System

Abstract

A system is provided.SOLUTION: A system, comprising: means for collecting data of lifestyle, health condition, and genetics of a user from a data collection device; means for integrating and storing the collected data in a centralized database; means for training a prediction model generated based on the integrated data to predict health risks and health condition of each user; means for generating and providing a customized health improvement plan to the user based on the prediction model; and means for monitoring changes in behavior data and health condition of the user and updating the customized health improvement plan in real time.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] In modern society, with increasing health awareness, there is a demand for personalized health management based on individual lifestyle habits, health status, and genetic characteristics. However, current systems and methods make it difficult to integrate this data and provide preventive measures and health improvement plans optimized for each user. In particular, there is a lack of systems that can predict individual health risks early and implement customized preventive measures. There is also a need for real-time monitoring of user behavioral data and changes in health status and rapid provision of necessary feedback. The present invention aims to provide a health management system that solves these problems. [Means for solving the problem]

[0005] To solve the above-mentioned problems, the present invention provides a health management system that includes the following means: First, a means for collecting data on a user's lifestyle habits, health status, and genetic characteristics from a data collection device is provided. Next, a means for integrating the collected data and storing it in a centralized database is provided. Further, a means for training a generative AI model based on the integrated data to predict each user's health risks and health status is provided. Next, a means for generating a customized health improvement plan based on the predictive model and providing it to the user is provided. Furthermore, a means for monitoring changes in the user's behavioral data and health status and updating the customized health improvement plan in real time is provided. Furthermore, in this system, the customized health improvement plan includes a meal plan, an exercise plan, and medical test recommendations, and the data collection device includes a smartwatch, a fitness device, and medical equipment. This allows for health management tailored to each individual user and prevents and improves health risks.

[0006] "Data Collection Device" refers to a combination of hardware and software for collecting a user's lifestyle, health, and genetic characteristics.

[0007] "Lifestyle habits" refers to the user's daily behavior and habits, specifically diet, exercise, sleep, stress management, etc.

[0008] "Health status" refers to data that indicates the user's current physical and mental state, and includes physiological data such as heart rate, blood pressure, and blood sugar level.

[0009] "Genetics" refers to characteristics based on a user's genetic information, including data that indicates certain disease risks or health trends.

[0010] "Integration" refers to the process of consolidating data collected from different sources and converting it into a usable format.

[0011] "Database" refers to a software system for efficiently storing, retrieving, and accessing collected and consolidated data.

[0012] "Predictive model" refers to a machine learning model that uses collected and integrated data to assess a user's health risks and health status in the future.

[0013] "Customized Health Improvement Plan" refers to a comprehensive health improvement plan, including appropriate diet, exercise, medical testing, etc., based on the user's individual data and predictive models.

[0014] "Monitoring" refers to the process of monitoring and analyzing user behavioral data and changes in health status in real time.

[0015] "Feedback" refers to information or instructions provided to a user that encourages them to adjust their behavior or health management.

[0016] A "smartwatch" refers to a wearable device that collects a user's health and activity data.

[0017] "Fitness Device" means a device used to record and monitor a user's exercise and activity data.

[0018] A "medical device" is a device used to measure and collect a user's health data, including, for example, a blood pressure monitor or a weight scale. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] The health management system according to the present invention predicts health risks for individual users and provides customized health improvement plans through the following steps.

[0041] First, users collect lifestyle data using data collection devices such as smartwatches and fitness devices. This data includes the number of steps taken, heart rate, sleep time, and activity level. Furthermore, users input information about their diet and medications through the device. Health status information (blood pressure, blood sugar, cholesterol levels, etc.) obtained through regular health checkups is also collected from medical devices.

[0042] The collected data is sent to a server where it is consolidated. The server cleans the raw data, imputes missing values, and removes outliers. The cleaned data is stored in a centralized database and organized by user.

[0043] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk, including predicting the risk of diseases such as heart disease and diabetes.

[0044] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet, a cardiovascular exercise plan, and relevant medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-fat, high-fiber diet and three days of cardiovascular exercise per week.

[0045] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, and undergoing recommended medical tests.

[0046] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[0047] For example, in the case of a female user in her 50s, data such as heart rate, number of steps, and sleep time is collected from a smartwatch, and information on diet and home medications is entered into the app. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan and aerobic exercise plan are generated and notified to the user via the device. The user then lives their daily life according to the proposed plan. The server collects and analyzes the executed data, evaluates the effectiveness of the plan, and makes adjustments as necessary.

[0048] In this way, the present invention provides health management optimized for each user, realizing the prevention and improvement of health risks.

[0049] The processing flow will be explained below.

[0050] Step 1: Collect data

[0051] The device automatically collects the user's lifestyle data (such as steps, heart rate, sleep time, and activity level) from smartwatches and fitness devices.

[0052] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[0053] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[0054] Step 2: Data integration and preprocessing

[0055] The server receives and integrates the data sent from the various data collection devices.

[0056] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[0057] The server stores the cleaned data in a centralized database, organized by user.

[0058] Step 3: Train the predictive model

[0059] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[0060] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[0061] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[0062] Step 4: Assess health risks

[0063] The server uses a trained predictive model to assess each user's health risk.

[0064] For example, it calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[0065] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[0066] Step 5: Generate a customized health improvement plan

[0067] The server generates a customized health improvement plan for each user based on the predictive model.

[0068] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[0069] Specifically, for example, users at high risk of heart disease are recommended to follow a low-fat, high-fiber diet and do aerobic exercise three times a week.

[0070] Step 6: Communicate and execute the plan

[0071] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[0072] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[0073] The user follows the health improvement plan and puts it into practice in their daily lives, specifically by changing their diet as instructed, doing the recommended exercises, and undergoing any necessary medical tests.

[0074] Step 7: Monitoring and feedback

[0075] The server monitors the user's behavioral data and changes in health status in real time.

[0076] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[0077] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[0078] Step 8: Assess long-term impact and update the plan

[0079] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[0080] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[0081] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[0082] Example 1

[0083] 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."

[0084] Conventional health management systems struggled not only to collect users' lifestyle and health data, but also to effectively integrate and analyze it. Furthermore, they lacked data cleaning and feature extraction processes to improve the accuracy of predictive models, making it impossible to provide users with appropriate health improvement plans. This made it difficult to provide health management optimized for each individual user.

[0085] 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.

[0086] In this invention, the server includes a means for filling in missing values ​​and eliminating outliers through a cleaning process, a means for applying statistical methods and machine learning algorithms to extract important features, and a means for monitoring changes in the user's behavioral data and health status and updating the customized health improvement plan in real time. This makes it possible to effectively integrate and analyze the user's lifestyle data and health data and provide an optimized health improvement plan for each individual user. The "data collection device" is a device for collecting data on the user's lifestyle, health status, and genetic characteristics.

[0087] A "centralized database" is a database in which collected data is integrated, organized, and stored.

[0088] A "predictive model" is a model generated based on the integrated data to predict the health risks and health status of each user.

[0089] "Health risks" are predicted results of diseases and health problems that a user may suffer from in the future.

[0090] A "health improvement plan" is a customized health promotion and lifestyle improvement plan generated based on a predictive model and provided to the user.

[0091] "Monitoring" is the process of monitoring user behavioral data and changes in health status in real time.

[0092] "Cleaning" is a process of organizing data to fill in missing values ​​and remove outliers.

[0093] "Features" are data elements that are extracted using statistical methods or machine learning algorithms and are considered important for training predictive models.

[0094] "Statistical methods" are statistical techniques and methodologies used in data analysis.

[0095] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and perform tasks such as prediction and classification.

[0096] "Real-time updates" is the process of adjusting and modifying your health improvement plan in immediate response to changes in your condition.

[0097] A "meal plan" is the specific meal content and frequency recommended to improve a user's health.

[0098] An "exercise plan" is the type and frequency of exercise suggested based on the user's fitness level and goals.

[0099] "Medical Test" means a professional test conducted to assess the User's health.

[0100] A "smartwatch" is a wearable device that measures and collects a user's physical activity data.

[0101] A "fitness device" is a dedicated piece of equipment used to collect a user's exercise data.

[0102] A "medical device" is a device or instrument used to collect data on a user's health status.

[0103] These definitions allow a more concrete understanding of the technical scope of the invention.

[0104] The health management system according to the present invention is configured by combining a plurality of data collection devices, terminals, and servers, which work together to manage the health of a user. Detailed embodiments of this system will be described below.

[0105] Data collection

[0106] First, the user wears a data collection device such as a smartwatch or fitness device to collect data on their daily lifestyle habits. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user also uses a device with a dedicated app installed to input data on their diet and medications. Furthermore, health condition data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups are collected from medical devices and entered into the device.

[0107] Data Integration and Cleaning

[0108] The device sends the collected data to a server in real time. The server then integrates the received data and performs a cleaning process. This cleaning process includes filling in missing values ​​and eliminating outliers. For example, if the heart rate data for a certain day is abnormally high, it is corrected to an appropriate value based on the data from before and after. This ensures the integrity and reliability of the data.

[0109] Training generative AI models

[0110] The server uses the cleaned data to train a generative AI model. Specifically, it uses Python libraries such as TensorFlow and scikit-learn to extract important features from the data and build a predictive model. This predictive model applies statistical methods and machine learning algorithms to assess each user's health risk.

[0111] Generate and deliver health improvement plans

[0112] Based on the trained predictive model, the server generates a customized health improvement plan for each user, including a low-salt diet plan, aerobic exercise plan, and relevant medical test recommendations. For example, a user at high risk of heart disease might be recommended a low-fat, high-fiber diet plan and three days of aerobic exercise per week. These plans are then sent to the user via their device, with detailed instructions and reminders.

[0113] Monitoring and real-time updates

[0114] The server monitors the user's behavioral data and changes in health status in real time. If any significant changes or abnormalities are detected, the server immediately notifies the user of countermeasures and updates the health improvement plan in real time. The user can adjust their daily life based on this feedback to maintain and improve their health.

[0115] Examples of specific examples and prompts

[0116] For example, for a female user in her 50s, the results would be as follows:

[0117] 1. The user wears a smartwatch to collect data such as heart rate, steps taken, and sleep time.

[0118] 2. Information about meals and home medical medications is entered into the terminal.

[0119] 3. The server consolidates this data and performs cleaning processing.

[0120] 4. The server predicts the risk of high blood pressure and generates a low-salt meal plan and an aerobic exercise plan.

[0121] 5. The device notifies the user of this plan.

[0122] 6. The user follows the proposed plan and continues with their daily life.

[0123] 7. The server collects and analyzes execution data, evaluates the effectiveness of the plan, and makes any necessary adjustments.

[0124] Prompt Sentence Examples

[0125] "For a female user in her 50s, please predict the risk of high blood pressure based on heart rate, steps, and sleep time data from the past week."

[0126] "Generate a customized low-sodium meal plan based on the user's dietary data."

[0127] "Please suggest an aerobic exercise plan based on the user's activity level data."

[0128] In accordance with the above aspects, the present invention provides optimized health management and preventative measures for individual users, thereby realizing reduction and improvement of health risks.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1: Data collection

[0131] Users wear smartwatches or fitness devices to collect daily life data such as steps taken, heart rate, sleep time, and activity level. This data is collected in real time and transmitted to the device.

[0132] Input: Raw data from smartwatches and fitness devices

[0133] Output: Lifestyle data transferred to the device (number of steps, heart rate, sleep time, activity level, etc.)

[0134] Step 2: Enter diet and medication data

[0135] Users enter information about their diet and medication into a dedicated app, which then collects all of their lifestyle-related data.

[0136] Input: Meal and medication information manually entered by the user into a dedicated app

[0137] Output: Meal content data and medication information data stored on the device

[0138] Step 3: Health status data collection

[0139] Users input the results of their regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) into the medical device, and this data is also stored on the terminal.

[0140] Input: Numerical values ​​obtained from medical equipment for health checkup data

[0141] Output: Health status data stored on the device

[0142] Step 4: Send data

[0143] The device transmits all collected data in real time to a server via an internet connection.

[0144] Input: All user data stored on the device (lifestyle data, dietary and medication data, health status data)

[0145] Output: User data sent to the server

[0146] Step 5: Data Cleaning

[0147] The server cleans the submitted data, imputing missing values ​​and eliminating outliers, using statistical methods and algorithms in the cleaning process.

[0148] Input: All user data sent from the device

[0149] Output: Data after cleaning (missing values ​​imputed, outliers removed)

[0150] Step 6: Data Integration

[0151] The server stores the cleaned data in a centralized database and organizes it by user.

[0152] Input: User data after cleaning

[0153] Output: A consolidated database (organized by user)

[0154] Step 7: Feature extraction

[0155] The server uses statistical methods and machine learning algorithms to extract important features, such as fluctuations in heart rate and rising trends in blood pressure.

[0156] Input: Integrated database

[0157] Output: Extracted important feature data

[0158] Step 8: Training the generative AI model

[0159] The server trains a generative AI model based on the extracted features, using tools such as Python's TensorFlow.

[0160] Input: Important feature data

[0161] Output: A trained predictive model

[0162] Step 9: Health Risk Prediction

[0163] The server uses trained predictive models to assess each user's health risks, such as heart disease and diabetes risk.

[0164] Input: Trained predictive model and user data

[0165] Output: Health risk assessment for each user

[0166] Step 10: Create a Health Improvement Plan

[0167] The server generates a customized health improvement plan based on the predicted results, including specific diet and exercise plans.

[0168] Input: Health risk assessment data

[0169] Output: A customized health improvement plan

[0170] Step 11: Plan Notification

[0171] The device will notify the user of the generated health improvement plan and provide detailed instructions and reminders.

[0172] Input: Health improvement plan received from the server

[0173] Output: Health improvement plan communicated to the user

[0174] Step 12: Monitoring and Feedback

[0175] The server monitors the user's behavioral data and changes in health status in real time, and immediately notifies users of any significant changes or abnormalities and adjusts the plan based on user feedback.

[0176] Input: Real-time behavioral data and feedback

[0177] Output: Updated health improvement plan and feedback notification

[0178] (Application example 1)

[0179] 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."

[0180] In modern society, many people are exposed to health risks due to lifestyle-related diseases and stress. Conventional health management systems have difficulty effectively collecting individual users' health data and providing individually customized health improvement plans. Furthermore, they lack the means to recommend health-related products that users can use on a daily basis and to easily purchase these products. It is necessary to provide a system that solves these issues and allows users to manage their health on a daily basis.

[0181] 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.

[0182] In this invention, the server includes means for collecting data on users' lifestyle habits, health conditions, and genetic characteristics from a data collection device, means for integrating the collected data and storing it in a centralized database, means for training a prediction model generated based on the integrated data to predict each user's health risks and health conditions, means for generating a customized health improvement plan based on the prediction model and providing it to the user, means for monitoring changes in the user's behavioral data and health conditions and updating the customized health improvement plan in real time, means for suggesting health-related products suitable for the user in a virtual store, and means for the user to purchase health-related products in the virtual store. This allows for optimal health management for each user, enabling effective prevention and improvement of health risks in daily life.

[0183] A "data collection device" is a device that collects data about a user's lifestyle, health, or genetic characteristics, including a smartwatch, fitness device, or medical device.

[0184] "Integration" refers to the process of collecting different types of data and putting them into a centralized database in an easily manageable form.

[0185] A "predictive model" is a model that uses statistical methods and machine learning algorithms to predict each user's health risks and health status based on collected data.

[0186] "Customized Health Improvement Plan" means an individually optimized health maintenance and improvement plan generated based on each user's individual data and predictive models, which includes a meal plan, exercise plan, and medical test recommendations.

[0187] A "database" is a structured collection of data that is used to centrally store and manage collected data.

[0188] "Virtual store" refers to a virtual store space that users can access online to browse and purchase health-related products.

[0189] "Product Recommendation" means suggesting appropriate health-related products to a user based on the user's health risks and needs as assessed by the predictive model.

[0190] "Real-time updates" refers to the process of instantly changing and adjusting a customized health improvement plan in response to changes in a user's behavioral data and health status.

[0191] "Behavioral data" refers to data related to a user's daily activities, including the number of steps taken, heart rate, and sleep time.

[0192] "Health status" refers to data that indicates the user's physical and mental health status, including blood pressure, blood sugar levels, cholesterol levels, etc.

[0193] A health management system according to the present invention includes the following components.

[0194] First, users use data collection devices (e.g., smartwatches, fitness devices, medical equipment) to collect data about their lifestyle, health, and genetic characteristics, including steps taken, heart rate, sleep duration, blood pressure, blood sugar, and cholesterol levels.

[0195] The server then consolidates the collected data and stores it in a centralized database, where it undergoes cleaning processes such as removing outliers and imputing missing values.

[0196] The server then uses the combined data to train a generative AI model, which uses statistical methods and machine learning algorithms (e.g., TensorFlow) to predict each user's health risks and conditions, including risk of diseases such as heart disease and diabetes.

[0197] The server generates a customized health improvement plan based on the predictive model, including a meal plan, exercise schedule, and medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-sodium meal plan and three days of aerobic exercise per week.

[0198] Furthermore, the customized health improvement plan is communicated to the user via their device (e.g., smartphone, head-mounted display), where they receive detailed instructions and set reminders to follow through, such as exercising regularly or changing their diet while wearing the smartwatch.

[0199] The server monitors user behavioral data and changes in health status in real time, and uses this data to continuously update the predictive model. If it detects any significant changes or abnormalities, it provides immediate feedback and notifies the user of appropriate measures.

[0200] This also includes a means for suggesting health-related products (e.g., supplements, fitness equipment, health foods, etc.) suitable for users in a virtual store. Users can use their devices to explore the virtual store and purchase the suggested products. This allows users to obtain related products as part of a health management system optimized for each individual user.

[0201] Specific examples

[0202] For example, for a 50-year-old female user, data such as the number of steps taken, heart rate, and sleep time are collected from the smartwatch. Additionally, health checkup results such as blood pressure and blood sugar levels are integrated into the database. The server uses this data to predict the risk of high blood pressure and generate a low-salt meal plan and aerobic exercise plan. The user wears a head-mounted display and visits a virtual store, where they can purchase suggested health-related products.

[0203] Prompt Sentence Examples

[0204] Based on the user's health data, assess their health risks and suggest appropriate health products to display in a virtual store. Users can view and purchase products in 3D using an HMD.

[0205] As described above, the present invention provides health management that is optimized for each user, enabling effective prevention and improvement of health risks in daily life.

[0206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0207] Step 1:

[0208] Users use smartwatches and fitness devices to collect data about their lifestyle and health.

[0209] Input: Data such as steps, heart rate, sleep time, blood pressure, blood sugar, and cholesterol levels.

[0210] Output: Raw data obtained from the data acquisition device.

[0211] Specifically, for example, a smartwatch measures the user's heart rate and number of steps, and transmits that data to a smartphone via Bluetooth.

[0212] Step 2:

[0213] The server consolidates the collected data and stores it in a centralized database.

[0214] Input: Data collected from smartwatches and fitness devices.

[0215] Output: Cleaned data stored in a centralized database.

[0216] Specifically, the server removes outliers and imputes missing values, and stores the formatted data in a database. For example, data cleaning is performed using libraries such as Pandas and NumPy.

[0217] Step 3:

[0218] The server trains a generative AI model based on the integrated data to predict each user's health risks and health status.

[0219] Input: The data in the cleaned database.

[0220] Output: Predictive model training results and health risk assessment.

[0221] Specifically, it uses Python and TensorFlow to run machine learning algorithms based on past data to predict each user's health risks.

[0222] Step 4:

[0223] The server generates a customized health improvement plan based on the predictive model and provides it to the user.

[0224] Input: The output data of the predictive model.

[0225] Output: A personalized health improvement plan for each user.

[0226] Specifically, for users with high health risks, the system creates a plan that includes a low-salt diet and aerobic exercise, and generates a notification.

[0227] Step 5:

[0228] A customized health improvement plan is provided via the user's device (smartphone or head-mounted display).

[0229] Enter: a customized health improvement plan.

[0230] Output: Health improvement plan details displayed on the device.

[0231] Specifically, it uses the smartphone's notification function to inform users of the plan and set reminders.

[0232] Step 6:

[0233] The user follows the provided plan in their daily life and again collects data.

[0234] Input: New data collected according to the health improvement plan.

[0235] Output: Data of the action taken.

[0236] Specifically, the user performs the suggested exercise and the data is collected by the smartwatch.

[0237] Step 7:

[0238] The server monitors user behavioral data and changes in health status in real time and updates the predictive model accordingly.

[0239] Input: Collected behavioral data again.

[0240] Output: Updated predictive model and adjusted health improvement plan.

[0241] Specifically, it retrains its AI models based on new data and adjusts health plans as needed.

[0242] Step 8:

[0243] The server proposes health-related products suitable for the user in the virtual store and provides the user with the ability to purchase the products through the terminal.

[0244] Input: The output of the predictive model and the user's health status data.

[0245] Output: Suitable health-related product suggestions displayed in a virtual store.

[0246] Specifically, we use WebGL or Unity to build a 3D virtual store and provide an interface where users can purchase suggested products. Users use a head-mounted display to explore the virtual store and purchase appropriate health products.

[0247] As described above, the system of the present invention provides optimized health management for each individual user, enabling effective prevention and improvement of health risks in daily life.

[0248] 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.

[0249] The health management system according to the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide a personalized health improvement plan. Specific embodiments of this system are as follows.

[0250] First, the user collects lifestyle data using a data collection device such as a smartwatch or fitness device. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user then inputs information about their diet and medications through the device. Health status information (blood pressure, blood sugar level, cholesterol level, etc.) obtained through regular health checkups is also collected from medical devices. Next, an emotion recognition method is used to collect emotion data. This emotion recognition method detects the user's emotional state using technologies such as voice analysis, facial expression analysis, and text analysis.

[0251] The collected data is sent to a server where it is integrated. The server then cleans the raw data, fills in missing values, and eliminates outliers. The cleaned data is then stored in a centralized database and organized by user. Sentiment data is also integrated and combined with other data for analysis.

[0252] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk. This assessment includes predicting the risk of diseases such as heart disease and diabetes. It also analyzes emotional data to assess the impact of emotional states on health.

[0253] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet plan, aerobic exercise schedule, and relevant medical test recommendations. Additionally, the server suggests stress management and relaxation techniques based on the user's emotional state. For example, if the user is experiencing high stress, the server may recommend meditation, deep breathing exercises, or relaxing music.

[0254] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, undergoing recommended medical tests, and practicing suggested relaxation techniques for stress management.

[0255] The server monitors user behavioral data and changes in health status in real time and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[0256] For example, in the case of a male user in his 40s, data such as heart rate, number of steps, and sleep time are collected from the smartwatch, and information on diet and home medical medications is entered into the app. In addition, daily stress levels are monitored using emotion recognition. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan, aerobic exercise plan, and relaxation methods are proposed. The device notifies the user of the generated plan and encourages them to carry it out. The user then lives their daily life according to the proposed plan, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[0257] In this way, the present invention provides personalized health management, preventing and improving health risks. The addition of an emotion engine achieves even higher levels of personalization, contributing to the improvement of the user's overall health.

[0258] The processing flow will be explained below.

[0259] Step 1: Collect data

[0260] The device automatically collects your lifestyle data from your smartwatch or fitness device, including steps taken, heart rate, sleep time, and activity levels.

[0261] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[0262] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[0263] The device collects user emotional data using emotion recognition means, such as voice analysis, facial expression analysis, and text analysis, to detect the user's emotional state.

[0264] Step 2: Data integration and preprocessing

[0265] The server receives and integrates the data sent from the various data collection devices.

[0266] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[0267] The server stores the cleaned data in a centralized database, organized by user, and sentiment data is also aggregated and combined with other data for analysis.

[0268] Step 3: Train the predictive model

[0269] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[0270] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[0271] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[0272] Step 4: Assess health risks

[0273] The server uses a trained predictive model to assess each user's health risk.

[0274] It calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[0275] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[0276] Emotional data is also used to assess the impact of a user's emotional state on their health.

[0277] Step 5: Generate a customized health improvement plan

[0278] The server generates a customized health improvement plan for each user based on the predictive model.

[0279] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[0280] Based on your emotional state, it also suggests stress management and relaxation techniques, such as meditation, deep breathing exercises, and relaxing music for users with high stress levels.

[0281] Step 6: Communicate and execute the plan

[0282] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[0283] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[0284] The user is then expected to follow the health improvement plan and implement it in their daily lives, including making suggested dietary changes, engaging in recommended exercise, undergoing necessary medical tests, and practicing suggested relaxation techniques for stress management.

[0285] Step 7: Monitoring and feedback

[0286] The server monitors the user's behavioral data and changes in health status in real time.

[0287] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[0288] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[0289] The device collects user feedback and sends it to the server, which uses it to optimize future plans.

[0290] Step 8: Assess long-term impact and update the plan

[0291] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[0292] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[0293] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[0294] Example 2

[0295] 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."

[0296] Current health management systems provide certain advice based on a user's lifestyle and health status, but lack comprehensive data analysis, including emotional state. Furthermore, they often lack the ability to generate personalized health improvement plans using generative AI models and update them in real time, making it difficult to accurately predict health risks and propose appropriate improvement plans for each user. Furthermore, the integration and cleaning of various data, as well as the extraction of important features, are complex and inefficient.

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

[0298] In this invention, the server includes means for collecting lifestyle, health, genetic, and emotional data of users from a data collection device, means for integrating the collected data and emotional data and storing them in a centralized database, means for training a generative AI model based on the integrated data to predict each user's health risk and emotional state, means for generating a customized health improvement plan based on the predictive model and providing it to the user, and means for monitoring changes in the user's behavioral data and health state and updating the customized health improvement plan in real time, thereby enabling accurate health risk prediction for each user and the generation and real-time updating of a personalized health improvement plan that also takes into account the user's emotional state.

[0299] A "data collection device" is a device for collecting a user's lifestyle, health, genetic, and emotional data, including a smartwatch, fitness device, medical device, and emotion recognition means.

[0300] "Lifestyle data" refers to data related to the user's daily life, including the number of steps taken, heart rate, sleep time, activity level, etc.

[0301] "Health status data" refers to data relating to the user's health status, including blood pressure, blood sugar level, cholesterol level, and the like.

[0302] "Genetic characteristic data" refers to data based on a user's genetic information, including genetic risks and genetic tendencies.

[0303] "Emotional data" refers to data related to a user's emotional state, such as stress, joy, or anger, collected using technologies such as voice analysis, facial expression analysis, and text analysis.

[0304] A "generative AI model" is an artificial intelligence model that is trained on integrated data and used to predict a user's health risks and emotional state.

[0305] A "predictive model" is a model that uses a generative AI model to predict specific health risks and emotional states.

[0306] A "Health Improvement Plan" is a plan for maintaining and improving health that is customized for each user based on a generative AI model, and includes a meal plan, an exercise plan, and stress management methods based on emotional state.

[0307] A "unified database" is a centralized database for integrating, organizing, and storing various types of collected data.

[0308] "Monitoring" refers to the continuous monitoring of user behavioral data and changes in health status, and involves real-time data collection and analysis.

[0309] "Real-time updates" refers to instantly updating the generative AI model and health improvement plan based on the latest data and providing feedback to users.

[0310] The health management system of the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide an individualized health improvement plan. To implement this system, the following hardware and software are used.

[0311] First, smartwatches, fitness devices, medical devices, and emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.) are used as data collection devices. Through these devices, users collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), health status data (blood pressure, blood glucose level, cholesterol level, etc.), and emotional data. Dietary information and medication intake are manually entered using a smartphone or tablet.

[0312] Next, all collected data is sent to a server, which consolidates the data and stores it in a centralized database. During this process, the data is cleaned (missing values ​​are filled in and outliers are removed). Once the data is consolidated, it is organized for each user, and emotion data is similarly consolidated and managed centrally.

[0313] The server then trains a generative AI model based on the integrated data. This model is built using machine learning algorithms (e.g., random forest, logistic regression, etc.). It extracts important features (e.g., long-term heart rate variability, stress level, etc.) and assesses each user's health risk and emotional state. This makes it possible to predict not only the risk of diseases such as heart disease and diabetes, but also the impact of emotional state on health.

[0314] The server generates a customized health improvement plan based on the predictive model. This plan includes a low-salt diet plan, a regular aerobic exercise schedule, recommendations for relevant medical tests, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations). The health improvement plan is then sent from the server to the device (smartphone or tablet) and notified to the user. The device provides detailed instructions and sets reminders to encourage implementation.

[0315] Users follow the plan provided by the device and use their smartwatch or fitness device to collect daily data. The collected data is then sent back to the server and monitored in real time. The server uses this data to continuously update the predictive model and provides feedback if it detects any significant changes or abnormalities. This feedback may include immediate action plans or adjusted health improvement plans.

[0316] As a concrete example, consider the case of a male user in his 40s. The user uses a smartwatch to collect data such as heart rate, steps, and sleep time, and enters information about his diet and medications through a smartphone app. Periodic health checkup data (blood pressure, blood sugar levels, etc.) obtained from medical devices is also sent to the server. Daily stress levels are also monitored using emotion recognition. The server integrates this data and trains a generative AI model. Based on the predictive model, the risk of high blood pressure is assessed and a low-salt meal plan, aerobic exercise schedule, and relaxation techniques are suggested. The device notifies the user of these plans and sets reminders to encourage their implementation. The user follows the plan as they go about their daily life, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[0317] An example prompt is, "Train a generative AI model based on lifestyle and health checkup data from a man in his 40s. Use the resulting features to predict heart disease risk and high blood pressure risk and generate a personalized health plan."

[0318] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0319] Step 1:

[0320] User data collection

[0321] Users wear a smartwatch or fitness device to collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), which is automatically recorded on the device.

[0322] Users manually enter information about their diet and medications using a smartphone or tablet, which is then stored in the application.

[0323] Users obtain health status data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups from medical institutions and send it to a server.

[0324] Emotion data is collected using emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.). For example, voice analysis can detect stress levels from users' everyday conversations. This data is also automatically stored on the device.

[0325] Input: steps, heart rate, sleep time, activity level, dietary information, medications taken, health check results, emotional data

[0326] Output: Raw data stored on the device and in the application

[0327] Step 2:

[0328] Data submission and integration

[0329] Lifestyle data is automatically sent from the user's smartwatch or fitness device to a server.

[0330] Users send information about their diet and medications to the server using their smartphone or tablet.

[0331] Regular health checkup data from medical institutions is also sent to the server.

[0332] The emotion data acquired from the emotion recognition means is transmitted to the server.

[0333] Input: Raw data stored on devices and applications

[0334] Output: Consolidated data sent to the server

[0335] Step 3:

[0336] Cleaning and storing data

[0337] The server cleans the received data. Specifically, it fills in missing values ​​and eliminates outliers. For example, if one day's worth of data is missing, it fills in the missing data with the average value of past data.

[0338] The server stores the cleaned data in a centralized database, organizing it for each user, and also aggregates the emotional data.

[0339] Input: Aggregated data sent to the server

[0340] Output: Cleaned data stored in a centralized database

[0341] Step 4:

[0342] Training generative AI models and generating predictive models

[0343] The server trains a generative AI model based on the combined data, extracting important features (e.g., long-term heart rate variability and stress levels).

[0344] The server uses machine learning algorithms (e.g., random forest, logistic regression, etc.) to build predictive models that assess each user's health risk and emotional state.

[0345] Input: Cleaned data stored in a centralized database

[0346] Output: Trained generative AI model and predictive model

[0347] Step 5:

[0348] Generate a customized health improvement plan

[0349] Based on the predictive model, the server generates a customized health improvement plan, including a low-salt meal plan, an aerobic exercise regimen, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations, etc.).

[0350] Input: Trained generative and predictive AI models

[0351] Output: A customized health improvement plan

[0352] Step 6:

[0353] Plan notification and execution

[0354] The server sends the generated health improvement plan to the user's device (smartphone or tablet).

[0355] The device will then notify the user of the plan details and set reminders to help them stick to it, such as a reminder to go for a 30-minute walk at 8am.

[0356] Enter: a customized health improvement plan.

[0357] Output: Notifications and reminder settings on user devices

[0358] Step 7:

[0359] Monitoring and Feedback

[0360] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on the collected data.

[0361] If the server detects any significant changes or abnormalities, it will provide immediate feedback and notify the user of corrective measures. For example, if a sudden increase in heart rate is detected, a notification will be sent urging the user to seek medical attention.

[0362] Input: Routinely collected behavioral and health data

[0363] Output: Updated prediction model and feedback notification

[0364] Through these steps, the system can comprehensively manage the user's lifestyle and health status, and provide and implement a personalized health improvement plan.

[0365] (Application example 2)

[0366] 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."

[0367] Conventional health management systems collect data on users' lifestyles and health conditions and provide health improvement plans based on that data, but because they do not take emotional data into account, it is difficult to provide more accurate predictions of health risks or comprehensive health improvement plans that include stress management.In addition, it is not possible to suggest products in physical stores that are tailored to each user's individual health and emotional state, so there is a lack of ways to improve the shopping experience in physical stores.

[0368] 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.

[0369] In this invention, the server includes: means for collecting data on a user's lifestyle, health condition, genetic characteristics, and emotional state from a data collection device; means for integrating the collected data and storing it in a centralized database; means for training a predictive model based on the integrated data to predict each user's health risk and health condition; means for generating a customized health improvement plan based on the predictive model and providing it to the user; means for monitoring changes in the user's behavioral data and health condition and updating the customized health improvement plan in real time; and means for suggesting products in physical stores according to the user's health condition and emotional state. This enables accurate prediction of health risks and provision of a comprehensive health improvement plan, further improving the shopping experience in physical stores.

[0370] "Data collection device" means a device for collecting data on a user's lifestyle, health, genetic characteristics, and emotional state.

[0371] "Lifestyle habits" refers to a user's daily activities and behavioral patterns, sleep time, eating habits, etc.

[0372] "Health Status" refers to information about your current physical and mental health.

[0373] "Genetics" refers to the characteristics and tendencies that are based on a user's genes.

[0374] "Emotional state" refers to the user's emotional or mood state.

[0375] A "centralized database" is a database in which collected data is integrated and managed in a unified manner.

[0376] A "predictive model" is a statistical or machine learning algorithm used to predict a user's health risk or health status based on collected data.

[0377] "Health risk" refers to the likelihood that a user will develop a particular disease or health problem.

[0378] "Means for predicting health status" refers to methods and technologies for predicting a user's current and future health status based on collected data.

[0379] "Health Improvement Plan" refers to specific action plans and recommendations for users to improve their health based on predicted health risks and health conditions.

[0380] "Behavioral Data" refers to data about the actions or activities that a user actually performs.

[0381] "Real-time updating means" refers to a method or system for instantly adjusting and updating a health improvement plan in response to changes in a user's behavior or circumstances.

[0382] "Brick and mortar store" refers to a commercial establishment located in a physical location where goods or services are offered.

[0383] "Means for making product recommendations" refers to a method or system for suggesting appropriate products or services based on a user's health and emotional state.

[0384] The health management system of the present invention collects data on a user's lifestyle, health status, genetic characteristics, and emotional state, and provides a personalized health improvement plan based on this data. The system includes a data collection device, a database, a prediction model, and a physical store product suggestion means.

[0385] First, the user uses a smartwatch or fitness device to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Then, using a smartphone or medical device, health status data such as blood pressure, blood sugar, and cholesterol levels are collected. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect the user's emotional state.

[0386] This collected data is sent to a cloud server, which consolidates and cleans the data before storing it in a centralized database. The server then uses a generative AI model to train a predictive model based on the consolidated data to assess the user's health risks and health status. This assessment predicts the risk of heart disease, diabetes, and other conditions.

[0387] Based on the predicted results, the server generates a personalized health improvement plan for each user. This plan includes a low-salt diet plan, a cardiovascular exercise plan, and recommendations for regular medical checkups. It also includes stress management and relaxation techniques based on emotional data. For example, if a user is experiencing high stress, meditation or yoga may be recommended.

[0388] This customized health improvement plan is sent to the user's device, which provides detailed instructions for the plan, sets reminders to encourage implementation, and provides direct feedback to the user. The user wears the smartwatch as they go about their daily life, syncing data to a cloud server. The server monitors changes in user data in real time and updates the health improvement plan as needed.

[0389] Furthermore, this system also has a product suggestion function in physical stores. Product suggestions are made through terminals in the physical store based on the user's health and emotional state. For example, if a user is in a high-stress state, it will suggest a relaxation yoga mat or a product with a relaxing fragrance.

[0390] For example, if a male user in his 40s is predicted to be at risk of high blood pressure based on health checkup data and heart rate, step count, and other data collected from his smartwatch, a low-salt meal plan, aerobic exercise plan, and yoga to relieve stress will be recommended. If the user is determined to be in a high-stress state, products with a relaxation effect will be suggested in a physical store.

[0391] An example of a prompt sentence is as follows:

[0392] "Based on the health data of user ID 'user123', please collect the following information and generate a health improvement plan."

[0393] "Smartwatch data (steps, heart rate, sleep time)"

[0394] "Health checkup data (blood pressure, blood sugar level, cholesterol level)"

[0395] "Emotional data (current emotional state)"

[0396] This will enable users to manage their health more precisely and comprehensively, and also improve the shopping experience in physical stores.

[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0398] Step 1:

[0399] Data collection

[0400] Subject: User

[0401] How it works:

[0402] Users use smartwatches and fitness devices to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Smartphones and medical devices also collect health data such as blood pressure, blood sugar, and cholesterol levels. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect data on the user's emotional state.

[0403] Input: Lifestyle data obtained from smartwatches and fitness devices, health data from smartphones and medical devices, and emotional state data from emotion recognition means.

[0404] Output: Collected lifestyle, health, and emotion data.

[0405] Step 2:

[0406] Sending data

[0407] Subject: Terminal

[0408] How it works:

[0409] The user's device sends the various data collected in step 1 to the cloud server. This data includes lifestyle data, health data, and emotional data.

[0410] Input: Collected lifestyle, health, and emotional data stored on the device.

[0411] Output: Raw data sent to cloud server.

[0412] Step 3:

[0413] Data integration and cleaning

[0414] Subject: Server

[0415] How it works:

[0416] The server integrates the various data sent to the cloud and performs data cleaning, such as filling in missing values ​​and eliminating outliers, to generate a clean dataset, which is then stored in a centralized database.

[0417] Input: Raw data sent to the cloud server.

[0418] Output: The cleaned consolidated dataset.

[0419] Step 4:

[0420] Training a predictive model

[0421] Subject: Server

[0422] How it works:

[0423] The server trains a generative AI model based on the dataset integrated in step 3. It extracts important features from the dataset and builds a predictive model that assesses the health risks and health status of each user.

[0424] Input: The consolidated dataset after cleaning.

[0425] Output: A trained predictive model.

[0426] Step 5:

[0427] Generate a health improvement plan

[0428] Subject: Server

[0429] How it works:

[0430] The server uses the trained predictive model to predict each user's health risks and generates a customized health improvement plan, which includes a low-salt diet plan, an aerobic exercise regimen, recommendations for regular medical checkups, and stress management and relaxation techniques.

[0431] Input: A trained predictive model.

[0432] Output: A customized health improvement plan.

[0433] Step 6:

[0434] Communicating and implementing health improvement plans

[0435] Subject: Terminal

[0436] How it works:

[0437] The device notifies the user of the health improvement plan sent from the server, provides detailed instructions for the plan, and sets reminders to encourage execution. The user wears the smartwatch to record their daily activities and synchronizes the data to the cloud server.

[0438] Input: Health improvement plan sent from the server.

[0439] Output: A health improvement plan notified to the user, along with a reminder to implement it.

[0440] Step 7:

[0441] Real-time monitoring and plan updates

[0442] Subject: Server

[0443] How it works:

[0444] The server monitors the user's synchronized behavioral data and changes in health status in real time, evaluates the effectiveness of the health improvement plan based on this data, updates the plan as necessary, and provides immediate feedback to the user.

[0445] Input: Behavioral and health change data synced from users.

[0446] Output: Real-time updated health improvement plan and feedback to the user.

[0447] Step 8:

[0448] Product proposals in physical stores

[0449] Subject: Terminal (in a physical store)

[0450] How it works:

[0451] The device in the physical store will suggest products based on the user's health and emotional state. For example, if the user is under high stress, it will suggest relaxation products. This suggestion will be sent to the user's device, encouraging them to make a purchase at the physical store.

[0452] Input: User health and emotional state data.

[0453] Output: Product suggestions notified to the user.

[0454] 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.

[0455] 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.

[0456] 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.

[0457] [Second embodiment]

[0458] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0459] 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.

[0460] 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).

[0461] 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.

[0462] 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.

[0463] 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).

[0464] 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. 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.

[0465] 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.

[0466] 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.

[0467] 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.

[0468] In the smart glasses 214, 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.

[0469] 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."

[0470] The health management system according to the present invention predicts health risks for individual users and provides customized health improvement plans through the following steps.

[0471] First, users collect lifestyle data using data collection devices such as smartwatches and fitness devices. This data includes the number of steps taken, heart rate, sleep time, and activity level. Furthermore, users input information about their diet and medications through the device. Health status information (blood pressure, blood sugar, cholesterol levels, etc.) obtained through regular health checkups is also collected from medical devices.

[0472] The collected data is sent to a server where it is consolidated. The server cleans the raw data, imputes missing values, and removes outliers. The cleaned data is stored in a centralized database and organized by user.

[0473] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk, including predicting the risk of diseases such as heart disease and diabetes.

[0474] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet, a cardiovascular exercise plan, and relevant medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-fat, high-fiber diet and three days of cardiovascular exercise per week.

[0475] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, and undergoing recommended medical tests.

[0476] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[0477] For example, in the case of a female user in her 50s, data such as heart rate, number of steps, and sleep time is collected from a smartwatch, and information on diet and home medications is entered into the app. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan and aerobic exercise plan are generated and notified to the user via the device. The user then lives their daily life according to the proposed plan. The server collects and analyzes the executed data, evaluates the effectiveness of the plan, and makes adjustments as necessary.

[0478] In this way, the present invention provides health management optimized for each user, realizing the prevention and improvement of health risks.

[0479] The processing flow will be explained below.

[0480] Step 1: Collect data

[0481] The device automatically collects the user's lifestyle data (such as steps, heart rate, sleep time, and activity level) from smartwatches and fitness devices.

[0482] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[0483] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[0484] Step 2: Data integration and preprocessing

[0485] The server receives and integrates the data sent from the various data collection devices.

[0486] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[0487] The server stores the cleaned data in a centralized database, organized by user.

[0488] Step 3: Train the predictive model

[0489] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[0490] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[0491] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[0492] Step 4: Assess health risks

[0493] The server uses a trained predictive model to assess each user's health risk.

[0494] For example, it calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[0495] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[0496] Step 5: Generate a customized health improvement plan

[0497] The server generates a customized health improvement plan for each user based on the predictive model.

[0498] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[0499] Specifically, for example, users at high risk of heart disease are recommended to follow a low-fat, high-fiber diet and do aerobic exercise three times a week.

[0500] Step 6: Communicate and execute the plan

[0501] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[0502] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[0503] The user follows the health improvement plan and puts it into practice in their daily lives, specifically by changing their diet as instructed, doing the recommended exercises, and undergoing any necessary medical tests.

[0504] Step 7: Monitoring and feedback

[0505] The server monitors the user's behavioral data and changes in health status in real time.

[0506] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[0507] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[0508] Step 8: Assess long-term impact and update the plan

[0509] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[0510] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[0511] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[0512] Example 1

[0513] 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."

[0514] Conventional health management systems struggled not only to collect users' lifestyle and health data, but also to effectively integrate and analyze it. Furthermore, they lacked data cleaning and feature extraction processes to improve the accuracy of predictive models, making it impossible to provide users with appropriate health improvement plans. This made it difficult to provide health management optimized for each individual user.

[0515] 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.

[0516] In this invention, the server includes a means for filling in missing values ​​and eliminating outliers through a cleaning process, a means for applying statistical methods and machine learning algorithms to extract important features, and a means for monitoring changes in the user's behavioral data and health status and updating the customized health improvement plan in real time. This makes it possible to effectively integrate and analyze the user's lifestyle data and health data and provide an optimized health improvement plan for each individual user. The "data collection device" is a device for collecting data on the user's lifestyle, health status, and genetic characteristics.

[0517] A "centralized database" is a database in which collected data is integrated, organized, and stored.

[0518] A "predictive model" is a model generated based on the integrated data to predict the health risks and health status of each user.

[0519] "Health risks" are predicted results of diseases and health problems that a user may suffer from in the future.

[0520] A "health improvement plan" is a customized health promotion and lifestyle improvement plan generated based on a predictive model and provided to the user.

[0521] "Monitoring" is the process of monitoring user behavioral data and changes in health status in real time.

[0522] "Cleaning" is a process of organizing data to fill in missing values ​​and remove outliers.

[0523] "Features" are data elements that are extracted using statistical methods or machine learning algorithms and are considered important for training predictive models.

[0524] "Statistical methods" are statistical techniques and methodologies used in data analysis.

[0525] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and perform tasks such as prediction and classification.

[0526] "Real-time updates" is the process of adjusting and modifying your health improvement plan in immediate response to changes in your condition.

[0527] A "meal plan" is the specific meal content and frequency recommended to improve a user's health.

[0528] An "exercise plan" is the type and frequency of exercise suggested based on the user's fitness level and goals.

[0529] "Medical Test" means a professional test conducted to assess the User's health.

[0530] A "smartwatch" is a wearable device that measures and collects a user's physical activity data.

[0531] A "fitness device" is a dedicated piece of equipment used to collect a user's exercise data.

[0532] A "medical device" is a device or instrument used to collect data on a user's health status.

[0533] These definitions allow a more concrete understanding of the technical scope of the invention.

[0534] The health management system according to the present invention is configured by combining a plurality of data collection devices, terminals, and servers, which work together to manage the health of a user. Detailed embodiments of this system will be described below.

[0535] Data collection

[0536] First, the user wears a data collection device such as a smartwatch or fitness device to collect data on their daily lifestyle habits. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user also uses a device with a dedicated app installed to input data on their diet and medications. Furthermore, health condition data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups are collected from medical devices and entered into the device.

[0537] Data Integration and Cleaning

[0538] The device sends the collected data to a server in real time. The server then integrates the received data and performs a cleaning process. This cleaning process includes filling in missing values ​​and eliminating outliers. For example, if the heart rate data for a certain day is abnormally high, it is corrected to an appropriate value based on the data from before and after. This ensures the integrity and reliability of the data.

[0539] Training generative AI models

[0540] The server uses the cleaned data to train a generative AI model. Specifically, it uses Python libraries such as TensorFlow and scikit-learn to extract important features from the data and build a predictive model. This predictive model applies statistical methods and machine learning algorithms to assess each user's health risk.

[0541] Generate and deliver health improvement plans

[0542] Based on the trained predictive model, the server generates a customized health improvement plan for each user, including a low-salt diet plan, aerobic exercise plan, and relevant medical test recommendations. For example, a user at high risk of heart disease might be recommended a low-fat, high-fiber diet plan and three days of aerobic exercise per week. These plans are then sent to the user via their device, with detailed instructions and reminders.

[0543] Monitoring and real-time updates

[0544] The server monitors the user's behavioral data and changes in health status in real time. If any significant changes or abnormalities are detected, the server immediately notifies the user of countermeasures and updates the health improvement plan in real time. The user can adjust their daily life based on this feedback to maintain and improve their health.

[0545] Examples of specific examples and prompts

[0546] For example, for a female user in her 50s, the results would be as follows:

[0547] 1. The user wears a smartwatch to collect data such as heart rate, steps taken, and sleep time.

[0548] 2. Information about meals and home medical medications is entered into the terminal.

[0549] 3. The server consolidates this data and performs cleaning processing.

[0550] 4. The server predicts the risk of high blood pressure and generates a low-salt meal plan and an aerobic exercise plan.

[0551] 5. The device notifies the user of this plan.

[0552] 6. The user follows the proposed plan and continues with their daily life.

[0553] 7. The server collects and analyzes execution data, evaluates the effectiveness of the plan, and makes any necessary adjustments.

[0554] Prompt Sentence Examples

[0555] "For a female user in her 50s, please predict the risk of high blood pressure based on heart rate, steps, and sleep time data from the past week."

[0556] "Generate a customized low-sodium meal plan based on the user's dietary data."

[0557] "Please suggest an aerobic exercise plan based on the user's activity level data."

[0558] In accordance with the above aspects, the present invention provides optimized health management and preventative measures for individual users, thereby realizing reduction and improvement of health risks.

[0559] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0560] Step 1: Data collection

[0561] Users wear smartwatches or fitness devices to collect daily life data such as steps taken, heart rate, sleep time, and activity level. This data is collected in real time and transmitted to the device.

[0562] Input: Raw data from smartwatches and fitness devices

[0563] Output: Lifestyle data transferred to the device (number of steps, heart rate, sleep time, activity level, etc.)

[0564] Step 2: Enter diet and medication data

[0565] Users enter information about their diet and medication into a dedicated app, which then collects all of their lifestyle-related data.

[0566] Input: Meal and medication information manually entered by the user into a dedicated app

[0567] Output: Meal content data and medication information data stored on the device

[0568] Step 3: Health status data collection

[0569] Users input the results of their regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) into the medical device, and this data is also stored on the terminal.

[0570] Input: Numerical values ​​obtained from medical equipment for health checkup data

[0571] Output: Health status data stored on the device

[0572] Step 4: Send data

[0573] The device transmits all collected data in real time to a server via an internet connection.

[0574] Input: All user data stored on the device (lifestyle data, dietary and medication data, health status data)

[0575] Output: User data sent to the server

[0576] Step 5: Data Cleaning

[0577] The server cleans the submitted data, imputing missing values ​​and eliminating outliers, using statistical methods and algorithms in the cleaning process.

[0578] Input: All user data sent from the device

[0579] Output: Data after cleaning (missing values ​​imputed, outliers removed)

[0580] Step 6: Data Integration

[0581] The server stores the cleaned data in a centralized database and organizes it by user.

[0582] Input: User data after cleaning

[0583] Output: A consolidated database (organized by user)

[0584] Step 7: Feature extraction

[0585] The server uses statistical methods and machine learning algorithms to extract important features, such as fluctuations in heart rate and rising trends in blood pressure.

[0586] Input: Integrated database

[0587] Output: Extracted important feature data

[0588] Step 8: Training the generative AI model

[0589] The server trains a generative AI model based on the extracted features, using tools such as Python's TensorFlow.

[0590] Input: Important feature data

[0591] Output: A trained predictive model

[0592] Step 9: Health Risk Prediction

[0593] The server uses trained predictive models to assess each user's health risks, such as heart disease and diabetes risk.

[0594] Input: Trained predictive model and user data

[0595] Output: Health risk assessment for each user

[0596] Step 10: Create a Health Improvement Plan

[0597] The server generates a customized health improvement plan based on the predicted results, including specific diet and exercise plans.

[0598] Input: Health risk assessment data

[0599] Output: A customized health improvement plan

[0600] Step 11: Plan Notification

[0601] The device will notify the user of the generated health improvement plan and provide detailed instructions and reminders.

[0602] Input: Health improvement plan received from the server

[0603] Output: Health improvement plan communicated to the user

[0604] Step 12: Monitoring and Feedback

[0605] The server monitors the user's behavioral data and changes in health status in real time, and immediately notifies users of any significant changes or abnormalities and adjusts the plan based on user feedback.

[0606] Input: Real-time behavioral data and feedback

[0607] Output: Updated health improvement plan and feedback notification

[0608] (Application example 1)

[0609] 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."

[0610] In modern society, many people are exposed to health risks due to lifestyle-related diseases and stress. Conventional health management systems have difficulty effectively collecting individual users' health data and providing individually customized health improvement plans. Furthermore, they lack the means to recommend health-related products that users can use on a daily basis and to easily purchase these products. It is necessary to provide a system that solves these issues and allows users to manage their health on a daily basis.

[0611] 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.

[0612] In this invention, the server includes means for collecting data on users' lifestyle habits, health conditions, and genetic characteristics from a data collection device, means for integrating the collected data and storing it in a centralized database, means for training a prediction model generated based on the integrated data to predict each user's health risks and health conditions, means for generating a customized health improvement plan based on the prediction model and providing it to the user, means for monitoring changes in the user's behavioral data and health conditions and updating the customized health improvement plan in real time, means for suggesting health-related products suitable for the user in a virtual store, and means for the user to purchase health-related products in the virtual store. This allows for optimal health management for each user, enabling effective prevention and improvement of health risks in daily life.

[0613] A "data collection device" is a device that collects data about a user's lifestyle, health, or genetic characteristics, including a smartwatch, fitness device, or medical device.

[0614] "Integration" refers to the process of collecting different types of data and putting them into a centralized database in an easily manageable form.

[0615] A "predictive model" is a model that uses statistical methods and machine learning algorithms to predict each user's health risks and health status based on collected data.

[0616] "Customized Health Improvement Plan" means an individually optimized health maintenance and improvement plan generated based on each user's individual data and predictive models, which includes a meal plan, exercise plan, and medical test recommendations.

[0617] A "database" is a structured collection of data that is used to centrally store and manage collected data.

[0618] "Virtual store" refers to a virtual store space that users can access online to browse and purchase health-related products.

[0619] "Product Recommendation" means suggesting appropriate health-related products to a user based on the user's health risks and needs as assessed by the predictive model.

[0620] "Real-time updates" refers to the process of instantly changing and adjusting a customized health improvement plan in response to changes in a user's behavioral data and health status.

[0621] "Behavioral data" refers to data related to a user's daily activities, including the number of steps taken, heart rate, and sleep time.

[0622] "Health status" refers to data that indicates the user's physical and mental health status, including blood pressure, blood sugar levels, cholesterol levels, etc.

[0623] A health management system according to the present invention includes the following components.

[0624] First, users use data collection devices (e.g., smartwatches, fitness devices, medical equipment) to collect data about their lifestyle, health, and genetic characteristics, including steps taken, heart rate, sleep duration, blood pressure, blood sugar, and cholesterol levels.

[0625] The server then consolidates the collected data and stores it in a centralized database, where it undergoes cleaning processes such as removing outliers and imputing missing values.

[0626] The server then uses the combined data to train a generative AI model, which uses statistical methods and machine learning algorithms (e.g., TensorFlow) to predict each user's health risks and conditions, including risk of diseases such as heart disease and diabetes.

[0627] The server generates a customized health improvement plan based on the predictive model, including a meal plan, exercise schedule, and medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-sodium meal plan and three days of aerobic exercise per week.

[0628] Furthermore, the customized health improvement plan is communicated to the user via their device (e.g., smartphone, head-mounted display), where they receive detailed instructions and set reminders to follow through, such as exercising regularly or changing their diet while wearing the smartwatch.

[0629] The server monitors user behavioral data and changes in health status in real time, and uses this data to continuously update the predictive model. If it detects any significant changes or abnormalities, it provides immediate feedback and notifies the user of appropriate measures.

[0630] This also includes a means for suggesting health-related products (e.g., supplements, fitness equipment, health foods, etc.) suitable for users in a virtual store. Users can use their devices to explore the virtual store and purchase the suggested products. This allows users to obtain related products as part of a health management system optimized for each individual user.

[0631] Specific examples

[0632] For example, for a 50-year-old female user, data such as the number of steps taken, heart rate, and sleep time are collected from the smartwatch. Additionally, health checkup results such as blood pressure and blood sugar levels are integrated into the database. The server uses this data to predict the risk of high blood pressure and generate a low-salt meal plan and aerobic exercise plan. The user wears a head-mounted display and visits a virtual store, where they can purchase suggested health-related products.

[0633] Prompt Sentence Examples

[0634] Based on the user's health data, assess their health risks and suggest appropriate health products to display in a virtual store. Users can view and purchase products in 3D using an HMD.

[0635] As described above, the present invention provides health management that is optimized for each user, enabling effective prevention and improvement of health risks in daily life.

[0636] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0637] Step 1:

[0638] Users use smartwatches and fitness devices to collect data about their lifestyle and health.

[0639] Input: Data such as steps, heart rate, sleep time, blood pressure, blood sugar, and cholesterol levels.

[0640] Output: Raw data obtained from the data acquisition device.

[0641] Specifically, for example, a smartwatch measures the user's heart rate and number of steps, and transmits that data to a smartphone via Bluetooth.

[0642] Step 2:

[0643] The server consolidates the collected data and stores it in a centralized database.

[0644] Input: Data collected from smartwatches and fitness devices.

[0645] Output: Cleaned data stored in a centralized database.

[0646] Specifically, the server removes outliers and imputes missing values, and stores the formatted data in a database. For example, data cleaning is performed using libraries such as Pandas and NumPy.

[0647] Step 3:

[0648] The server trains a generative AI model based on the integrated data to predict each user's health risks and health status.

[0649] Input: The data in the cleaned database.

[0650] Output: Predictive model training results and health risk assessment.

[0651] Specifically, it uses Python and TensorFlow to run machine learning algorithms based on past data to predict each user's health risks.

[0652] Step 4:

[0653] The server generates a customized health improvement plan based on the predictive model and provides it to the user.

[0654] Input: The output data of the predictive model.

[0655] Output: A personalized health improvement plan for each user.

[0656] Specifically, for users with high health risks, the system creates a plan that includes a low-salt diet and aerobic exercise, and generates a notification.

[0657] Step 5:

[0658] A customized health improvement plan is provided via the user's device (smartphone or head-mounted display).

[0659] Enter: a customized health improvement plan.

[0660] Output: Health improvement plan details displayed on the device.

[0661] Specifically, it uses the smartphone's notification function to inform users of the plan and set reminders.

[0662] Step 6:

[0663] The user follows the provided plan in their daily life and again collects data.

[0664] Input: New data collected according to the health improvement plan.

[0665] Output: Data of the action taken.

[0666] Specifically, the user performs the suggested exercise and the data is collected by the smartwatch.

[0667] Step 7:

[0668] The server monitors user behavioral data and changes in health status in real time and updates the predictive model accordingly.

[0669] Input: Collected behavioral data again.

[0670] Output: Updated predictive model and adjusted health improvement plan.

[0671] Specifically, it retrains its AI models based on new data and adjusts health plans as needed.

[0672] Step 8:

[0673] The server proposes health-related products suitable for the user in the virtual store and provides the user with the ability to purchase the products through the terminal.

[0674] Input: The output of the predictive model and the user's health status data.

[0675] Output: Suitable health-related product suggestions displayed in a virtual store.

[0676] Specifically, we use WebGL or Unity to build a 3D virtual store and provide an interface where users can purchase suggested products. Users use a head-mounted display to explore the virtual store and purchase appropriate health products.

[0677] As described above, the system of the present invention provides optimized health management for each individual user, enabling effective prevention and improvement of health risks in daily life.

[0678] 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.

[0679] The health management system according to the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide a personalized health improvement plan. Specific embodiments of this system are as follows.

[0680] First, the user collects lifestyle data using a data collection device such as a smartwatch or fitness device. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user then inputs information about their diet and medications through the device. Health status information (blood pressure, blood sugar level, cholesterol level, etc.) obtained through regular health checkups is also collected from medical devices. Next, an emotion recognition method is used to collect emotion data. This emotion recognition method detects the user's emotional state using technologies such as voice analysis, facial expression analysis, and text analysis.

[0681] The collected data is sent to a server where it is integrated. The server then cleans the raw data, fills in missing values, and eliminates outliers. The cleaned data is then stored in a centralized database and organized by user. Sentiment data is also integrated and combined with other data for analysis.

[0682] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk. This assessment includes predicting the risk of diseases such as heart disease and diabetes. It also analyzes emotional data to assess the impact of emotional states on health.

[0683] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet plan, aerobic exercise schedule, and relevant medical test recommendations. Additionally, the server suggests stress management and relaxation techniques based on the user's emotional state. For example, if the user is experiencing high stress, the server may recommend meditation, deep breathing exercises, or relaxing music.

[0684] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, undergoing recommended medical tests, and practicing suggested relaxation techniques for stress management.

[0685] The server monitors user behavioral data and changes in health status in real time and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[0686] For example, in the case of a male user in his 40s, data such as heart rate, number of steps, and sleep time are collected from the smartwatch, and information on dietary habits and home medical medications is entered into the app. In addition, daily stress levels are monitored using emotion recognition. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan, aerobic exercise plan, and relaxation techniques are proposed. The device notifies the user of the generated plan and encourages them to carry it out. The user then lives their daily life according to the proposed plan, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[0687] In this way, the present invention provides personalized health management, preventing and improving health risks. The addition of an emotion engine achieves even higher levels of personalization, contributing to the improvement of the user's overall health.

[0688] The processing flow will be explained below.

[0689] Step 1: Collect data

[0690] The device automatically collects lifestyle data from users' smartwatches and fitness devices, including steps taken, heart rate, sleep time, and activity levels.

[0691] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[0692] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[0693] The device collects user emotional data using emotion recognition means, such as voice analysis, facial expression analysis, and text analysis, to detect the user's emotional state.

[0694] Step 2: Data integration and preprocessing

[0695] The server receives and integrates the data sent from the various data collection devices.

[0696] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[0697] The server stores the cleaned data in a centralized database, organized by user, and sentiment data is also aggregated and combined with other data for analysis.

[0698] Step 3: Train the predictive model

[0699] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[0700] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[0701] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[0702] Step 4: Assess health risks

[0703] The server uses a trained predictive model to assess each user's health risk.

[0704] It calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[0705] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[0706] Emotional data is also used to assess the impact of a user's emotional state on their health.

[0707] Step 5: Generate a customized health improvement plan

[0708] The server generates a customized health improvement plan for each user based on the predictive model.

[0709] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[0710] Based on your emotional state, it also suggests stress management and relaxation techniques, such as meditation, deep breathing exercises, and relaxing music for users with high stress levels.

[0711] Step 6: Communicate and execute the plan

[0712] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[0713] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[0714] The user is then expected to follow the health improvement plan and implement it in their daily lives, including making suggested dietary changes, engaging in recommended exercise, undergoing necessary medical tests, and practicing suggested relaxation techniques for stress management.

[0715] Step 7: Monitoring and feedback

[0716] The server monitors the user's behavioral data and changes in health status in real time.

[0717] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[0718] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[0719] The device collects user feedback and sends it to the server, which uses it to optimize future plans.

[0720] Step 8: Assess long-term impact and update the plan

[0721] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[0722] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[0723] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[0724] Example 2

[0725] 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."

[0726] Current health management systems provide certain advice based on a user's lifestyle and health status, but lack comprehensive data analysis, including emotional state. Furthermore, they often lack the ability to generate personalized health improvement plans using generative AI models and update them in real time, making it difficult to accurately predict health risks and propose appropriate improvement plans for each user. Furthermore, the integration and cleaning of various data, as well as the extraction of important features, are complex and inefficient.

[0727] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0728] In this invention, the server includes means for collecting lifestyle, health, genetic, and emotional data of users from a data collection device, means for integrating the collected data and emotional data and storing them in a centralized database, means for training a generative AI model based on the integrated data to predict each user's health risk and emotional state, means for generating a customized health improvement plan based on the predictive model and providing it to the user, and means for monitoring changes in the user's behavioral data and health state and updating the customized health improvement plan in real time, thereby enabling accurate health risk prediction for each user and the generation and real-time updating of a personalized health improvement plan that also takes into account the user's emotional state.

[0729] A "data collection device" is a device for collecting a user's lifestyle, health, genetic, and emotional data, including a smartwatch, fitness device, medical device, and emotion recognition means.

[0730] "Lifestyle data" refers to data related to the user's daily life, including the number of steps taken, heart rate, sleep time, activity level, etc.

[0731] "Health status data" refers to data relating to the user's health status, including blood pressure, blood sugar level, cholesterol level, and the like.

[0732] "Genetic characteristic data" refers to data based on a user's genetic information, including genetic risks and genetic tendencies.

[0733] "Emotional data" refers to data related to a user's emotional state, such as stress, joy, or anger, collected using technologies such as voice analysis, facial expression analysis, and text analysis.

[0734] A "generative AI model" is an artificial intelligence model that is trained on integrated data and used to predict a user's health risks and emotional state.

[0735] A "predictive model" is a model that uses a generative AI model to predict specific health risks and emotional states.

[0736] A "Health Improvement Plan" is a plan for maintaining and improving health that is customized for each user based on a generative AI model, and includes a meal plan, an exercise plan, and stress management methods based on emotional state.

[0737] A "unified database" is a centralized database for integrating, organizing, and storing various types of collected data.

[0738] "Monitoring" refers to the continuous monitoring of user behavioral data and changes in health status, and involves real-time data collection and analysis.

[0739] "Real-time updates" refers to instantly updating the generative AI model and health improvement plan based on the latest data and providing feedback to users.

[0740] The health management system of the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide an individualized health improvement plan. To implement this system, the following hardware and software are used.

[0741] First, smartwatches, fitness devices, medical devices, and emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.) are used as data collection devices. Through these devices, users collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), health status data (blood pressure, blood glucose level, cholesterol level, etc.), and emotional data. Dietary information and medication intake are manually entered using a smartphone or tablet.

[0742] Next, all collected data is sent to a server, which consolidates the data and stores it in a centralized database. During this process, the data is cleaned (missing values ​​are filled in and outliers are removed). Once the data is consolidated, it is organized for each user, and emotion data is similarly consolidated and managed centrally.

[0743] The server then trains a generative AI model based on the integrated data. This model is built using machine learning algorithms (e.g., random forest, logistic regression, etc.). It extracts important features (e.g., long-term heart rate variability, stress level, etc.) and assesses each user's health risk and emotional state. This makes it possible to predict not only the risk of diseases such as heart disease and diabetes, but also the impact of emotional state on health.

[0744] The server generates a customized health improvement plan based on the predictive model. This plan includes a low-salt diet plan, a regular aerobic exercise schedule, recommendations for relevant medical tests, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations). The health improvement plan is then sent from the server to the device (smartphone or tablet) and notified to the user. The device provides detailed instructions and sets reminders to encourage implementation.

[0745] Users follow the plan provided by the device and use their smartwatch or fitness device to collect daily data. The collected data is then sent back to the server and monitored in real time. The server uses this data to continuously update the predictive model and provides feedback if it detects any significant changes or abnormalities. This feedback may include immediate action plans or adjusted health improvement plans.

[0746] As a concrete example, consider the case of a male user in his 40s. The user uses a smartwatch to collect data such as heart rate, steps, and sleep time, and enters information about his diet and medications through a smartphone app. Periodic health checkup data (blood pressure, blood sugar levels, etc.) obtained from medical devices is also sent to the server. Daily stress levels are also monitored using emotion recognition. The server integrates this data and trains a generative AI model. Based on the predictive model, the risk of high blood pressure is assessed and a low-salt meal plan, aerobic exercise schedule, and relaxation techniques are suggested. The device notifies the user of these plans and sets reminders to encourage their implementation. The user follows the plan as they go about their daily life, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[0747] An example prompt is, "Train a generative AI model based on lifestyle and health checkup data from a man in his 40s. Use the resulting features to predict heart disease risk and high blood pressure risk and generate a personalized health plan."

[0748] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0749] Step 1:

[0750] User data collection

[0751] Users wear a smartwatch or fitness device to collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), which is automatically recorded on the device.

[0752] Users manually enter information about their diet and medications using a smartphone or tablet, which is then stored in the application.

[0753] Users obtain health status data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups from medical institutions and send it to a server.

[0754] Emotion data is collected using emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.). For example, voice analysis can detect stress levels from users' everyday conversations. This data is also automatically stored on the device.

[0755] Input: steps, heart rate, sleep time, activity level, dietary information, medications taken, health check results, emotional data

[0756] Output: Raw data stored on the device and in the application

[0757] Step 2:

[0758] Data submission and integration

[0759] Lifestyle data is automatically sent from the user's smartwatch or fitness device to a server.

[0760] Users send information about their diet and medications to the server using their smartphone or tablet.

[0761] Regular health checkup data from medical institutions is also sent to the server.

[0762] The emotion data acquired from the emotion recognition means is transmitted to the server.

[0763] Input: Raw data stored on devices and applications

[0764] Output: Consolidated data sent to the server

[0765] Step 3:

[0766] Cleaning and storing data

[0767] The server cleans the received data. Specifically, it fills in missing values ​​and eliminates outliers. For example, if one day's worth of data is missing, it fills in the missing data with the average value of past data.

[0768] The server stores the cleaned data in a centralized database, organizing it for each user, and also aggregates the emotional data.

[0769] Input: Aggregated data sent to the server

[0770] Output: Cleaned data stored in a centralized database

[0771] Step 4:

[0772] Training generative AI models and generating predictive models

[0773] The server trains a generative AI model based on the combined data, extracting important features (e.g., long-term heart rate variability and stress levels).

[0774] The server uses machine learning algorithms (e.g., random forest, logistic regression, etc.) to build predictive models that assess each user's health risk and emotional state.

[0775] Input: Cleaned data stored in a centralized database

[0776] Output: Trained generative AI model and predictive model

[0777] Step 5:

[0778] Generate a customized health improvement plan

[0779] Based on the predictive model, the server generates a customized health improvement plan, including a low-salt meal plan, an aerobic exercise regimen, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations, etc.).

[0780] Input: Trained generative and predictive AI models

[0781] Output: A customized health improvement plan

[0782] Step 6:

[0783] Plan notification and execution

[0784] The server sends the generated health improvement plan to the user's device (smartphone or tablet).

[0785] The device will then notify the user of the plan details and set reminders to help them stick to it, such as a reminder to go for a 30-minute walk at 8am.

[0786] Enter: a customized health improvement plan.

[0787] Output: Notifications and reminder settings on user devices

[0788] Step 7:

[0789] Monitoring and Feedback

[0790] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on the collected data.

[0791] If the server detects any significant changes or abnormalities, it will provide immediate feedback and notify the user of corrective measures. For example, if a sudden increase in heart rate is detected, a notification will be sent urging the user to seek medical attention.

[0792] Input: Routinely collected behavioral and health data

[0793] Output: Updated prediction model and feedback notification

[0794] Through these steps, the system can comprehensively manage the user's lifestyle and health status, and provide and implement a personalized health improvement plan.

[0795] (Application example 2)

[0796] 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."

[0797] Conventional health management systems collect data on users' lifestyles and health conditions and provide health improvement plans based on that data, but because they do not take emotional data into account, it is difficult to provide more accurate predictions of health risks or comprehensive health improvement plans that include stress management.In addition, it is not possible to suggest products in physical stores that are tailored to each user's individual health and emotional state, so there is a lack of ways to improve the shopping experience in physical stores.

[0798] 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.

[0799] In this invention, the server includes: means for collecting data on a user's lifestyle, health condition, genetic characteristics, and emotional state from a data collection device; means for integrating the collected data and storing it in a centralized database; means for training a predictive model based on the integrated data to predict each user's health risk and health condition; means for generating a customized health improvement plan based on the predictive model and providing it to the user; means for monitoring changes in the user's behavioral data and health condition and updating the customized health improvement plan in real time; and means for suggesting products in physical stores according to the user's health condition and emotional state. This enables accurate prediction of health risks and provision of a comprehensive health improvement plan, further improving the shopping experience in physical stores.

[0800] "Data collection device" means a device for collecting data on a user's lifestyle, health, genetic characteristics, and emotional state.

[0801] "Lifestyle habits" refers to a user's daily activities and behavioral patterns, sleep time, eating habits, etc.

[0802] "Health Status" refers to information about your current physical and mental health.

[0803] "Genetics" refers to the characteristics and tendencies that are based on a user's genes.

[0804] "Emotional state" refers to the user's emotional or mood state.

[0805] A "centralized database" is a database in which collected data is integrated and managed in a unified manner.

[0806] A "predictive model" is a statistical or machine learning algorithm used to predict a user's health risk or health status based on collected data.

[0807] "Health risk" refers to the likelihood that a user will develop a particular disease or health problem.

[0808] "Means for predicting health status" refers to methods and technologies for predicting a user's current and future health status based on collected data.

[0809] "Health Improvement Plan" refers to specific action plans and recommendations for users to improve their health based on predicted health risks and health conditions.

[0810] "Behavioral Data" refers to data about the actions or activities that a user actually performs.

[0811] "Real-time updating means" refers to a method or system for instantly adjusting and updating a health improvement plan in response to changes in a user's behavior or circumstances.

[0812] "Brick and mortar store" refers to a commercial establishment located in a physical location where goods or services are offered.

[0813] "Means for making product recommendations" refers to a method or system for suggesting appropriate products or services based on a user's health and emotional state.

[0814] The health management system of the present invention collects data on a user's lifestyle, health status, genetic characteristics, and emotional state, and provides a personalized health improvement plan based on this data. The system includes a data collection device, a database, a prediction model, and a physical store product suggestion means.

[0815] First, the user uses a smartwatch or fitness device to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Then, using a smartphone or medical device, health status data such as blood pressure, blood sugar, and cholesterol levels are collected. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect the user's emotional state.

[0816] This collected data is sent to a cloud server, which consolidates and cleans the data before storing it in a centralized database. The server then uses a generative AI model to train a predictive model based on the consolidated data to assess the user's health risks and health status. This assessment predicts the risk of heart disease, diabetes, and other conditions.

[0817] Based on the predicted results, the server generates a personalized health improvement plan for each user. This plan includes a low-salt diet plan, a cardiovascular exercise plan, and recommendations for regular medical checkups. It also includes stress management and relaxation techniques based on emotional data. For example, if a user is experiencing high stress, meditation or yoga may be recommended.

[0818] This customized health improvement plan is sent to the user's device, which provides detailed instructions for the plan, sets reminders to encourage implementation, and provides direct feedback to the user. The user wears the smartwatch as they go about their daily life, syncing data to a cloud server. The server monitors changes in user data in real time and updates the health improvement plan as needed.

[0819] Furthermore, this system also has a product suggestion function in physical stores. Product suggestions are made through terminals in the physical store based on the user's health and emotional state. For example, if a user is in a high-stress state, it will suggest a relaxation yoga mat or a product with a relaxing fragrance.

[0820] For example, if a male user in his 40s is predicted to be at risk of high blood pressure based on health checkup data and heart rate, step count, and other data collected from his smartwatch, a low-salt meal plan, aerobic exercise plan, and yoga to relieve stress will be recommended. If the user is determined to be in a high-stress state, products with a relaxation effect will be suggested in a physical store.

[0821] An example of a prompt sentence is as follows:

[0822] "Based on the health data of user ID 'user123', please collect the following information and generate a health improvement plan."

[0823] "Smartwatch data (steps, heart rate, sleep time)"

[0824] "Health checkup data (blood pressure, blood sugar level, cholesterol level)"

[0825] "Emotional data (current emotional state)"

[0826] This will enable users to manage their health more precisely and comprehensively, and also improve the shopping experience in physical stores.

[0827] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0828] Step 1:

[0829] Data collection

[0830] Subject: User

[0831] How it works:

[0832] Users use smartwatches and fitness devices to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Smartphones and medical devices also collect health data such as blood pressure, blood sugar, and cholesterol levels. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect data on the user's emotional state.

[0833] Input: Lifestyle data obtained from smartwatches and fitness devices, health data from smartphones and medical devices, and emotional state data from emotion recognition means.

[0834] Output: Collected lifestyle, health, and emotion data.

[0835] Step 2:

[0836] Sending data

[0837] Subject: Terminal

[0838] How it works:

[0839] The user's device sends the various data collected in step 1 to the cloud server. This data includes lifestyle data, health data, and emotional data.

[0840] Input: Collected lifestyle, health, and emotional data stored on the device.

[0841] Output: Raw data sent to cloud server.

[0842] Step 3:

[0843] Data integration and cleaning

[0844] Subject: Server

[0845] How it works:

[0846] The server integrates the various data sent to the cloud and performs data cleaning, such as filling in missing values ​​and eliminating outliers, to generate a clean dataset, which is then stored in a centralized database.

[0847] Input: Raw data sent to the cloud server.

[0848] Output: The cleaned consolidated dataset.

[0849] Step 4:

[0850] Training a predictive model

[0851] Subject: Server

[0852] How it works:

[0853] The server trains a generative AI model based on the dataset integrated in step 3. It extracts important features from the dataset and builds a predictive model that assesses the health risks and health status of each user.

[0854] Input: The consolidated dataset after cleaning.

[0855] Output: A trained predictive model.

[0856] Step 5:

[0857] Generate a health improvement plan

[0858] Subject: Server

[0859] How it works:

[0860] The server uses the trained predictive model to predict each user's health risks and generates a customized health improvement plan, which includes a low-salt diet plan, an aerobic exercise regimen, recommendations for regular medical checkups, and stress management and relaxation techniques.

[0861] Input: A trained predictive model.

[0862] Output: A customized health improvement plan.

[0863] Step 6:

[0864] Communicating and implementing health improvement plans

[0865] Subject: Terminal

[0866] How it works:

[0867] The device notifies the user of the health improvement plan sent from the server, provides detailed instructions for the plan, and sets reminders to encourage execution. The user wears the smartwatch to record their daily activities and synchronizes the data to the cloud server.

[0868] Input: Health improvement plan sent from the server.

[0869] Output: A health improvement plan notified to the user, along with a reminder to implement it.

[0870] Step 7:

[0871] Real-time monitoring and plan updates

[0872] Subject: Server

[0873] How it works:

[0874] The server monitors the user's synchronized behavioral data and changes in health status in real time, evaluates the effectiveness of the health improvement plan based on this data, updates the plan as necessary, and provides immediate feedback to the user.

[0875] Input: Behavioral and health change data synced from users.

[0876] Output: Real-time updated health improvement plan and feedback to the user.

[0877] Step 8:

[0878] Product proposals in physical stores

[0879] Subject: Terminal (in a physical store)

[0880] How it works:

[0881] The device in the physical store will suggest products based on the user's health and emotional state. For example, if the user is under high stress, it will suggest relaxation products. This suggestion will be sent to the user's device, encouraging them to make a purchase at the physical store.

[0882] Input: User health and emotional state data.

[0883] Output: Product suggestions notified to the user.

[0884] 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.

[0885] 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.

[0886] 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.

[0887] [Third embodiment]

[0888] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0889] 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.

[0890] 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).

[0891] 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.

[0892] 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.

[0893] 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).

[0894] 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. 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.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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."

[0900] The health management system according to the present invention predicts health risks for individual users and provides customized health improvement plans through the following steps.

[0901] First, users collect lifestyle data using data collection devices such as smartwatches and fitness devices. This data includes the number of steps taken, heart rate, sleep time, and activity level. Furthermore, users input information about their diet and medications through the device. Health status information (blood pressure, blood sugar, cholesterol levels, etc.) obtained through regular health checkups is also collected from medical devices.

[0902] The collected data is sent to a server where it is consolidated. The server cleans the raw data, imputes missing values, and removes outliers. The cleaned data is stored in a centralized database and organized by user.

[0903] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk, including predicting the risk of diseases such as heart disease and diabetes.

[0904] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet, a cardiovascular exercise plan, and relevant medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-fat, high-fiber diet and three days of cardiovascular exercise per week.

[0905] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, and undergoing recommended medical tests.

[0906] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[0907] For example, in the case of a female user in her 50s, data such as heart rate, number of steps, and sleep time is collected from a smartwatch, and information on diet and home medications is entered into the app. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan and aerobic exercise plan are generated and notified to the user via the device. The user then lives their daily life according to the proposed plan. The server collects and analyzes the executed data, evaluates the effectiveness of the plan, and makes adjustments as necessary.

[0908] In this way, the present invention provides health management optimized for each user, realizing the prevention and improvement of health risks.

[0909] The processing flow will be explained below.

[0910] Step 1: Collect data

[0911] The device automatically collects the user's lifestyle data (such as steps, heart rate, sleep time, and activity level) from smartwatches and fitness devices.

[0912] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[0913] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[0914] Step 2: Data integration and preprocessing

[0915] The server receives and integrates the data sent from the various data collection devices.

[0916] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[0917] The server stores the cleaned data in a centralized database, organized by user.

[0918] Step 3: Train the predictive model

[0919] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[0920] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[0921] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[0922] Step 4: Assess health risks

[0923] The server uses a trained predictive model to assess each user's health risk.

[0924] For example, it calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[0925] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[0926] Step 5: Generate a customized health improvement plan

[0927] The server generates a customized health improvement plan for each user based on the predictive model.

[0928] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[0929] Specifically, for example, users at high risk of heart disease are recommended to follow a low-fat, high-fiber diet and do aerobic exercise three times a week.

[0930] Step 6: Communicate and execute the plan

[0931] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[0932] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[0933] The user follows the health improvement plan and puts it into practice in their daily lives, specifically by changing their diet as instructed, doing the recommended exercises, and undergoing any necessary medical tests.

[0934] Step 7: Monitoring and feedback

[0935] The server monitors the user's behavioral data and changes in health status in real time.

[0936] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[0937] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[0938] Step 8: Assess long-term impact and update the plan

[0939] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[0940] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[0941] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[0942] Example 1

[0943] 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."

[0944] Conventional health management systems struggled not only to collect users' lifestyle and health data, but also to effectively integrate and analyze it. Furthermore, they lacked data cleaning and feature extraction processes to improve the accuracy of predictive models, making it impossible to provide users with appropriate health improvement plans. This made it difficult to provide health management optimized for each individual user.

[0945] 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.

[0946] In this invention, the server includes a means for filling in missing values ​​and eliminating outliers through a cleaning process, a means for applying statistical methods and machine learning algorithms to extract important features, and a means for monitoring changes in the user's behavioral data and health status and updating the customized health improvement plan in real time. This makes it possible to effectively integrate and analyze the user's lifestyle data and health data and provide an optimized health improvement plan for each individual user. The "data collection device" is a device for collecting data on the user's lifestyle, health status, and genetic characteristics.

[0947] A "centralized database" is a database in which collected data is integrated, organized, and stored.

[0948] A "predictive model" is a model generated based on the integrated data to predict the health risks and health status of each user.

[0949] "Health risks" are predicted results of diseases and health problems that a user may suffer from in the future.

[0950] A "health improvement plan" is a customized health promotion and lifestyle improvement plan generated based on a predictive model and provided to the user.

[0951] "Monitoring" is the process of monitoring user behavioral data and changes in health status in real time.

[0952] "Cleaning" is a process of organizing data to fill in missing values ​​and remove outliers.

[0953] "Features" are data elements that are extracted using statistical methods or machine learning algorithms and are considered important for training predictive models.

[0954] "Statistical methods" are statistical techniques and methodologies used in data analysis.

[0955] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and perform tasks such as prediction and classification.

[0956] "Real-time updates" is the process of adjusting and modifying your health improvement plan in immediate response to changes in your condition.

[0957] A "meal plan" is the specific meal content and frequency recommended to improve a user's health.

[0958] An "exercise plan" is the type and frequency of exercise suggested based on the user's fitness level and goals.

[0959] "Medical Test" means a professional test conducted to assess the User's health.

[0960] A "smartwatch" is a wearable device that measures and collects a user's physical activity data.

[0961] A "fitness device" is a dedicated piece of equipment used to collect a user's exercise data.

[0962] A "medical device" is a device or instrument used to collect data on a user's health status.

[0963] These definitions allow a more concrete understanding of the technical scope of the invention.

[0964] The health management system according to the present invention is configured by combining a plurality of data collection devices, terminals, and servers, which work together to manage the health of a user. Detailed embodiments of this system will be described below.

[0965] Data collection

[0966] First, the user wears a data collection device such as a smartwatch or fitness device to collect data on their daily lifestyle habits. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user also uses a device with a dedicated app installed to input data on their diet and medications. Furthermore, health condition data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups are collected from medical devices and entered into the device.

[0967] Data Integration and Cleaning

[0968] The device sends the collected data to a server in real time. The server then integrates the received data and performs a cleaning process. This cleaning process includes filling in missing values ​​and eliminating outliers. For example, if the heart rate data for a certain day is abnormally high, it is corrected to an appropriate value based on the data from before and after. This ensures the integrity and reliability of the data.

[0969] Training generative AI models

[0970] The server uses the cleaned data to train a generative AI model. Specifically, it uses Python libraries such as TensorFlow and scikit-learn to extract important features from the data and build a predictive model. This predictive model applies statistical methods and machine learning algorithms to assess each user's health risk.

[0971] Generate and deliver health improvement plans

[0972] Based on the trained predictive model, the server generates a customized health improvement plan for each user, including a low-salt diet plan, aerobic exercise plan, and relevant medical test recommendations. For example, a user at high risk of heart disease might be recommended a low-fat, high-fiber diet plan and three days of aerobic exercise per week. These plans are then sent to the user via their device, with detailed instructions and reminders.

[0973] Monitoring and real-time updates

[0974] The server monitors the user's behavioral data and changes in health status in real time. If any significant changes or abnormalities are detected, the server immediately notifies the user of countermeasures and updates the health improvement plan in real time. The user can adjust their daily life based on this feedback to maintain and improve their health.

[0975] Examples of specific examples and prompts

[0976] For example, for a female user in her 50s, the results would be as follows:

[0977] 1. The user wears a smartwatch to collect data such as heart rate, steps taken, and sleep time.

[0978] 2. Information about meals and home medical medications is entered into the terminal.

[0979] 3. The server consolidates this data and performs cleaning processing.

[0980] 4. The server predicts the risk of high blood pressure and generates a low-salt meal plan and an aerobic exercise plan.

[0981] 5. The device notifies the user of this plan.

[0982] 6. The user follows the proposed plan and continues with their daily life.

[0983] 7. The server collects and analyzes execution data, evaluates the effectiveness of the plan, and makes any necessary adjustments.

[0984] Prompt Sentence Examples

[0985] "For a female user in her 50s, please predict the risk of high blood pressure based on heart rate, steps, and sleep time data from the past week."

[0986] "Generate a customized low-sodium meal plan based on the user's dietary data."

[0987] "Please suggest an aerobic exercise plan based on the user's activity level data."

[0988] In accordance with the above aspects, the present invention provides optimized health management and preventative measures for individual users, thereby realizing reduction and improvement of health risks.

[0989] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0990] Step 1: Data collection

[0991] Users wear smartwatches or fitness devices to collect daily life data such as steps taken, heart rate, sleep time, and activity level. This data is collected in real time and transmitted to the device.

[0992] Input: Raw data from smartwatches and fitness devices

[0993] Output: Lifestyle data transferred to the device (number of steps, heart rate, sleep time, activity level, etc.)

[0994] Step 2: Enter diet and medication data

[0995] Users enter information about their diet and medication into a dedicated app, which then collects all of their lifestyle-related data.

[0996] Input: Meal and medication information manually entered by the user into a dedicated app

[0997] Output: Meal content data and medication information data stored on the device

[0998] Step 3: Health status data collection

[0999] Users input the results of their regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) into the medical device, and this data is also stored on the terminal.

[1000] Input: Numerical values ​​obtained from medical equipment for health checkup data

[1001] Output: Health status data stored on the device

[1002] Step 4: Send data

[1003] The device transmits all collected data in real time to a server via an internet connection.

[1004] Input: All user data stored on the device (lifestyle data, dietary and medication data, health status data)

[1005] Output: User data sent to the server

[1006] Step 5: Data Cleaning

[1007] The server cleans the submitted data, imputing missing values ​​and eliminating outliers, using statistical methods and algorithms in the cleaning process.

[1008] Input: All user data sent from the device

[1009] Output: Data after cleaning (missing values ​​imputed, outliers removed)

[1010] Step 6: Data Integration

[1011] The server stores the cleaned data in a centralized database and organizes it by user.

[1012] Input: User data after cleaning

[1013] Output: A consolidated database (organized by user)

[1014] Step 7: Feature extraction

[1015] The server uses statistical methods and machine learning algorithms to extract important features, such as fluctuations in heart rate and rising trends in blood pressure.

[1016] Input: Integrated database

[1017] Output: Extracted important feature data

[1018] Step 8: Training the generative AI model

[1019] The server trains a generative AI model based on the extracted features, using tools such as Python's TensorFlow.

[1020] Input: Important feature data

[1021] Output: A trained predictive model

[1022] Step 9: Health Risk Prediction

[1023] The server uses trained predictive models to assess each user's health risks, such as heart disease and diabetes risk.

[1024] Input: Trained predictive model and user data

[1025] Output: Health risk assessment for each user

[1026] Step 10: Create a Health Improvement Plan

[1027] The server generates a customized health improvement plan based on the predicted results, including specific diet and exercise plans.

[1028] Input: Health risk assessment data

[1029] Output: A customized health improvement plan

[1030] Step 11: Plan Notification

[1031] The device will notify the user of the generated health improvement plan and provide detailed instructions and reminders.

[1032] Input: Health improvement plan received from the server

[1033] Output: Health improvement plan communicated to the user

[1034] Step 12: Monitoring and Feedback

[1035] The server monitors the user's behavioral data and changes in health status in real time, and immediately notifies users of any significant changes or abnormalities and adjusts the plan based on user feedback.

[1036] Input: Real-time behavioral data and feedback

[1037] Output: Updated health improvement plan and feedback notification

[1038] (Application example 1)

[1039] 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."

[1040] In modern society, many people are exposed to health risks due to lifestyle-related diseases and stress. Conventional health management systems have difficulty effectively collecting individual users' health data and providing individually customized health improvement plans. Furthermore, they lack the means to recommend health-related products that users can use on a daily basis and to easily purchase these products. It is necessary to provide a system that solves these issues and allows users to manage their health on a daily basis.

[1041] 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.

[1042] In this invention, the server includes means for collecting data on users' lifestyle habits, health conditions, and genetic characteristics from a data collection device, means for integrating the collected data and storing it in a centralized database, means for training a prediction model generated based on the integrated data to predict each user's health risks and health conditions, means for generating a customized health improvement plan based on the prediction model and providing it to the user, means for monitoring changes in the user's behavioral data and health conditions and updating the customized health improvement plan in real time, means for suggesting health-related products suitable for the user in a virtual store, and means for the user to purchase health-related products in the virtual store. This allows for optimal health management for each user, enabling effective prevention and improvement of health risks in daily life.

[1043] A "data collection device" is a device that collects data about a user's lifestyle, health, or genetic characteristics, including a smartwatch, fitness device, or medical device.

[1044] "Integration" refers to the process of collecting different types of data and putting them into a centralized database in an easily manageable form.

[1045] A "predictive model" is a model that uses statistical methods and machine learning algorithms to predict each user's health risks and health status based on collected data.

[1046] "Customized Health Improvement Plan" means an individually optimized health maintenance and improvement plan generated based on each user's individual data and predictive models, which includes a meal plan, exercise plan, and medical test recommendations.

[1047] A "database" is a structured collection of data that is used to centrally store and manage collected data.

[1048] "Virtual store" refers to a virtual store space that users can access online to browse and purchase health-related products.

[1049] "Product Recommendation" means suggesting appropriate health-related products to a user based on the user's health risks and needs as assessed by the predictive model.

[1050] "Real-time updates" refers to the process of instantly changing and adjusting a customized health improvement plan in response to changes in a user's behavioral data and health status.

[1051] "Behavioral data" refers to data related to a user's daily activities, including the number of steps taken, heart rate, and sleep time.

[1052] "Health status" refers to data that indicates the user's physical and mental health status, including blood pressure, blood sugar levels, cholesterol levels, etc.

[1053] A health management system according to the present invention includes the following components.

[1054] First, users use data collection devices (e.g., smartwatches, fitness devices, medical equipment) to collect data about their lifestyle, health, and genetic characteristics, including steps taken, heart rate, sleep duration, blood pressure, blood sugar, and cholesterol levels.

[1055] The server then consolidates the collected data and stores it in a centralized database, where it undergoes cleaning processes such as removing outliers and imputing missing values.

[1056] The server then uses the combined data to train a generative AI model, which uses statistical methods and machine learning algorithms (e.g., TensorFlow) to predict each user's health risks and conditions, including risk of diseases such as heart disease and diabetes.

[1057] The server generates a customized health improvement plan based on the predictive model, including a meal plan, exercise schedule, and medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-sodium meal plan and three days of aerobic exercise per week.

[1058] Furthermore, the customized health improvement plan is communicated to the user via their device (e.g., smartphone, head-mounted display), where they receive detailed instructions and set reminders to follow through, such as exercising regularly or changing their diet while wearing the smartwatch.

[1059] The server monitors user behavioral data and changes in health status in real time, and uses this data to continuously update the predictive model. If it detects any significant changes or abnormalities, it provides immediate feedback and notifies the user of appropriate measures.

[1060] This also includes a means for suggesting health-related products (e.g., supplements, fitness equipment, health foods, etc.) suitable for users in a virtual store. Users can use their devices to explore the virtual store and purchase the suggested products. This allows users to obtain related products as part of a health management system optimized for each individual user.

[1061] Specific examples

[1062] For example, for a 50-year-old female user, data such as the number of steps taken, heart rate, and sleep time are collected from the smartwatch. Additionally, health checkup results such as blood pressure and blood sugar levels are integrated into the database. The server uses this data to predict the risk of high blood pressure and generate a low-salt meal plan and aerobic exercise plan. The user wears a head-mounted display and visits a virtual store, where they can purchase suggested health-related products.

[1063] Prompt Sentence Examples

[1064] Based on the user's health data, assess their health risks and suggest appropriate health products to display in a virtual store. Users can view and purchase products in 3D using an HMD.

[1065] As described above, the present invention provides health management that is optimized for each user, enabling effective prevention and improvement of health risks in daily life.

[1066] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1067] Step 1:

[1068] Users use smartwatches and fitness devices to collect data about their lifestyle and health.

[1069] Input: Data such as steps, heart rate, sleep time, blood pressure, blood sugar, and cholesterol levels.

[1070] Output: Raw data obtained from the data acquisition device.

[1071] Specifically, for example, a smartwatch measures the user's heart rate and number of steps, and transmits that data to a smartphone via Bluetooth.

[1072] Step 2:

[1073] The server consolidates the collected data and stores it in a centralized database.

[1074] Input: Data collected from smartwatches and fitness devices.

[1075] Output: Cleaned data stored in a centralized database.

[1076] Specifically, the server removes outliers and imputes missing values, and stores the formatted data in a database. For example, data cleaning is performed using libraries such as Pandas and NumPy.

[1077] Step 3:

[1078] The server trains a generative AI model based on the integrated data to predict each user's health risks and health status.

[1079] Input: The data in the cleaned database.

[1080] Output: Predictive model training results and health risk assessment.

[1081] Specifically, it uses Python and TensorFlow to run machine learning algorithms based on past data to predict each user's health risks.

[1082] Step 4:

[1083] The server generates a customized health improvement plan based on the predictive model and provides it to the user.

[1084] Input: The output data of the predictive model.

[1085] Output: A personalized health improvement plan for each user.

[1086] Specifically, for users with high health risks, the system creates a plan that includes a low-salt diet and aerobic exercise, and generates a notification.

[1087] Step 5:

[1088] A customized health improvement plan is provided via the user's device (smartphone or head-mounted display).

[1089] Enter: a customized health improvement plan.

[1090] Output: Health improvement plan details displayed on the device.

[1091] Specifically, it uses the smartphone's notification function to inform users of the plan and set reminders.

[1092] Step 6:

[1093] The user follows the provided plan in their daily life and again collects data.

[1094] Input: New data collected according to the health improvement plan.

[1095] Output: Data of the action taken.

[1096] Specifically, the user performs the suggested exercise and the data is collected by the smartwatch.

[1097] Step 7:

[1098] The server monitors user behavioral data and changes in health status in real time and updates the predictive model accordingly.

[1099] Input: Collected behavioral data again.

[1100] Output: Updated predictive model and adjusted health improvement plan.

[1101] Specifically, it retrains its AI models based on new data and adjusts health plans as needed.

[1102] Step 8:

[1103] The server proposes health-related products suitable for the user in the virtual store and provides the user with the ability to purchase the products through the terminal.

[1104] Input: The output of the predictive model and the user's health status data.

[1105] Output: Suitable health-related product suggestions displayed in a virtual store.

[1106] Specifically, we use WebGL or Unity to build a 3D virtual store and provide an interface where users can purchase suggested products. Users use a head-mounted display to explore the virtual store and purchase appropriate health products.

[1107] As described above, the system of the present invention provides optimized health management for each individual user, enabling effective prevention and improvement of health risks in daily life.

[1108] 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.

[1109] The health management system according to the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide a personalized health improvement plan. Specific embodiments of this system are as follows.

[1110] First, the user collects lifestyle data using a data collection device such as a smartwatch or fitness device. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user then inputs information about their diet and medications through the device. Health status information (blood pressure, blood sugar level, cholesterol level, etc.) obtained through regular health checkups is also collected from medical devices. Next, an emotion recognition method is used to collect emotion data. This emotion recognition method detects the user's emotional state using technologies such as voice analysis, facial expression analysis, and text analysis.

[1111] The collected data is sent to a server where it is integrated. The server then cleans the raw data, fills in missing values, and eliminates outliers. The cleaned data is then stored in a centralized database and organized by user. Sentiment data is also integrated and combined with other data for analysis.

[1112] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk. This assessment includes predicting the risk of diseases such as heart disease and diabetes. It also analyzes emotional data to assess the impact of emotional states on health.

[1113] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet plan, aerobic exercise schedule, and relevant medical test recommendations. Additionally, the server suggests stress management and relaxation techniques based on the user's emotional state. For example, if the user is experiencing high stress, the server may recommend meditation, deep breathing exercises, or relaxing music.

[1114] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, undergoing recommended medical tests, and practicing suggested relaxation techniques for stress management.

[1115] The server monitors user behavioral data and changes in health status in real time and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[1116] For example, in the case of a male user in his 40s, data such as heart rate, number of steps, and sleep time are collected from the smartwatch, and information on dietary habits and home medical medications is entered into the app. In addition, daily stress levels are monitored using emotion recognition. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan, aerobic exercise plan, and relaxation techniques are proposed. The device notifies the user of the generated plan and encourages them to carry it out. The user then lives their daily life according to the proposed plan, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[1117] In this way, the present invention provides personalized health management, preventing and improving health risks. The addition of an emotion engine achieves even higher levels of personalization, contributing to the improvement of the user's overall health.

[1118] The processing flow will be explained below.

[1119] Step 1: Collect data

[1120] The device automatically collects lifestyle data from users' smartwatches and fitness devices, including steps taken, heart rate, sleep time, and activity levels.

[1121] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[1122] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[1123] The device collects user emotional data using emotion recognition means, such as voice analysis, facial expression analysis, and text analysis, to detect the user's emotional state.

[1124] Step 2: Data integration and preprocessing

[1125] The server receives and integrates the data sent from the various data collection devices.

[1126] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[1127] The server stores the cleaned data in a centralized database, organized by user, and sentiment data is also aggregated and combined with other data for analysis.

[1128] Step 3: Train the predictive model

[1129] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[1130] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[1131] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[1132] Step 4: Assess health risks

[1133] The server uses a trained predictive model to assess each user's health risk.

[1134] It calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[1135] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[1136] Emotional data is also used to assess the impact of a user's emotional state on their health.

[1137] Step 5: Generate a customized health improvement plan

[1138] The server generates a customized health improvement plan for each user based on the predictive model.

[1139] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[1140] Based on your emotional state, it also suggests stress management and relaxation techniques, such as meditation, deep breathing exercises, and relaxing music for users with high stress levels.

[1141] Step 6: Communicate and execute the plan

[1142] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[1143] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[1144] The user is then expected to follow the health improvement plan and implement it in their daily lives, including making suggested dietary changes, engaging in recommended exercise, undergoing necessary medical tests, and practicing suggested relaxation techniques for stress management.

[1145] Step 7: Monitoring and feedback

[1146] The server monitors the user's behavioral data and changes in health status in real time.

[1147] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[1148] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[1149] The device collects user feedback and sends it to the server, which uses it to optimize future plans.

[1150] Step 8: Assess long-term impact and update the plan

[1151] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[1152] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[1153] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[1154] Example 2

[1155] 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."

[1156] Current health management systems provide certain advice based on a user's lifestyle and health status, but lack comprehensive data analysis, including emotional state. Furthermore, they often lack the ability to generate personalized health improvement plans using generative AI models and update them in real time, making it difficult to accurately predict health risks and propose appropriate improvement plans for each user. Furthermore, the integration and cleaning of various data, as well as the extraction of important features, are complex and inefficient.

[1157] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1158] In this invention, the server includes means for collecting lifestyle, health, genetic, and emotional data of users from a data collection device, means for integrating the collected data and emotional data and storing them in a centralized database, means for training a generative AI model based on the integrated data to predict each user's health risk and emotional state, means for generating a customized health improvement plan based on the predictive model and providing it to the user, and means for monitoring changes in the user's behavioral data and health state and updating the customized health improvement plan in real time, thereby enabling accurate health risk prediction for each user and the generation and real-time updating of a personalized health improvement plan that also takes into account the user's emotional state.

[1159] A "data collection device" is a device for collecting a user's lifestyle, health, genetic, and emotional data, including a smartwatch, fitness device, medical device, and emotion recognition means.

[1160] "Lifestyle data" refers to data related to the user's daily life, including the number of steps taken, heart rate, sleep time, activity level, etc.

[1161] "Health status data" refers to data relating to the user's health status, including blood pressure, blood sugar level, cholesterol level, and the like.

[1162] "Genetic characteristic data" refers to data based on a user's genetic information, including genetic risks and genetic tendencies.

[1163] "Emotional data" refers to data related to a user's emotional state, such as stress, joy, or anger, collected using technologies such as voice analysis, facial expression analysis, and text analysis.

[1164] A "generative AI model" is an artificial intelligence model that is trained on integrated data and used to predict a user's health risks and emotional state.

[1165] A "predictive model" is a model that uses a generative AI model to predict specific health risks and emotional states.

[1166] A "Health Improvement Plan" is a plan for maintaining and improving health that is customized for each user based on a generative AI model, and includes a meal plan, an exercise plan, and stress management methods based on emotional state.

[1167] A "unified database" is a centralized database for integrating, organizing, and storing various types of collected data.

[1168] "Monitoring" refers to the continuous monitoring of user behavioral data and changes in health status, and involves real-time data collection and analysis.

[1169] "Real-time updates" refers to instantly updating the generative AI model and health improvement plan based on the latest data and providing feedback to users.

[1170] The health management system of the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide a personalized health improvement plan. To implement this system, the following hardware and software are used.

[1171] First, smartwatches, fitness devices, medical devices, and emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.) are used as data collection devices. Through these devices, users collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), health status data (blood pressure, blood glucose level, cholesterol level, etc.), and emotional data. Dietary information and medication intake are manually entered using a smartphone or tablet.

[1172] Next, all collected data is sent to a server, which consolidates the data and stores it in a centralized database. During this process, the data is cleaned (missing values ​​are filled in and outliers are removed). Once the data is consolidated, it is organized for each user, and emotion data is similarly consolidated and managed centrally.

[1173] The server then trains a generative AI model based on the integrated data. This model is built using machine learning algorithms (e.g., random forest, logistic regression, etc.). It extracts important features (e.g., long-term heart rate variability, stress level, etc.) and assesses each user's health risk and emotional state. This makes it possible to predict not only the risk of diseases such as heart disease and diabetes, but also the impact of emotional state on health.

[1174] The server generates a customized health improvement plan based on the predictive model. This plan includes a low-salt diet plan, a regular aerobic exercise schedule, recommendations for relevant medical tests, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations). The health improvement plan is then sent from the server to the device (smartphone or tablet) and notified to the user. The device provides detailed instructions and sets reminders to encourage implementation.

[1175] Users follow the plan provided by the device and use their smartwatch or fitness device to collect daily data. The collected data is then sent back to the server and monitored in real time. The server uses this data to continuously update the predictive model and provides feedback if it detects any significant changes or abnormalities. This feedback may include immediate action plans or adjusted health improvement plans.

[1176] As a concrete example, consider the case of a male user in his 40s. The user uses a smartwatch to collect data such as heart rate, steps, and sleep time, and enters information about his diet and medications through a smartphone app. Periodic health checkup data (blood pressure, blood sugar levels, etc.) obtained from medical devices is also sent to the server. Daily stress levels are also monitored using emotion recognition. The server integrates this data and trains a generative AI model. Based on the predictive model, the risk of high blood pressure is assessed and a low-salt meal plan, aerobic exercise schedule, and relaxation techniques are suggested. The device notifies the user of these plans and sets reminders to encourage their implementation. The user follows the plan as they go about their daily life, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[1177] An example prompt is, "Train a generative AI model based on lifestyle and health checkup data from a man in his 40s. Use the resulting features to predict heart disease risk and high blood pressure risk and generate a personalized health plan."

[1178] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1179] Step 1:

[1180] User data collection

[1181] Users wear a smartwatch or fitness device to collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), which is automatically recorded on the device.

[1182] Users manually enter information about their diet and medications using a smartphone or tablet, which is then stored in the application.

[1183] Users obtain health status data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups from medical institutions and send it to a server.

[1184] Emotion data is collected using emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.). For example, voice analysis can detect stress levels from users' everyday conversations. This data is also automatically stored on the device.

[1185] Input: steps, heart rate, sleep time, activity level, dietary information, medications taken, health check results, emotional data

[1186] Output: Raw data stored on the device and in the application

[1187] Step 2:

[1188] Data submission and integration

[1189] Lifestyle data is automatically sent from the user's smartwatch or fitness device to a server.

[1190] Users send information about their diet and medications to the server using their smartphone or tablet.

[1191] Regular health checkup data from medical institutions is also sent to the server.

[1192] The emotion data acquired from the emotion recognition means is transmitted to the server.

[1193] Input: Raw data stored on devices and applications

[1194] Output: Consolidated data sent to the server

[1195] Step 3:

[1196] Cleaning and storing data

[1197] The server cleans the received data. Specifically, it fills in missing values ​​and eliminates outliers. For example, if one day's worth of data is missing, it fills in the missing data with the average value of past data.

[1198] The server stores the cleaned data in a centralized database, organizing it for each user, and also aggregates the emotional data.

[1199] Input: Aggregated data sent to the server

[1200] Output: Cleaned data stored in a centralized database

[1201] Step 4:

[1202] Training generative AI models and generating predictive models

[1203] The server trains a generative AI model based on the combined data, extracting important features (e.g., long-term heart rate variability and stress levels).

[1204] The server uses machine learning algorithms (e.g., random forest, logistic regression, etc.) to build predictive models that assess each user's health risk and emotional state.

[1205] Input: Cleaned data stored in a centralized database

[1206] Output: Trained generative AI model and predictive model

[1207] Step 5:

[1208] Generate a customized health improvement plan

[1209] Based on the predictive model, the server generates a customized health improvement plan, including a low-salt meal plan, an aerobic exercise regimen, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations, etc.).

[1210] Input: Trained generative and predictive AI models

[1211] Output: A customized health improvement plan

[1212] Step 6:

[1213] Plan notification and execution

[1214] The server sends the generated health improvement plan to the user's device (smartphone or tablet).

[1215] The device will then notify the user of the plan details and set reminders to help them stick to it, such as a reminder to go for a 30-minute walk at 8am.

[1216] Enter: a customized health improvement plan.

[1217] Output: Notifications and reminder settings on user devices

[1218] Step 7:

[1219] Monitoring and Feedback

[1220] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on the collected data.

[1221] If the server detects any significant changes or abnormalities, it will provide immediate feedback and notify the user of corrective measures. For example, if a sudden increase in heart rate is detected, a notification will be sent urging the user to seek medical attention.

[1222] Input: Routinely collected behavioral and health data

[1223] Output: Updated prediction model and feedback notification

[1224] Through these steps, the system can comprehensively manage the user's lifestyle and health status, and provide and implement a personalized health improvement plan.

[1225] (Application example 2)

[1226] 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."

[1227] Conventional health management systems collect data on users' lifestyles and health conditions and provide health improvement plans based on that data, but because they do not take emotional data into account, it is difficult to provide more accurate predictions of health risks or comprehensive health improvement plans that include stress management.In addition, it is not possible to suggest products in physical stores that are tailored to each user's individual health and emotional state, so there is a lack of ways to improve the shopping experience in physical stores.

[1228] 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.

[1229] In this invention, the server includes: means for collecting data on a user's lifestyle, health condition, genetic characteristics, and emotional state from a data collection device; means for integrating the collected data and storing it in a centralized database; means for training a predictive model based on the integrated data to predict each user's health risk and health condition; means for generating a customized health improvement plan based on the predictive model and providing it to the user; means for monitoring changes in the user's behavioral data and health condition and updating the customized health improvement plan in real time; and means for suggesting products in physical stores according to the user's health condition and emotional state. This enables accurate prediction of health risks and provision of a comprehensive health improvement plan, further improving the shopping experience in physical stores.

[1230] "Data collection device" means a device for collecting data on a user's lifestyle, health, genetic characteristics, and emotional state.

[1231] "Lifestyle habits" refers to a user's daily activities and behavioral patterns, sleep time, eating habits, etc.

[1232] "Health Status" refers to information about your current physical and mental health.

[1233] "Genetics" refers to the characteristics and tendencies that are based on a user's genes.

[1234] "Emotional state" refers to the user's emotional or mood state.

[1235] A "centralized database" is a database in which collected data is integrated and managed in a unified manner.

[1236] A "predictive model" is a statistical or machine learning algorithm used to predict a user's health risk or health status based on collected data.

[1237] "Health risk" refers to the likelihood that a user will develop a particular disease or health problem.

[1238] "Means for predicting health status" refers to methods and technologies for predicting a user's current and future health status based on collected data.

[1239] "Health Improvement Plan" refers to specific action plans and recommendations for users to improve their health based on predicted health risks and health conditions.

[1240] "Behavioral Data" refers to data about the actions or activities that a user actually performs.

[1241] "Real-time updating means" refers to a method or system for instantly adjusting and updating a health improvement plan in response to changes in a user's behavior or circumstances.

[1242] "Brick and mortar store" refers to a commercial establishment located in a physical location where goods or services are offered.

[1243] "Means for making product recommendations" refers to a method or system for suggesting appropriate products or services based on a user's health and emotional state.

[1244] The health management system of the present invention collects data on a user's lifestyle, health status, genetic characteristics, and emotional state, and provides a personalized health improvement plan based on this data. The system includes a data collection device, a database, a prediction model, and a physical store product suggestion means.

[1245] First, the user uses a smartwatch or fitness device to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Then, using a smartphone or medical device, health status data such as blood pressure, blood sugar, and cholesterol levels are collected. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect the user's emotional state.

[1246] This collected data is sent to a cloud server, which consolidates and cleans the data before storing it in a centralized database. The server then uses a generative AI model to train a predictive model based on the consolidated data to assess the user's health risks and health status. This assessment predicts the risk of heart disease, diabetes, and other conditions.

[1247] Based on the predicted results, the server generates a personalized health improvement plan for each user. This plan includes a low-salt diet plan, a cardiovascular exercise plan, and recommendations for regular medical checkups. It also includes stress management and relaxation techniques based on emotional data. For example, if a user is experiencing high stress, meditation or yoga may be recommended.

[1248] This customized health improvement plan is sent to the user's device, which provides detailed instructions for the plan, sets reminders to encourage implementation, and provides direct feedback to the user. The user wears the smartwatch as they go about their daily life, syncing data to a cloud server. The server monitors changes in user data in real time and updates the health improvement plan as needed.

[1249] Furthermore, this system also has a product suggestion function in physical stores. Product suggestions are made through terminals in the physical store based on the user's health and emotional state. For example, if a user is in a high-stress state, it will suggest a relaxation yoga mat or a product with a relaxing fragrance.

[1250] For example, if a male user in his 40s is predicted to be at risk of high blood pressure based on health checkup data and heart rate, step count, and other data collected from his smartwatch, a low-salt meal plan, aerobic exercise plan, and yoga to relieve stress will be recommended. If the user is determined to be in a high-stress state, products with a relaxation effect will be suggested in a physical store.

[1251] An example of a prompt sentence is as follows:

[1252] "Based on the health data of user ID 'user123', please collect the following information and generate a health improvement plan."

[1253] "Smartwatch data (steps, heart rate, sleep time)"

[1254] "Health checkup data (blood pressure, blood sugar level, cholesterol level)"

[1255] "Emotional data (current emotional state)"

[1256] This will enable users to manage their health more precisely and comprehensively, and also improve the shopping experience in physical stores.

[1257] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1258] Step 1:

[1259] Data collection

[1260] Subject: User

[1261] How it works:

[1262] Users use smartwatches and fitness devices to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Smartphones and medical devices also collect health data such as blood pressure, blood sugar, and cholesterol levels. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect data on the user's emotional state.

[1263] Input: Lifestyle data obtained from smartwatches and fitness devices, health data from smartphones and medical devices, and emotional state data from emotion recognition means.

[1264] Output: Collected lifestyle, health, and emotion data.

[1265] Step 2:

[1266] Sending data

[1267] Subject: Terminal

[1268] How it works:

[1269] The user's device sends the various data collected in step 1 to the cloud server. This data includes lifestyle data, health data, and emotional data.

[1270] Input: Collected lifestyle, health, and emotional data stored on the device.

[1271] Output: Raw data sent to cloud server.

[1272] Step 3:

[1273] Data integration and cleaning

[1274] Subject: Server

[1275] How it works:

[1276] The server integrates the various data sent to the cloud and performs data cleaning, such as filling in missing values ​​and eliminating outliers, to generate a clean dataset, which is then stored in a centralized database.

[1277] Input: Raw data sent to the cloud server.

[1278] Output: The cleaned consolidated dataset.

[1279] Step 4:

[1280] Training a predictive model

[1281] Subject: Server

[1282] How it works:

[1283] The server trains a generative AI model based on the dataset integrated in step 3. It extracts important features from the dataset and builds a predictive model that assesses the health risks and health status of each user.

[1284] Input: The consolidated dataset after cleaning.

[1285] Output: A trained predictive model.

[1286] Step 5:

[1287] Generate a health improvement plan

[1288] Subject: Server

[1289] How it works:

[1290] The server uses the trained predictive model to predict each user's health risks and generates a customized health improvement plan, which includes a low-salt diet plan, an aerobic exercise regimen, recommendations for regular medical checkups, and stress management and relaxation techniques.

[1291] Input: A trained predictive model.

[1292] Output: A customized health improvement plan.

[1293] Step 6:

[1294] Communicating and implementing health improvement plans

[1295] Subject: Terminal

[1296] How it works:

[1297] The device notifies the user of the health improvement plan sent from the server, provides detailed instructions for the plan, and sets reminders to encourage execution. The user wears the smartwatch to record their daily activities and synchronizes the data to the cloud server.

[1298] Input: Health improvement plan sent from the server.

[1299] Output: A health improvement plan notified to the user, along with a reminder to implement it.

[1300] Step 7:

[1301] Real-time monitoring and plan updates

[1302] Subject: Server

[1303] How it works:

[1304] The server monitors the user's synchronized behavioral data and changes in health status in real time, evaluates the effectiveness of the health improvement plan based on this data, updates the plan as necessary, and provides immediate feedback to the user.

[1305] Input: Behavioral and health change data synced from users.

[1306] Output: Real-time updated health improvement plan and feedback to the user.

[1307] Step 8:

[1308] Product proposals in physical stores

[1309] Subject: Terminal (in a physical store)

[1310] How it works:

[1311] The device in the physical store will suggest products based on the user's health and emotional state. For example, if the user is under high stress, it will suggest relaxation products. This suggestion will be sent to the user's device, encouraging them to make a purchase at the physical store.

[1312] Input: User health and emotional state data.

[1313] Output: Product suggestions notified to the user.

[1314] 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.

[1315] 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.

[1316] 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.

[1317] [Fourth embodiment]

[1318] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1319] 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.

[1320] 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).

[1321] 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.

[1322] 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.

[1323] 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).

[1324] 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. 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.

[1325] 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.

[1326] 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.

[1327] 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.

[1328] 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.

[1329] 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.

[1330] 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."

[1331] The health management system according to the present invention predicts health risks for individual users and provides customized health improvement plans through the following steps.

[1332] First, users collect lifestyle data using data collection devices such as smartwatches and fitness devices. This data includes the number of steps taken, heart rate, sleep time, and activity level. Furthermore, users input information about their diet and medications through the device. Health status information (blood pressure, blood sugar, cholesterol levels, etc.) obtained through regular health checkups is also collected from medical devices.

[1333] The collected data is sent to a server where it is consolidated. The server cleans the raw data, imputes missing values, and removes outliers. The cleaned data is stored in a centralized database and organized by user.

[1334] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk, including predicting the risk of diseases such as heart disease and diabetes.

[1335] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet, a cardiovascular exercise plan, and relevant medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-fat, high-fiber diet and three days of cardiovascular exercise per week.

[1336] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, and undergoing recommended medical tests.

[1337] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[1338] For example, in the case of a female user in her 50s, data such as heart rate, number of steps, and sleep time is collected from a smartwatch, and information on diet and home medications is entered into the app. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan and aerobic exercise plan are generated and notified to the user via the device. The user then lives their daily life according to the proposed plan. The server collects and analyzes the executed data, evaluates the effectiveness of the plan, and makes adjustments as necessary.

[1339] In this way, the present invention provides health management optimized for each user, realizing the prevention and improvement of health risks.

[1340] The processing flow will be explained below.

[1341] Step 1: Collect data

[1342] The device automatically collects the user's lifestyle data (such as steps, heart rate, sleep time, and activity level) from smartwatches and fitness devices.

[1343] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[1344] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[1345] Step 2: Data integration and preprocessing

[1346] The server receives and integrates the data sent from the various data collection devices.

[1347] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[1348] The server stores the cleaned data in a centralized database, organized by user.

[1349] Step 3: Train the predictive model

[1350] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[1351] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[1352] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[1353] Step 4: Assess health risks

[1354] The server uses a trained predictive model to assess each user's health risk.

[1355] For example, it calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[1356] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[1357] Step 5: Generate a customized health improvement plan

[1358] The server generates a customized health improvement plan for each user based on the predictive model.

[1359] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[1360] Specifically, for example, users at high risk of heart disease are recommended to follow a low-fat, high-fiber diet and do aerobic exercise three times a week.

[1361] Step 6: Communicate and execute the plan

[1362] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[1363] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[1364] The user follows the health improvement plan and puts it into practice in their daily lives, specifically by changing their diet as instructed, doing the recommended exercises, and undergoing any necessary medical tests.

[1365] Step 7: Monitoring and feedback

[1366] The server monitors the user's behavioral data and changes in health status in real time.

[1367] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[1368] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[1369] Step 8: Assess long-term impact and update the plan

[1370] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[1371] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[1372] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[1373] Example 1

[1374] 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."

[1375] Conventional health management systems struggled not only to collect users' lifestyle and health data, but also to effectively integrate and analyze it. Furthermore, they lacked data cleaning and feature extraction processes to improve the accuracy of predictive models, making it impossible to provide users with appropriate health improvement plans. This made it difficult to provide health management optimized for each individual user.

[1376] 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.

[1377] In this invention, the server includes a means for filling in missing values ​​and eliminating outliers through a cleaning process, a means for applying statistical methods and machine learning algorithms to extract important features, and a means for monitoring changes in the user's behavioral data and health status and updating the customized health improvement plan in real time. This makes it possible to effectively integrate and analyze the user's lifestyle data and health data and provide an optimized health improvement plan for each individual user. The "data collection device" is a device for collecting data on the user's lifestyle, health status, and genetic characteristics.

[1378] A "centralized database" is a database in which collected data is integrated, organized, and stored.

[1379] A "predictive model" is a model generated based on the integrated data to predict the health risks and health status of each user.

[1380] "Health risks" are predicted results of diseases and health problems that a user may suffer from in the future.

[1381] A "health improvement plan" is a customized health promotion and lifestyle improvement plan generated based on a predictive model and provided to the user.

[1382] "Monitoring" is the process of monitoring user behavioral data and changes in health status in real time.

[1383] "Cleaning" is a process of organizing data to fill in missing values ​​and remove outliers.

[1384] "Features" are data elements that are extracted using statistical methods or machine learning algorithms and are considered important for training predictive models.

[1385] "Statistical methods" are statistical techniques and methodologies used in data analysis.

[1386] A "machine learning algorithm" is an algorithm that allows a computer to learn from data and perform tasks such as prediction and classification.

[1387] "Real-time updates" is the process of adjusting and modifying your health improvement plan in immediate response to changes in your condition.

[1388] A "meal plan" is the specific meal content and frequency recommended to improve a user's health.

[1389] An "exercise plan" is the type and frequency of exercise suggested based on the user's fitness level and goals.

[1390] "Medical Test" means a professional test conducted to assess the User's health.

[1391] A "smartwatch" is a wearable device that measures and collects a user's physical activity data.

[1392] A "fitness device" is a dedicated piece of equipment used to collect a user's exercise data.

[1393] A "medical device" is a device or instrument used to collect data on a user's health status.

[1394] These definitions allow a more concrete understanding of the technical scope of the invention.

[1395] The health management system according to the present invention is configured by combining a plurality of data collection devices, terminals, and servers, which work together to manage the health of a user. Detailed embodiments of this system will be described below.

[1396] Data collection

[1397] First, the user wears a data collection device such as a smartwatch or fitness device to collect data on their daily lifestyle habits. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user also uses a device with a dedicated app installed to input data on their diet and medications. Furthermore, health condition data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups are collected from medical devices and entered into the device.

[1398] Data Integration and Cleaning

[1399] The device sends the collected data to a server in real time. The server then integrates the received data and performs a cleaning process. This cleaning process includes filling in missing values ​​and eliminating outliers. For example, if the heart rate data for a certain day is abnormally high, it is corrected to an appropriate value based on the data from before and after. This ensures the integrity and reliability of the data.

[1400] Training generative AI models

[1401] The server uses the cleaned data to train a generative AI model. Specifically, it uses Python libraries such as TensorFlow and scikit-learn to extract important features from the data and build a predictive model. This predictive model applies statistical methods and machine learning algorithms to assess each user's health risk.

[1402] Generate and deliver health improvement plans

[1403] Based on the trained predictive model, the server generates a customized health improvement plan for each user, including a low-salt diet plan, aerobic exercise plan, and relevant medical test recommendations. For example, a user at high risk of heart disease might be recommended a low-fat, high-fiber diet plan and three days of aerobic exercise per week. These plans are then sent to the user via their device, with detailed instructions and reminders.

[1404] Monitoring and real-time updates

[1405] The server monitors the user's behavioral data and changes in health status in real time. If any significant changes or abnormalities are detected, the server immediately notifies the user of countermeasures and updates the health improvement plan in real time. The user can adjust their daily life based on this feedback to maintain and improve their health.

[1406] Examples of specific examples and prompts

[1407] For example, for a female user in her 50s, the results would be as follows:

[1408] 1. The user wears a smartwatch to collect data such as heart rate, steps taken, and sleep time.

[1409] 2. Information about meals and home medical medications is entered into the terminal.

[1410] 3. The server consolidates this data and performs cleaning processing.

[1411] 4. The server predicts the risk of high blood pressure and generates a low-salt meal plan and an aerobic exercise plan.

[1412] 5. The device notifies the user of this plan.

[1413] 6. The user follows the proposed plan and continues with their daily life.

[1414] 7. The server collects and analyzes execution data, evaluates the effectiveness of the plan, and makes any necessary adjustments.

[1415] Prompt Sentence Examples

[1416] "For a female user in her 50s, please predict the risk of high blood pressure based on heart rate, steps, and sleep time data from the past week."

[1417] "Generate a customized low-sodium meal plan based on the user's dietary data."

[1418] "Please suggest an aerobic exercise plan based on the user's activity level data."

[1419] In accordance with the above aspects, the present invention provides optimized health management and preventative measures for individual users, thereby realizing reduction and improvement of health risks.

[1420] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1421] Step 1: Data collection

[1422] Users wear smartwatches or fitness devices to collect daily life data such as steps taken, heart rate, sleep time, and activity level. This data is collected in real time and transmitted to the device.

[1423] Input: Raw data from smartwatches and fitness devices

[1424] Output: Lifestyle data transferred to the device (number of steps, heart rate, sleep time, activity level, etc.)

[1425] Step 2: Enter diet and medication data

[1426] Users enter information about their diet and medication into a dedicated app, which then collects all of their lifestyle-related data.

[1427] Input: Meal and medication information manually entered by the user into a dedicated app

[1428] Output: Meal content data and medication information data stored on the device

[1429] Step 3: Health status data collection

[1430] Users input the results of their regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) into the medical device, and this data is also stored on the terminal.

[1431] Input: Numerical values ​​obtained from medical equipment for health checkup data

[1432] Output: Health status data stored on the device

[1433] Step 4: Send data

[1434] The device transmits all collected data in real time to a server via an internet connection.

[1435] Input: All user data stored on the device (lifestyle data, dietary and medication data, health status data)

[1436] Output: User data sent to the server

[1437] Step 5: Data Cleaning

[1438] The server cleans the submitted data, imputing missing values ​​and eliminating outliers, using statistical methods and algorithms in the cleaning process.

[1439] Input: All user data sent from the device

[1440] Output: Data after cleaning (missing values ​​imputed, outliers removed)

[1441] Step 6: Data Integration

[1442] The server stores the cleaned data in a centralized database and organizes it by user.

[1443] Input: User data after cleaning

[1444] Output: A consolidated database (organized by user)

[1445] Step 7: Feature extraction

[1446] The server uses statistical methods and machine learning algorithms to extract important features, such as fluctuations in heart rate and rising trends in blood pressure.

[1447] Input: Integrated database

[1448] Output: Extracted important feature data

[1449] Step 8: Training the generative AI model

[1450] The server trains a generative AI model based on the extracted features, using tools such as Python's TensorFlow.

[1451] Input: Important feature data

[1452] Output: A trained predictive model

[1453] Step 9: Health Risk Prediction

[1454] The server uses trained predictive models to assess each user's health risks, such as heart disease and diabetes risk.

[1455] Input: Trained predictive model and user data

[1456] Output: Health risk assessment for each user

[1457] Step 10: Create a Health Improvement Plan

[1458] The server generates a customized health improvement plan based on the predicted results, including specific diet and exercise plans.

[1459] Input: Health risk assessment data

[1460] Output: A customized health improvement plan

[1461] Step 11: Plan Notification

[1462] The device will notify the user of the generated health improvement plan and provide detailed instructions and reminders.

[1463] Input: Health improvement plan received from the server

[1464] Output: Health improvement plan communicated to the user

[1465] Step 12: Monitoring and Feedback

[1466] The server monitors the user's behavioral data and changes in health status in real time, and immediately notifies users of any significant changes or abnormalities and adjusts the plan based on user feedback.

[1467] Input: Real-time behavioral data and feedback

[1468] Output: Updated health improvement plan and feedback notification

[1469] (Application example 1)

[1470] 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."

[1471] In modern society, many people are exposed to health risks due to lifestyle-related diseases and stress. Conventional health management systems have difficulty effectively collecting individual users' health data and providing individually customized health improvement plans. Furthermore, they lack the means to recommend health-related products that users can use on a daily basis and to easily purchase these products. It is necessary to provide a system that solves these issues and allows users to manage their health on a daily basis.

[1472] 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.

[1473] In this invention, the server includes means for collecting data on users' lifestyle habits, health conditions, and genetic characteristics from a data collection device, means for integrating the collected data and storing it in a centralized database, means for training a prediction model generated based on the integrated data to predict each user's health risks and health conditions, means for generating a customized health improvement plan based on the prediction model and providing it to the user, means for monitoring changes in the user's behavioral data and health conditions and updating the customized health improvement plan in real time, means for suggesting health-related products suitable for the user in a virtual store, and means for the user to purchase health-related products in the virtual store. This allows for optimal health management for each user, enabling effective prevention and improvement of health risks in daily life.

[1474] A "data collection device" is a device that collects data about a user's lifestyle, health, or genetic characteristics, including a smartwatch, fitness device, or medical device.

[1475] "Integration" refers to the process of collecting different types of data and putting them into a centralized database in an easily manageable form.

[1476] A "predictive model" is a model that uses statistical methods and machine learning algorithms to predict each user's health risks and health status based on collected data.

[1477] "Customized Health Improvement Plan" means an individually optimized health maintenance and improvement plan generated based on each user's individual data and predictive models, which includes a meal plan, exercise plan, and medical test recommendations.

[1478] A "database" is a structured collection of data that is used to centrally store and manage collected data.

[1479] "Virtual store" refers to a virtual store space that users can access online to browse and purchase health-related products.

[1480] "Product Recommendation" means suggesting appropriate health-related products to a user based on the user's health risks and needs as assessed by the predictive model.

[1481] "Real-time updates" refers to the process of instantly changing and adjusting a customized health improvement plan in response to changes in a user's behavioral data and health status.

[1482] "Behavioral data" refers to data related to a user's daily activities, including the number of steps taken, heart rate, and sleep time.

[1483] "Health status" refers to data that indicates the user's physical and mental health status, including blood pressure, blood sugar levels, cholesterol levels, etc.

[1484] A health management system according to the present invention includes the following components.

[1485] First, users use data collection devices (e.g., smartwatches, fitness devices, medical equipment) to collect data about their lifestyle, health, and genetic characteristics, including steps taken, heart rate, sleep duration, blood pressure, blood sugar, and cholesterol levels.

[1486] The server then consolidates the collected data and stores it in a centralized database, where it undergoes cleaning processes such as removing outliers and imputing missing values.

[1487] The server then uses the combined data to train a generative AI model, which uses statistical methods and machine learning algorithms (e.g., TensorFlow) to predict each user's health risks and conditions, including risk of diseases such as heart disease and diabetes.

[1488] The server generates a customized health improvement plan based on the predictive model, including a meal plan, exercise schedule, and medical test recommendations. For example, a user at high risk for heart disease might be recommended a low-sodium meal plan and three days of aerobic exercise per week.

[1489] Furthermore, the customized health improvement plan is communicated to the user via their device (e.g., smartphone, head-mounted display), where they receive detailed instructions and set reminders to follow through, such as exercising regularly or changing their diet while wearing the smartwatch.

[1490] The server monitors user behavioral data and changes in health status in real time, and uses this data to continuously update the predictive model. If it detects any significant changes or abnormalities, it provides immediate feedback and notifies the user of appropriate measures.

[1491] This also includes a means for suggesting health-related products (e.g., supplements, fitness equipment, health foods, etc.) suitable for users in a virtual store. Users can use their devices to explore the virtual store and purchase the suggested products. This allows users to obtain related products as part of a health management system optimized for each individual user.

[1492] Specific examples

[1493] For example, for a 50-year-old female user, data such as the number of steps taken, heart rate, and sleep time are collected from the smartwatch. Additionally, health checkup results such as blood pressure and blood sugar levels are integrated into the database. The server uses this data to predict the risk of high blood pressure and generate a low-salt meal plan and aerobic exercise plan. The user wears a head-mounted display and visits a virtual store, where they can purchase suggested health-related products.

[1494] Prompt Sentence Examples

[1495] Based on the user's health data, assess their health risks and suggest appropriate health products to display in a virtual store. Users can view and purchase products in 3D using an HMD.

[1496] As described above, the present invention provides health management that is optimized for each user, enabling effective prevention and improvement of health risks in daily life.

[1497] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1498] Step 1:

[1499] Users use smartwatches and fitness devices to collect data about their lifestyle and health.

[1500] Input: Data such as steps, heart rate, sleep time, blood pressure, blood sugar, and cholesterol levels.

[1501] Output: Raw data obtained from the data acquisition device.

[1502] Specifically, for example, a smartwatch measures the user's heart rate and number of steps, and transmits that data to a smartphone via Bluetooth.

[1503] Step 2:

[1504] The server consolidates the collected data and stores it in a centralized database.

[1505] Input: Data collected from smartwatches and fitness devices.

[1506] Output: Cleaned data stored in a centralized database.

[1507] Specifically, the server removes outliers and imputes missing values, and stores the formatted data in a database. For example, data cleaning is performed using libraries such as Pandas and NumPy.

[1508] Step 3:

[1509] The server trains a generative AI model based on the integrated data to predict each user's health risks and health status.

[1510] Input: The data in the cleaned database.

[1511] Output: Predictive model training results and health risk assessment.

[1512] Specifically, it uses Python and TensorFlow to run machine learning algorithms based on past data to predict each user's health risks.

[1513] Step 4:

[1514] The server generates a customized health improvement plan based on the predictive model and provides it to the user.

[1515] Input: The output data of the predictive model.

[1516] Output: A personalized health improvement plan for each user.

[1517] Specifically, for users with high health risks, the system creates a plan that includes a low-salt diet and aerobic exercise, and generates a notification.

[1518] Step 5:

[1519] A customized health improvement plan is provided via the user's device (smartphone or head-mounted display).

[1520] Enter: a customized health improvement plan.

[1521] Output: Health improvement plan details displayed on the device.

[1522] Specifically, it uses the smartphone's notification function to inform users of the plan and set reminders.

[1523] Step 6:

[1524] The user follows the provided plan in their daily life and again collects data.

[1525] Input: New data collected according to the health improvement plan.

[1526] Output: Data of the action taken.

[1527] Specifically, the user performs the suggested exercise and the data is collected by the smartwatch.

[1528] Step 7:

[1529] The server monitors user behavioral data and changes in health status in real time and updates the predictive model accordingly.

[1530] Input: Collected behavioral data again.

[1531] Output: Updated predictive model and adjusted health improvement plan.

[1532] Specifically, it retrains its AI models based on new data and adjusts health plans as needed.

[1533] Step 8:

[1534] The server proposes health-related products suitable for the user in the virtual store and provides the user with the ability to purchase the products through the terminal.

[1535] Input: The output of the predictive model and the user's health status data.

[1536] Output: Suitable health-related product suggestions displayed in a virtual store.

[1537] Specifically, we use WebGL or Unity to build a 3D virtual store and provide an interface where users can purchase suggested products. Users use a head-mounted display to explore the virtual store and purchase appropriate health products.

[1538] As described above, the system of the present invention provides optimized health management for each individual user, enabling effective prevention and improvement of health risks in daily life.

[1539] 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.

[1540] The health management system according to the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide a personalized health improvement plan. Specific embodiments of this system are as follows.

[1541] First, the user collects lifestyle data using a data collection device such as a smartwatch or fitness device. This data includes the number of steps taken, heart rate, sleep time, and activity level. The user then inputs information about their diet and medications through the device. Health status information (blood pressure, blood sugar level, cholesterol level, etc.) obtained through regular health checkups is also collected from medical devices. Next, an emotion recognition method is used to collect emotion data. This emotion recognition method detects the user's emotional state using technologies such as voice analysis, facial expression analysis, and text analysis.

[1542] The collected data is sent to a server where it is integrated. The server then cleans the raw data, fills in missing values, and eliminates outliers. The cleaned data is then stored in a centralized database and organized by user. Sentiment data is also integrated and combined with other data for analysis.

[1543] The server then trains a generative AI model based on the integrated data. The server extracts key features and builds a predictive model. The predictive model uses statistical methods and machine learning algorithms to assess each user's health risk. This assessment includes predicting the risk of diseases such as heart disease and diabetes. It also analyzes emotional data to assess the impact of emotional states on health.

[1544] The server generates a customized health improvement plan based on the predictive model, including a low-salt diet plan, aerobic exercise schedule, and relevant medical test recommendations. Additionally, the server suggests stress management and relaxation techniques based on the user's emotional state. For example, if the user is experiencing high stress, the server may recommend meditation, deep breathing exercises, or relaxing music.

[1545] This customized plan is communicated to the user through the device, which provides detailed instructions and sets reminders to encourage them to follow through. The user then follows the plan and puts it into practice in their daily lives, for example by exercising regularly while wearing the smartwatch, changing their diet, undergoing recommended medical tests, and practicing suggested relaxation techniques for stress management.

[1546] The server monitors user behavioral data and changes in health status in real time and updates the predictive model based on this data. If significant changes or abnormalities are detected, the server provides immediate feedback and notifies the user of countermeasures. It also collects user feedback to evaluate the effectiveness of the health improvement plan.

[1547] For example, in the case of a male user in his 40s, data such as heart rate, number of steps, and sleep time are collected from the smartwatch, and information on dietary habits and home medical medications is entered into the app. In addition, daily stress levels are monitored using emotion recognition. The server integrates this data and predicts the risk of high blood pressure. Based on the prediction, a low-salt meal plan, aerobic exercise plan, and relaxation techniques are proposed. The device notifies the user of the generated plan and encourages them to carry it out. The user then lives their daily life according to the proposed plan, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[1548] In this way, the present invention provides personalized health management, preventing and improving health risks. The addition of an emotion engine achieves even higher levels of personalization, contributing to the improvement of the user's overall health.

[1549] The processing flow will be explained below.

[1550] Step 1: Collect data

[1551] The device automatically collects lifestyle data from users' smartwatches and fitness devices, including steps taken, heart rate, sleep time, and activity levels.

[1552] Users enter information such as their diet, medications, and subjective health status via a mobile app or web portal.

[1553] The terminal obtains the results of regular health checkups (blood pressure, blood sugar levels, cholesterol levels, etc.) from medical equipment and sends them to a server.

[1554] The device collects user emotional data using emotion recognition means, such as voice analysis, facial expression analysis, and text analysis, to detect the user's emotional state.

[1555] Step 2: Data integration and preprocessing

[1556] The server receives and integrates the data sent from the various data collection devices.

[1557] Data cleaning is performed on the received data, where missing values ​​are filled in and outliers are removed to improve data quality.

[1558] The server stores the cleaned data in a centralized database, organized by user, and sentiment data is also aggregated and combined with other data for analysis.

[1559] Step 3: Train the predictive model

[1560] The server performs feature engineering based on the integrated data to extract important variables required for the predictive model.

[1561] The extracted features are used to train a machine learning model, specifically by splitting the dataset into training and testing sets and evaluating the model's performance.

[1562] The server verifies the accuracy of the predictive model and tunes hyperparameters as necessary.

[1563] Step 4: Assess health risks

[1564] The server uses a trained predictive model to assess each user's health risk.

[1565] It calculates the risk of diseases such as heart disease and diabetes and generates a risk score for each user.

[1566] The server visualizes the risk assessment results in a dashboard format and prepares to present them to the user in an easily understandable format.

[1567] Emotional data is also used to assess the impact of a user's emotional state on their health.

[1568] Step 5: Generate a customized health improvement plan

[1569] The server generates a customized health improvement plan for each user based on the predictive model.

[1570] The plan includes a low-sodium meal plan, an aerobic exercise regimen, and recommendations for any necessary medical tests.

[1571] Based on your emotional state, it also suggests stress management and relaxation techniques, such as meditation, deep breathing exercises, and relaxing music for users with high stress levels.

[1572] Step 6: Communicate and execute the plan

[1573] The device will then notify the user of the generated health improvement plan, which will include specific instructions and how to implement it.

[1574] The device will set reminders and alerts to encourage users to follow through on the suggested plan.

[1575] The user is then expected to follow the health improvement plan and implement it in their daily lives, including making suggested dietary changes, engaging in recommended exercise, undergoing necessary medical tests, and practicing suggested relaxation techniques for stress management.

[1576] Step 7: Monitoring and feedback

[1577] The server monitors the user's behavioral data and changes in health status in real time.

[1578] Based on newly collected data, the predictive model is updated on an ongoing basis, and the effectiveness is evaluated by comparing the current situation with past data.

[1579] If the server detects any significant changes or abnormalities, it will immediately notify the user and suggest countermeasures.

[1580] The device collects user feedback and sends it to the server, which uses it to optimize future plans.

[1581] Step 8: Assess long-term impact and update the plan

[1582] The server will accumulate long-term data and provide a detailed evaluation of the effectiveness of each user's health improvement plan.

[1583] We regularly compile evaluation results, provide reports to users, and optimize plans based on their feedback.

[1584] The server adjusts the health improvement plan as needed to continuously provide optimal health management for each user.

[1585] Example 2

[1586] 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."

[1587] Current health management systems provide certain advice based on a user's lifestyle and health status, but lack comprehensive data analysis, including emotional state. Furthermore, they often lack the ability to generate personalized health improvement plans using generative AI models and update them in real time, making it difficult to accurately predict health risks and propose appropriate improvement plans for each user. Furthermore, the integration and cleaning of various data, as well as the extraction of important features, are complex and inefficient.

[1588] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1589] In this invention, the server includes means for collecting lifestyle, health, genetic, and emotional data of users from a data collection device, means for integrating the collected data and emotional data and storing them in a centralized database, means for training a generative AI model based on the integrated data to predict each user's health risk and emotional state, means for generating a customized health improvement plan based on the predictive model and providing it to the user, and means for monitoring changes in the user's behavioral data and health state and updating the customized health improvement plan in real time, thereby enabling accurate health risk prediction for each user and the generation and real-time updating of a personalized health improvement plan that also takes into account the user's emotional state.

[1590] A "data collection device" is a device for collecting a user's lifestyle, health, genetic, and emotional data, including a smartwatch, fitness device, medical device, and emotion recognition means.

[1591] "Lifestyle data" refers to data related to the user's daily life, including the number of steps taken, heart rate, sleep time, activity level, etc.

[1592] "Health status data" refers to data relating to the user's health status, including blood pressure, blood sugar level, cholesterol level, and the like.

[1593] "Genetic characteristic data" refers to data based on a user's genetic information, including genetic risks and genetic tendencies.

[1594] "Emotional data" refers to data related to a user's emotional state, such as stress, joy, or anger, collected using technologies such as voice analysis, facial expression analysis, and text analysis.

[1595] A "generative AI model" is an artificial intelligence model that is trained on integrated data and used to predict a user's health risks and emotional state.

[1596] A "predictive model" is a model that uses a generative AI model to predict specific health risks and emotional states.

[1597] A "Health Improvement Plan" is a plan for maintaining and improving health that is customized for each user based on a generative AI model, and includes a meal plan, an exercise plan, and stress management methods based on emotional state.

[1598] A "unified database" is a centralized database for integrating, organizing, and storing various types of collected data.

[1599] "Monitoring" refers to the continuous monitoring of user behavioral data and changes in health status, and involves real-time data collection and analysis.

[1600] "Real-time updates" refers to instantly updating the generative AI model and health improvement plan based on the latest data and providing feedback to users.

[1601] The health management system of the present invention comprehensively analyzes a user's lifestyle, health status, genetic characteristics, and emotional data to provide an individualized health improvement plan. To implement this system, the following hardware and software are used.

[1602] First, smartwatches, fitness devices, medical devices, and emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.) are used as data collection devices. Through these devices, users collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), health status data (blood pressure, blood glucose level, cholesterol level, etc.), and emotional data. Dietary information and medication intake are manually entered using a smartphone or tablet.

[1603] Next, all collected data is sent to a server, which consolidates the data and stores it in a centralized database. During this process, the data is cleaned (missing values ​​are filled in and outliers are removed). Once the data is consolidated, it is organized for each user, and emotion data is similarly consolidated and managed centrally.

[1604] The server then trains a generative AI model based on the integrated data. This model is built using machine learning algorithms (e.g., random forest, logistic regression, etc.). It extracts important features (e.g., long-term heart rate variability, stress level, etc.) and assesses each user's health risk and emotional state. This makes it possible to predict not only the risk of diseases such as heart disease and diabetes, but also the impact of emotional state on health.

[1605] The server generates a customized health improvement plan based on the predictive model. This plan includes a low-salt diet plan, a regular aerobic exercise schedule, recommendations for relevant medical tests, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations). The health improvement plan is then sent from the server to the device (smartphone or tablet) and notified to the user. The device provides detailed instructions and sets reminders to encourage implementation.

[1606] Users follow the plan provided by the device and use their smartwatch or fitness device to collect daily data. The collected data is then sent back to the server and monitored in real time. The server uses this data to continuously update the predictive model and provides feedback if it detects any significant changes or abnormalities. This feedback may include immediate action plans or adjusted health improvement plans.

[1607] As a concrete example, consider the case of a male user in his 40s. The user uses a smartwatch to collect data such as heart rate, steps, and sleep time, and enters information about his diet and medications through a smartphone app. Periodic health checkup data (blood pressure, blood sugar levels, etc.) obtained from medical devices is also sent to the server. Daily stress levels are also monitored using emotion recognition. The server integrates this data and trains a generative AI model. Based on the predictive model, the risk of high blood pressure is assessed and a low-salt meal plan, aerobic exercise schedule, and relaxation techniques are suggested. The device notifies the user of these plans and sets reminders to encourage their implementation. The user follows the plan as they go about their daily life, and the data is collected and analyzed by the server. The server evaluates the effectiveness of the plan and makes adjustments as necessary.

[1608] An example prompt is, "Train a generative AI model based on lifestyle and health checkup data from a man in his 40s. Use the resulting features to predict heart disease risk and high blood pressure risk and generate a personalized health plan."

[1609] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1610] Step 1:

[1611] User data collection

[1612] Users wear a smartwatch or fitness device to collect lifestyle data (number of steps, heart rate, sleep time, activity level, etc.), which is automatically recorded on the device.

[1613] Users manually enter information about their diet and medications using a smartphone or tablet, which is then stored in the application.

[1614] Users obtain health status data such as blood pressure, blood sugar, and cholesterol levels obtained during regular health checkups from medical institutions and send it to a server.

[1615] Emotion data is collected using emotion recognition methods (voice analysis, facial expression analysis, text analysis, etc.). For example, voice analysis can detect stress levels from users' everyday conversations. This data is also automatically stored on the device.

[1616] Input: steps, heart rate, sleep time, activity level, dietary information, medications taken, health check results, emotional data

[1617] Output: Raw data stored on the device and in the application

[1618] Step 2:

[1619] Data submission and integration

[1620] Lifestyle data is automatically sent from the user's smartwatch or fitness device to a server.

[1621] Users send information about their diet and medications to the server using their smartphone or tablet.

[1622] Regular health checkup data from medical institutions is also sent to the server.

[1623] The emotion data acquired from the emotion recognition means is transmitted to the server.

[1624] Input: Raw data stored on devices and applications

[1625] Output: Consolidated data sent to the server

[1626] Step 3:

[1627] Cleaning and storing data

[1628] The server cleans the received data. Specifically, it fills in missing values ​​and eliminates outliers. For example, if one day's worth of data is missing, it fills in the missing data with the average value of past data.

[1629] The server stores the cleaned data in a centralized database, organizing it for each user, and also aggregates the emotional data.

[1630] Input: Aggregated data sent to the server

[1631] Output: Cleaned data stored in a centralized database

[1632] Step 4:

[1633] Training generative AI models and generating predictive models

[1634] The server trains a generative AI model based on the combined data, extracting important features (e.g., long-term heart rate variability and stress levels).

[1635] The server uses machine learning algorithms (e.g., random forest, logistic regression, etc.) to build predictive models that assess each user's health risk and emotional state.

[1636] Input: Cleaned data stored in a centralized database

[1637] Output: Trained generative AI model and predictive model

[1638] Step 5:

[1639] Generate a customized health improvement plan

[1640] Based on the predictive model, the server generates a customized health improvement plan, including a low-salt meal plan, an aerobic exercise regimen, and stress management techniques based on emotional state (e.g., meditation, deep breathing exercises, relaxing music recommendations, etc.).

[1641] Input: Trained generative and predictive AI models

[1642] Output: A customized health improvement plan

[1643] Step 6:

[1644] Plan notification and execution

[1645] The server sends the generated health improvement plan to the user's device (smartphone or tablet).

[1646] The device will then notify the user of the plan details and set reminders to help them stick to it, such as a reminder to go for a 30-minute walk at 8am.

[1647] Enter: a customized health improvement plan.

[1648] Output: Notifications and reminder settings on user devices

[1649] Step 7:

[1650] Monitoring and Feedback

[1651] The server monitors user behavioral data and changes in health status in real time, and updates the predictive model based on the collected data.

[1652] If the server detects any significant changes or abnormalities, it will provide immediate feedback and notify the user of corrective measures. For example, if a sudden increase in heart rate is detected, a notification will be sent urging the user to seek medical attention.

[1653] Input: Routinely collected behavioral and health data

[1654] Output: Updated prediction model and feedback notification

[1655] Through these steps, the system can comprehensively manage the user's lifestyle and health status, and provide and implement a personalized health improvement plan.

[1656] (Application example 2)

[1657] 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."

[1658] Conventional health management systems collect data on users' lifestyles and health conditions and provide health improvement plans based on that data, but because they do not take emotional data into account, it is difficult to provide more accurate predictions of health risks or comprehensive health improvement plans that include stress management.In addition, it is not possible to suggest products in physical stores that are tailored to each user's individual health and emotional state, so there is a lack of ways to improve the shopping experience in physical stores.

[1659] 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.

[1660] In this invention, the server includes: means for collecting data on a user's lifestyle, health condition, genetic characteristics, and emotional state from a data collection device; means for integrating the collected data and storing it in a centralized database; means for training a predictive model based on the integrated data to predict each user's health risk and health condition; means for generating a customized health improvement plan based on the predictive model and providing it to the user; means for monitoring changes in the user's behavioral data and health condition and updating the customized health improvement plan in real time; and means for suggesting products in physical stores according to the user's health condition and emotional state. This enables accurate prediction of health risks and provision of a comprehensive health improvement plan, further improving the shopping experience in physical stores.

[1661] "Data collection device" means a device for collecting data on a user's lifestyle, health, genetic characteristics, and emotional state.

[1662] "Lifestyle habits" refers to a user's daily activities and behavioral patterns, sleep time, eating habits, etc.

[1663] "Health Status" refers to information about your current physical and mental health.

[1664] "Genetics" refers to the characteristics and tendencies that are based on a user's genes.

[1665] "Emotional state" refers to the user's emotional or mood state.

[1666] A "centralized database" is a database in which collected data is integrated and managed in a unified manner.

[1667] A "predictive model" is a statistical or machine learning algorithm used to predict a user's health risk or health status based on collected data.

[1668] "Health risk" refers to the likelihood that a user will develop a particular disease or health problem.

[1669] "Means for predicting health status" refers to methods and technologies for predicting a user's current and future health status based on collected data.

[1670] "Health Improvement Plan" refers to specific action plans and recommendations for users to improve their health based on predicted health risks and health conditions.

[1671] "Behavioral Data" refers to data about the actions or activities that a user actually performs.

[1672] "Real-time updating means" refers to a method or system for instantly adjusting and updating a health improvement plan in response to changes in a user's behavior or circumstances.

[1673] "Brick and mortar store" refers to a commercial establishment located in a physical location where goods or services are offered.

[1674] "Means for making product recommendations" refers to a method or system for suggesting appropriate products or services based on a user's health and emotional state.

[1675] The health management system of the present invention collects data on a user's lifestyle, health status, genetic characteristics, and emotional state, and provides a personalized health improvement plan based on this data. The system includes a data collection device, a database, a prediction model, and a physical store product suggestion means.

[1676] First, the user uses a smartwatch or fitness device to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Then, using a smartphone or medical device, health status data such as blood pressure, blood sugar, and cholesterol levels are collected. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect the user's emotional state.

[1677] This collected data is sent to a cloud server, which consolidates and cleans the data before storing it in a centralized database. The server then uses a generative AI model to train a predictive model based on the consolidated data to assess the user's health risks and health status. This assessment predicts the risk of heart disease, diabetes, and other conditions.

[1678] Based on the predicted results, the server generates a personalized health improvement plan for each user. This plan includes a low-salt diet plan, a cardiovascular exercise plan, and recommendations for regular medical checkups. It also includes stress management and relaxation techniques based on emotional data. For example, if a user is experiencing high stress, meditation or yoga may be recommended.

[1679] This customized health improvement plan is sent to the user's device, which provides detailed instructions for the plan, sets reminders to encourage implementation, and provides direct feedback to the user. The user wears the smartwatch as they go about their daily life, syncing data to a cloud server. The server monitors changes in user data in real time and updates the health improvement plan as needed.

[1680] Furthermore, this system also has a product suggestion function in physical stores. Product suggestions are made through terminals in the physical store based on the user's health and emotional state. For example, if a user is in a high-stress state, it will suggest a relaxation yoga mat or a product with a relaxing fragrance.

[1681] For example, if a male user in his 40s is predicted to be at risk of high blood pressure based on health checkup data and heart rate, step count, and other data collected from his smartwatch, a low-salt meal plan, aerobic exercise plan, and yoga to relieve stress will be recommended. If the user is determined to be in a high-stress state, products with a relaxation effect will be suggested in a physical store.

[1682] An example of a prompt sentence is as follows:

[1683] "Based on the health data of user ID 'user123', please collect the following information and generate a health improvement plan."

[1684] "Smartwatch data (steps, heart rate, sleep time)"

[1685] "Health checkup data (blood pressure, blood sugar level, cholesterol level)"

[1686] "Emotional data (current emotional state)"

[1687] This will enable users to manage their health more precisely and comprehensively, and also improve the shopping experience in physical stores.

[1688] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1689] Step 1:

[1690] Data collection

[1691] Subject: User

[1692] How it works:

[1693] Users use smartwatches and fitness devices to collect lifestyle data such as the number of steps taken, heart rate, and sleep time. Smartphones and medical devices also collect health data such as blood pressure, blood sugar, and cholesterol levels. Furthermore, emotion recognition tools utilize voice analysis, facial expression analysis, and text analysis to collect data on the user's emotional state.

[1694] Input: Lifestyle data obtained from smartwatches and fitness devices, health data from smartphones and medical devices, and emotional state data from emotion recognition means.

[1695] Output: Collected lifestyle, health, and emotion data.

[1696] Step 2:

[1697] Sending data

[1698] Subject: Terminal

[1699] How it works:

[1700] The user's device sends the various data collected in step 1 to the cloud server. This data includes lifestyle data, health data, and emotional data.

[1701] Input: Collected lifestyle, health, and emotional data stored on the device.

[1702] Output: Raw data sent to cloud server.

[1703] Step 3:

[1704] Data integration and cleaning

[1705] Subject: Server

[1706] How it works:

[1707] The server integrates the various data sent to the cloud and performs data cleaning, such as filling in missing values ​​and eliminating outliers, to generate a clean dataset, which is then stored in a centralized database.

[1708] Input: Raw data sent to the cloud server.

[1709] Output: The cleaned consolidated dataset.

[1710] Step 4:

[1711] Training a predictive model

[1712] Subject: Server

[1713] How it works:

[1714] The server trains a generative AI model based on the dataset integrated in step 3. It extracts important features from the dataset and builds a predictive model that assesses the health risks and health status of each user.

[1715] Input: The consolidated dataset after cleaning.

[1716] Output: A trained predictive model.

[1717] Step 5:

[1718] Generate a health improvement plan

[1719] Subject: Server

[1720] How it works:

[1721] The server uses the trained predictive model to predict each user's health risks and generates a customized health improvement plan, which includes a low-salt diet plan, an aerobic exercise regimen, recommendations for regular medical checkups, and stress management and relaxation techniques.

[1722] Input: A trained predictive model.

[1723] Output: A customized health improvement plan.

[1724] Step 6:

[1725] Communicating and implementing health improvement plans

[1726] Subject: Terminal

[1727] How it works:

[1728] The device notifies the user of the health improvement plan sent from the server, provides detailed instructions for the plan, and sets reminders to encourage execution. The user wears the smartwatch to record their daily activities and synchronizes the data to the cloud server.

[1729] Input: Health improvement plan sent from the server.

[1730] Output: A health improvement plan notified to the user, along with a reminder to implement it.

[1731] Step 7:

[1732] Real-time monitoring and plan updates

[1733] Subject: Server

[1734] How it works:

[1735] The server monitors the user's synchronized behavioral data and changes in health status in real time, evaluates the effectiveness of the health improvement plan based on this data, updates the plan as necessary, and provides immediate feedback to the user.

[1736] Input: Behavioral and health change data synced from users.

[1737] Output: Real-time updated health improvement plan and feedback to the user.

[1738] Step 8:

[1739] Product proposals in physical stores

[1740] Subject: Terminal (in a physical store)

[1741] How it works:

[1742] The device in the physical store will suggest products based on the user's health and emotional state. For example, if the user is under high stress, it will suggest relaxation products. This suggestion will be sent to the user's device, encouraging them to make a purchase at the physical store.

[1743] Input: User health and emotional state data.

[1744] Output: Product suggestions notified to the user.

[1745] 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.

[1746] 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.

[1747] 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.

[1748] 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.

[1749] 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.

[1750] 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.

[1751] 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).

[1752] 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.

[1753] 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."

[1754] 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.

[1755] 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).

[1756] 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.

[1757] 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.

[1758] 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.

[1759] 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.

[1760] 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.

[1761] 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.

[1762] 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.

[1763] 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.

[1764] 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.

[1765] 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.

[1766] The following is further disclosed regarding the above embodiment.

[1767] (Claim 1)

[1768] means for collecting lifestyle, health, and genetic data of the user from the data collection device;

[1769] means for aggregating and storing the collected data in a centralized database;

[1770] A means for training a predictive model generated based on the integrated data to predict health risks and health conditions for each user;

[1771] means for generating and providing a user with a customized health improvement plan based on the predictive model;

[1772] means for monitoring user behavioral data and changes in health status and updating the customized health improvement plan in real time;

[1773] A system including:

[1774] (Claim 2)

[1775] 10. The system of claim 1, wherein the customized health improvement plan includes a meal plan, an exercise regimen, and medical test recommendations.

[1776] (Claim 3)

[1777] 10. The system of claim 1, wherein the data collection devices include a smart watch, a fitness device, and a medical device.

[1778] "Example 1" (Claim 1)

[1779] means for collecting lifestyle, health, and genetic dat...

Claims

1. means for collecting lifestyle, health, and genetic data of the user from the data collection device; means for aggregating and storing the collected data in a centralized database; A means for training a predictive model generated based on the integrated data to predict health risks and health conditions for each user; means for generating and providing a user with a customized health improvement plan based on the predictive model; means for monitoring user behavioral data and changes in health status and updating the customized health improvement plan in real time; A system including:

2. 10. The system of claim 1, wherein the customized health improvement plan includes a meal plan, an exercise regimen, and medical test recommendations.

3. The system of claim 1 , wherein the data collection devices include a smart watch, a fitness device, and a medical device.

Images