] Specifically, the server, the terminal, or the user operates as follows.

[1155] First, the user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily life.

[1156] Next, the device (smartwatch) transfers the collected vital data and behavioral pattern data to a smartphone, where the data is transmitted wirelessly in real time.

[1157] The device (smartphone) periodically sends the data it receives to the server. The data is securely encrypted and sent without delay over the Internet.

[1158] The data received by the server is first cleaned to remove outliers and incomplete data. Next, the data is standardized and converted into a format that is easy to analyze. Statistical models and machine learning algorithms are then used to analyze the user's heart rate fluctuations, sleep patterns, and other factors. Based on the results of this analysis, the user's mental health status is assessed. For example, if the heart rate is higher than normal and the user is not getting enough sleep, the server will assess that the user is feeling stressed.

[1159] Furthermore, this invention uses an emotion engine. The device (smartphone) collects the user's facial expressions and voice and analyzes them through the emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time. Voice analysis detects changes in emotion from the tone and speed of the user's voice. This emotion data is also sent to the server and integrated with other vital data and behavioral pattern data.

[1160] The server can then factor in emotional data to further assess the user's mental health. For example, if the user's heart rate is high and their voice tone is depressed, the server may assess that the user is likely depressed.

[1161] Based on the evaluation results, the server then generates personalized counseling content, using a large-scale language model (LLM) to create counseling content that provides feedback and advice tailored to the user's condition.

[1162] When a user opens the smartphone app to receive counseling, the device connects the user to an AI counselor. The AI ​​counselor on the server then presents questions to the user in a dialogue format and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?" This allows the user to describe their condition in detail and receive appropriate feedback and advice.

[1163] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor the user's mental health. It can provide additional counseling or alerts as needed. For example, if the server detects an abnormality, such as the user's heart rate again becoming higher than normal, it can send another counseling notification.

[1164] This system allows users to easily receive counseling 24 hours a day even when they are experiencing a decline in their mental health or motivation, reducing the burden of mental health care. It also alleviates the situation where people are unable to receive care due to a shortage of medical professionals, and contributes to improving social labor productivity.

[1165] The processing flow will be explained below.

[1166] Step 1:

[1167] The user wears a smartwatch, which collects vital data such as the user's heart rate, sleep patterns, and activity level, thereby recording the user's physiological information in their daily lives.

[1168] Step 2:

[1169] The vital data and behavioral pattern data collected by the device (smartwatch) are transferred to a smartphone in real time via wireless communication.

[1170] Step 3:

[1171] The device (smartphone) periodically sends the received data to the server. The data is encrypted and sent over the Internet.

[1172] Step 4:

[1173] The server cleans the incoming data, removing outliers and incomplete data, checks the data for integrity, and converts it into a format suitable for analysis.

[1174] Step 5:

[1175] The server standardizes the cleaned data and analyzes it using statistical models and machine learning algorithms to analyze the user's heart rate variability and sleep patterns.

[1176] Step 6:

[1177] The server evaluates the user's mental health based on the analysis results. For example, if the user's heart rate is higher than normal and they are not getting enough sleep, the server will assess that the user is feeling stressed.

[1178] Step 7:

[1179] The device (smartphone) collects the user's facial expressions and voice data, and the collected emotion data is sent to the emotion engine.

[1180] Step 8:

[1181] The emotion engine on the server analyzes the user's facial expressions and evaluates emotions such as joy, sadness, anger, etc. in real time. It also analyzes voice data and recognizes the user's emotional state from the tone and speed of the voice.

[1182] Step 9:

[1183] The server then combines the emotion data with other vital and behavioral data to provide a more detailed assessment of the user's mental health. For example, if the facial expression indicates sadness and the voice is depressed, it may determine that the user is likely depressed.

[1184] Step 10:

[1185] The server generates personalized counseling content based on the evaluation results, using a large-scale language model (LLM) to generate advice and feedback tailored to the user's condition.

[1186] Step 11:

[1187] When a user opens a counseling app on their smartphone, they are connected to an AI counselor through the app.

[1188] Step 12:

[1189] The AI ​​counselor on the server presents questions to the user in a dialogue format, for example, "You seem to be having trouble sleeping lately. Is there something that's bothering you?"

[1190] Step 13:

[1191] The user answers the questions of the AI ​​counselor. The answers are sent to the server, and the AI ​​counselor decides the next question or advice.

[1192] Step 14:

[1193] The server analyzes the user's answers and provides next steps and specific advice, such as "Try taking deep breaths, they'll help you relax."

[1194] Step 15:

[1195] Even after the counseling session has ended, the server continues to collect and analyze the user's data to monitor the user's mental health. If necessary, the server can provide additional counseling or provide warnings. For example, if an abnormality such as a higher-than-normal heart rate is detected again, another counseling notification can be sent.

[1196] Example 2

[1197] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1198] Conventional mental healthcare systems have limitations in assessing a user's emotional state based solely on physiological and behavioral data. It is difficult to grasp the user's emotional state in detail. In particular, because fluctuations in mental health are also reflected in facial expressions and voice, assessments that do not take these data into account are insufficient, resulting in a problem of reduced accuracy in personalized advice.

[1199] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting physiological data and behavioral data from the user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized advice content based on the evaluation results, means for providing advice to the user in an interactive format, means for continuously monitoring the user's data even after the advice is provided, means for collecting the user's facial expression data and voice data and analyzing the emotional state, and means for evaluating the user's mental health state in detail based on the analysis results. This makes it possible to evaluate the user's mental health state in detail based on the user's facial expression and voice data in addition to the user's physiological data, thereby enabling the generation and provision of highly accurate personalized advice content.

[1200] "Physiological data" refers to data relating to the internal state of the user's body, such as heart rate, blood pressure, body temperature, and breathing patterns.

[1201] "Behavioral data" refers to data such as the user's movements and activity levels in daily life, sleep patterns, and exercise levels.

[1202] "Mental health status" refers to a state related to mental health, such as a user's stress level, emotional state, psychological stability, and mood.

[1203] "Personalized advice" refers to feedback and advice that is customized based on each user's individual mental health status and characteristics.

[1204] "Dialogue-based advice" is advice provided through an interactive exchange with the user, often in a conversational format and involving a question-and-answer process.

[1205] "Monitoring" is a means of continuously tracking a user's status and data and responding if anything deviates from the normal range.

[1206] "Facial expression data" refers to data relating to the user's emotional or mood state, which can be obtained from facial expressions, such as smiles, anger, sadness, etc.

[1207] "Voice data" refers to data relating to the emotions and mental state of a user that can be obtained from the tone, pitch, speed, strength, etc. of the voice uttered by the user.

[1208] "Analysis" is the process of evaluating collected data using statistical models and machine learning algorithms to derive meaningful information.

[1209] The present invention provides a system for providing a detailed assessment of a user's mental health status and providing personalized advice. The system collects data from a device worn by the user and analyzes the data to assess the user's health status. Specific embodiments for implementing the present invention will be described below.

[1210] First, the user wears a device such as a smartwatch or smartphone. The smartwatch collects physiological data such as heart rate, blood pressure, body temperature, and sleep patterns, as well as behavioral data such as activity levels, on a daily basis. The smartphone also collects the user's emotional state using facial and voice recognition technologies.

[1211] The collected data is transferred from the device (smartwatch) to a smartphone via wireless communication (e.g., Bluetooth), where it is encrypted and securely transmitted to a server via the Internet.

[1212] The server cleans the received data, removes outliers, and standardizes it. It then analyzes the data using statistical models and machine learning algorithms. This analysis assesses the user's mental health based on heart rate variability and sleep patterns. It also includes an emotion engine that analyzes facial expressions and voice data, allowing it to assess the user's emotional state.

[1213] For example, if the user's heart rate is higher than normal and the tone of their voice is depressed, the server can assess that the user is feeling stressed.

[1214] The server then uses a large-scale language model (LLM) to generate personalized advice that provides feedback and advice tailored to the user's condition. The generated advice is then provided to the user through a smartphone app. The app interactively presents questions to the user and determines the next action based on the user's answers.

[1215] Examples of specific prompts include the following:

[1216] "Evaluate whether the user is experiencing stress based on recent heart rate and sleep pattern data."

[1217] "When a user asks about recent mood changes, generate a recommendation based on their answer, suggesting the next course of action."

[1218] Finally, the server continues to collect user data after the advice is implemented to continuously monitor the user's mental health, providing additional advice or warnings as needed to help the user receive effective mental health care.

[1219] This system allows users to manage their own mental health 24 hours a day and receive timely and accurate feedback. It also makes up for the shortage of medical resources and contributes to improving the mental health of society as a whole.

[1220] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1221] Step 1: Collect user data

[1222] A user puts on a smartwatch. The smartwatch automatically collects physiological and behavioral data, such as heart rate, sleep patterns, and activity levels. For example, the smartwatch starts measuring heart rate the moment the user wakes up in the morning and puts it on. The input data is about the user's physiological state and behavior, and the output is vital data stored on the device.

[1223] Step 2: Transferring data

[1224] The device (smartwatch) transmits collected vital data and behavioral pattern data to a smartphone in real time using wireless communication (such as Bluetooth). For example, after a user finishes jogging, the device automatically transmits heart rate and calorie consumption data to the smartphone. The input data is the vital data stored in the smartwatch, and the output is the data transferred to the smartphone.

[1225] Step 3: Sending data

[1226] The device (smartphone) periodically sends the received data to a server. The data is encrypted and sent securely over the Internet without delay. The input data is vital and behavioral data stored on the smartphone, and the output is encrypted data sent to the server.

[1227] Step 4: Process the data

[1228] The data received by the server is first cleaned to remove outliers and incomplete data. Then, a standardization process is performed to convert the data into a format that is easier to analyze. The input data is the encrypted data sent to the server, and the output is the cleaned and standardized data. Specifically, heart rate data from people who are active late at night is removed as an outlier, and the remaining data is standardized.

[1229] Step 5: Mental health assessment

[1230] The server evaluates the user's mental health based on the analyzed data. This evaluation is performed using statistical models and machine learning algorithms. The input data is cleaned and standardized data, and the output is the user's mental health assessment result. Specifically, if a high heart rate and lack of sleep are detected, the server evaluates the user as being in a stressed state.

[1231] Step 6: Collect and analyze emotion data

[1232] The device (smartphone) collects the user's facial expressions and voice and analyzes them through an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects changes in emotion from the tone and speed of voice. The input data is facial expression data and voice data, and the output is emotional data analyzed in real time.

[1233] Step 7: Sending Emotion Data

[1234] The device (smartphone) sends the collected emotional data to a server, which then integrates this data with other vital data. The input data is emotional data analyzed in real time, and the output is the emotional data sent to the server.

[1235] Step 8: Detailed Mental Health Assessment

[1236] The server integrates the emotional data and vital data to provide a more detailed assessment of the user's mental health. The input data is the integrated emotional and vital data, and the output is a detailed mental health assessment result. Specifically, if the heart rate is high and the voice tone is depressed, the server assesses that the user is likely to be depressed.

[1237] Step 9: Creating counseling content

[1238] The server generates personalized advice based on the user's mental health assessment using a large-scale language model (LLM). The input data is the detailed mental health assessment results, and the output is customized advice. For example, specific advice such as "Try deep breathing and relaxing music" as relaxation techniques to reduce stress is generated.

[1239] Step 10: Conducting counseling

[1240] When a user opens the app on their smartphone, the device connects them to an AI counselor. The AI ​​counselor presents questions to the user in a dialogue format and determines the next action based on the user's answers. The input data is customized advice, and the output is consultation and feedback provided to the user. Specifically, if the user answers "I haven't been able to sleep lately," the AI ​​counselor will present the next question: "Is that something you're worried about?"

[1241] Step 11: Continuous monitoring and feedback

[1242] The server continues to collect data on the user and continuously monitors their mental health. It provides additional counseling or warnings as needed. The input data is continuously collected vital and emotional data, and the output is additional advice or warnings. Specifically, if the user's heart rate again shows abnormal values, another counseling notification is sent.

[1243] (Application example 2)

[1244] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1245] Currently, many people need mental health support, but it is difficult to receive professional counseling. Furthermore, there is a lack of systems that can detect mental health problems such as stress and anxiety early and implement appropriate measures. In particular, there is a need for systems that provide real-time mental health care in daily life and provide appropriate content for relaxation and learning. A system that analyzes a user's emotional state and provides personalized counseling and content tailored to that state would be extremely useful in improving mental health, but such systems have not yet been fully implemented.

[1246] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1247] In this invention, the server includes means for collecting vital data and behavioral pattern data from a user, means for analyzing the collected data and evaluating the user's mental health state, means for generating personalized counseling content based on the evaluation results, means for conducting interactive counseling with the user, means for continuously monitoring the user's data even after the counseling, and means for analyzing the user's emotional state and recommending mental health care content based on the emotional data. This allows the user to receive mental health care while being provided with personalized content such as relaxing music, meditation guides, stretching videos, and learning content in real time, tailored to their mental health state.

[1248] "Vital data" refers to physiological data such as a user's heart rate, sleep patterns, and activity level.

[1249] "Behavioral pattern data" refers to data related to the user's behavior and activities in their daily lives.

[1250] "Emotional data" refers to data relating to the emotional state of a user that is analyzed from their facial expressions and voice.

[1251] "Analysis" refers to the process of evaluating collected data using statistical models and machine learning algorithms to derive results.

[1252] "Mental health status" refers to the psychological and emotional well-being of a user.

[1253] "Personalized counseling content" refers to counseling advice and feedback that is optimized based on the individual user's mental health status.

[1254] "Dialogue-based counseling" refers to interactive counseling conducted between the user and the AI ​​counselor through questions and answers.

[1255] "Monitoring" refers to the process of continuously watching user data to detect fluctuations and anomalies.

[1256] "Content" refers to relaxing music, meditation guides, stretching videos, learning content, etc. provided to support users' mental health care.

[1257] "Recommendation method" refers to the process of selecting and providing optimal content to the user based on the user's emotional state and vital data.

[1258] This invention is a comprehensive AI counselor system to support users' mental health care. It collects and analyzes vital data, behavioral pattern data, and emotional data, and provides optimal counseling and content based on the results.

[1259] This system consists of three main components: a server, a terminal (such as a smartphone or smartwatch), and a user.

[1260] First, the user wears a smartwatch and collects vital data such as heart rate, sleep patterns, and activity levels during daily activities. The device then transfers this collected data in real time to a smartphone, which then transmits the data to a server.

[1261] The server receives the data via a secure internet connection, first cleaning it to remove outliers and incomplete data, then standardizing and converting it into an easy-to-analyze format, and using statistical models and machine learning algorithms to analyze the user's heart rate variability, sleep patterns, and other data to assess their mental health.

[1262] In addition, the user's smartphone collects facial expressions and voice data and analyzes the emotional data using an emotion engine. Facial expression analysis recognizes emotions such as sadness, anger, and joy in real time, while voice analysis detects emotional changes from the tone and speed of the voice. This emotional data is also sent to a server and integrated with other vital data and behavioral pattern data.

[1263] The server uses this integrated data to perform a detailed assessment of the user's mental health status, and based on the assessment results, generates personalized counseling content and optimal content (relaxing music, meditation guides, stretching videos, learning content, etc.). The generated content is delivered to the user's smartphone, allowing the user to receive interactive counseling or view recommended content.

[1264] Here's a specific example: If a user feels like they want to relax, their heart rate will rise and their tone of voice will indicate they are feeling stressed. In this case, the system will provide relaxing music and deep breathing guidance. For example, the system might say, "Your heart rate has been high for some time. We recommend some relaxing music (classical, nature sounds, etc.)."

[1265] In this way, this system is a powerful tool for supporting users' mental health care and improving the quality of their daily lives. Users can always receive the optimal support for their condition in real time.

[1266] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1267] Step 1:

[1268] The user wears a smartwatch to collect vital data such as heart rate, sleep patterns, and activity level. The input is the user's physiological information, and the output is vital data. This data is recorded in real time by the smartwatch.

[1269] Step 2:

[1270] The terminal (smartwatch) transfers the vital data collected to the smartphone. The input is the vital data collected by the smartwatch, and the output is the data transferred to the smartphone. The data is transmitted in real time via wireless communication.

[1271] Step 3:

[1272] The data received by the device (smartphone) is periodically sent to the server. The input is the vital data transferred to the smartphone, and the output is the data sent to the server. The data is encrypted and sent without delay over the Internet.

[1273] Step 4:

[1274] The server cleans the data it receives, removing outliers and incomplete data. The input is the vital data sent to the server, and the output is the cleaned data. At this stage, the data is standardized and converted into a format that is easy to analyze.

[1275] Step 5:

[1276] The server uses statistical models and machine learning algorithms to analyze the user's heart rate fluctuations and sleep patterns. The input is cleaned vital data, and the output is the analysis results (the user's mental health status). The data analysis evaluates whether the user is feeling stressed.

[1277] Step 6:

[1278] The device (smartphone) collects the user's facial expressions and voice and analyzes them using an emotion engine. The input is the user's facial expression image and voice clip, and the output is the analyzed emotion data. Emotions such as sadness, anger, and joy are recognized from facial expressions, and emotional changes are recognized in real time from the tone and speed of voice.

[1279] Step 7:

[1280] The emotional data collected by the device is sent to a server and integrated with other vital data and behavioral pattern data. The input is the analyzed emotional data, and the output is an integrated dataset. Based on the integrated data, a more detailed mental health status is assessed.

[1281] Step 8:

[1282] The server generates personalized counseling and content for the user's mental health care based on the evaluation results. The input is the integrated dataset, and the output is the generated counseling and recommended content. Specifically, it uses a large-scale language model (LLM) to create feedback and advice, and recommends relaxing music, meditation guides, stretching videos, learning content, and other items that are optimal for the user's current state.

[1283] Step 9:

[1284] When a user opens a smartphone app to receive counseling, the device connects the user with an AI counselor. The input is the user's counseling request, and the output is an interactive counseling session. The AI ​​counselor on the server presents questions to the user and determines the next action based on the user's answers. For example, if the user answers, "I haven't been able to sleep lately," the AI ​​counselor will ask the next question, "Is that something you're worried about?"

[1285] Step 10:

[1286] Even after the counseling session ends, the server continues to collect and analyze the user's data to monitor their mental health. The input is continuously collected vital and emotional data, and the output is an updated mental health assessment. If necessary, the server provides additional counseling or warnings. Specifically, if an abnormality such as a recurring high heart rate is detected, the server sends another counseling notification.

[1287] 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.

[1288] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1289] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1290] 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.

[1291] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1292] 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.

[1293] 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).

[1294] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1295] 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."

[1296] 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.

[1297] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1298] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1299] 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.

[1300] 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.

[1301] 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.

[1302] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1303] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1304] 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.

[1305] 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.

[1306] 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.

[1307] 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.

[1308] The following is further disclosed regarding the above embodiment.

[1309] (Claim 1)

[1310] means for collecting vital data and behavioral pattern data from a user;

[1311] means for analyzing the collected data and assessing the user's mental health status;

[1312] a means for generating personalized counseling content based on the assessment results;

[1313] means for conducting interactive counseling with the user;

[1314] A means of continuously monitoring user data after counseling;

[1315] A system including:

[1316] (Claim 2)

[1317] a means of cleaning and standardizing the collected data;

[1318] The system of claim 1 further comprising:

[1319] (Claim 3)

[1320] a means for generating alerts or feedback to the user;

[1321] The system of claim 1 further comprising:

[1322] "Example 1"

[1323] (Claim 1)

[1324] means for collecting physiological data and behavioral pattern data from a user;

[1325] means for transmitting the collected data to a server over a network;

[1326] means for cleaning and standardizing the received data;

[1327] means for analyzing the cleaned data and assessing the user's psychological well-being;

[1328] a means for generating personalized counseling content based on the assessment results;

[1329] A means of providing feedback and advice to users using generative AI models; and

[1330] means for interactively counseling the user;

[1331] A means of continuously monitoring user data after counseling;

[1332] A system including:

[1333] (Claim 2)

[1334] a means of cleaning and standardizing the collected data;

[1335] and a means to further analyze the data using machine learning algorithms.

[1336] The system of claim 1 further comprising:

[1337] (Claim 3)

[1338] a means for generating alerts or feedback to the user;

[1339] means for automatically sending re-counseling notices based on user data;

[1340] The system of claim 1 further comprising:

[1341] "Application Example 1"

[1342] (Claim 1)

[1343] means for collecting vital data and behavioral pattern data from a user;

[1344] means for analyzing the collected data and assessing the user's mental health status;

[1345] a means for generating personalized counseling content based on the assessment results;

[1346] means for conducting interactive counseling with the user;

[1347] A means of continuously monitoring user data after counseling;

[1348] A means for collecting and analyzing user purchasing behavior data;

[1349] A means for generating product proposals that link the user's psychological state and purchasing behavior;

[1350] A system including:

[1351] (Claim 2)

[1352] a means of cleaning and standardizing the collected data;

[1353] The system of claim 1 further comprising:

[1354] (Claim 3)

[1355] a means for generating alerts or feedback to the user;

[1356] The system of claim 1 further comprising:

[1357] "Example 2: Combining Emotion Engines"

[1358] (Claim 1)

[1359] means for collecting physiological and behavioral data from a user;

[1360] means for analyzing the collected data and assessing the user's mental health status;

[1361] means for generating personalized advice based on the evaluation results;

[1362] means for interactively providing advice to a user;

[1363] a means for continuing to monitor the user's data after the advisory; and

[1364] means for collecting facial expression data and voice data of a user and analyzing the emotional state of the user;

[1365] Based on the analysis results, a detailed mental health assessment method and

[1366] A system including:

[1367] (Claim 2)

[1368] a means of filtering and standardizing the collected data;

[1369] The system of claim 1 further comprising:

[1370] (Claim 3)

[1371] a means for generating alerts or feedback to the user;

[1372] The system of claim 1 further comprising:

[1373] "Application example 2 when combining emotion engines"

[1374] (Claim 1)

[1375] means for collecting vital data and behavioral pattern data from a user;

[1376] means for analyzing the collected data and assessing the user's mental health status;

[1377] a means for generating personalized counseling content based on the assessment results;

[1378] means for conducting interactive counseling with the user;

[1379] A means of continuously monitoring user data after counseling;

[1380] means for analyzing the emotional state of a user and recommending content for mental health care based on the emotional data;

[1381] A system including:

[1382] (Claim 2)

[1383] a means of cleaning and standardizing the collected data;

[1384] The system of claim 1 further comprising:

[1385] (Claim 3)

[1386] a means for generating alerts or feedback to the user;

[1387] The system of claim 1 further comprising: [Explanation of symbols]

[1388] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting vital data and behavioral pattern data from a user; means for analyzing the collected data and assessing the user's mental health status; a means for generating personalized counseling content based on the assessment results; means for conducting interactive counseling with the user; A means of continuously monitoring user data after counseling; A system including:

2. a means of cleaning and standardizing the collected data; The system of claim 1 further comprising:

3. a means for generating alerts or feedback to the user; The system of claim 1 further comprising:

Images