System

Abstract

A system is provided.SOLUTION: A system including a terminal that collects medical information, symptoms, and lifestyle data of a user, a server that stores and pre-processes the collected data, a means that analyzes the pre-processed data and predicts future health risks using a generated AI model, a means that generates a diagnosis and a proposal based on the analysis result and notifies the user, and a means that transmits feedback of the user to the server again and performs relearning of the generated AI model.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, the aging population and the rise of chronic diseases have made personal health management and preventive medicine increasingly important. However, many people find it difficult to perform appropriate health management and preventive medicine in their daily lives, leading to an ever-increasing need for self-diagnosis and telemedicine. Current medical systems struggle to provide personalized healthcare support to individual users, and preventive measures based on individual health conditions and lifestyle habits are insufficient. This invention aims to provide effective and personalized medical support to users, predict health risks, and derive improvement measures. [Means for solving the problem]

[0005] The present invention provides a system that includes a device that collects a user's medical information, symptoms, and lifestyle data; a server that stores and preprocesses the collected data; a means for analyzing the preprocessed data and predicting future health risks using a generative AI model; a means for generating a diagnosis and proposal based on the analysis results and notifying the user; and a means for sending user feedback back to the server and retraining the generative AI model. This system analyzes each user's health data and provides personalized risk predictions, diagnoses, and proposals, encouraging the user to take appropriate self-care and preventative measures. Furthermore, the system uses user feedback data to continuously improve the accuracy of the generative AI model, providing even more effective medical support.

[0006] "Terminal" refers to a device or application that collects a user's medical information, symptoms, and lifestyle data.

[0007] "Server" means a computer system for storing, pre-processing and analyzing collected data.

[0008] "Preprocessing" refers to the process of converting collected data into a format suitable for analysis, such as filling in missing values ​​and eliminating outliers.

[0009] A "generative AI model" is an artificial intelligence algorithm that analyzes a user's health data and predicts future health risks.

[0010] "Analysis" is the process of using pre-processed data to train a generative AI model to assess the user's health and lifestyle habits.

[0011] "Diagnosis" refers to assessing the user's health condition based on the analysis results and suggesting necessary medical treatment or preventive measures.

[0012] "Suggestions" are specific self-care methods and preventive measures that are appropriate for the user based on the diagnostic results.

[0013] "Notification" refers to the act of informing the user of diagnostic results and suggestions via the device.

[0014] "Feedback" refers to providing the system with information about changes in the user's behavior or health status.

[0015] "Retraining" is the process of updating a generative AI model using user feedback data to improve its prediction accuracy. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: a terminal (smartphone, tablet, wearable device, etc.), a server, and the user.

[0038] System Overview

[0039] 1. Data Collection

[0040] The device collects users' medical information, symptoms, and lifestyle data, including step counts, heart rate, and sleep duration from the wearable device, as well as food logs and symptom reports from a smartphone app.

[0041] The terminal periodically synchronizes with the wearable device and prepares to send the collected data to the server.

[0042] 2. Data transmission and storage

[0043] The device sends the collected data to a server via the Internet, where it is encrypted and securely transmitted.

[0044] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[0045] 3. Data analysis and prediction

[0046] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks.

[0047] The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive and remedial measures.

[0048] 4. Generating Diagnoses and Recommendations

[0049] Based on the analysis results, the server diagnoses the user's health condition and generates suggestions for appropriate medical treatment and self-care.

[0050] The server sends the generated proposal to the terminal.

[0051] 5. Notifications and Feedback

[0052] The device notifies the user of the server's suggestions and diagnostic results, providing detailed feedback in the form of alerts and dashboards.

[0053] The user then takes action to improve their self-care and lifestyle habits based on the suggestions, and then enters the results back into the device.

[0054] 6. Re-learning and evaluation

[0055] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data.

[0056] The server adjusts the diagnosis and recommendations accordingly based on changes in the user's behavior and health status, providing more personalized support.

[0057] Specific examples

[0058] 1. Data Collection Example

[0059] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from a wearable device worn by the user.

[0060] Users enter details of their meals into a smartphone app, such as what they had for breakfast and their calorie intake.

[0061] 2. Examples of data transmission and storage

[0062] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[0063] 3. Examples of data analysis and prediction

[0064] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[0065] 4. Example of generating a diagnosis and a suggestion

[0066] The server diagnoses that "you need to increase your exercise" and suggests a daily exercise goal (e.g., 30 minutes of walking).

[0067] 5. Notification and Feedback Examples

[0068] The device will notify the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day."

[0069] The user begins exercising and enters the results into the device after one week.

[0070] 6. Re-learning and assessment examples

[0071] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[0072] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The device collects the user's medical information, symptoms, and lifestyle data. This includes data from wearable devices (e.g., steps taken, heart rate, sleep duration) and data input from smartphone apps (e.g., dietary details, exercise records). The device periodically acquires this data and temporarily stores it locally.

[0076] Step 2:

[0077] The data collected by the device is sent to a server over the internet, where it is encrypted to protect the user's privacy. The data is sent periodically, usually while connected to Wi-Fi.

[0078] Step 3:

[0079] The server receives the data sent from the device and stores it in a database. When storing the data, it checks for consistency and detects missing or outlier values. Data is supplemented or corrected as necessary.

[0080] Step 4:

[0081] The server analyzes the preprocessed data and uses a generative AI model to learn the user's health and lifestyle patterns. This analysis uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[0082] Step 5:

[0083] The server then predicts the user's health risk based on the analysis results. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise. This prediction is made using a generative AI model that derives future risk from past data.

[0084] Step 6:

[0085] The server generates a diagnosis and recommendations tailored to the user, including specific advice for exercise (e.g., 30 minutes of walking daily), dietary improvements, and stress management methods. The diagnosis and recommendations are personalized and customized for each user.

[0086] Step 7:

[0087] The server generates suggestions and sends diagnostic results to the device. The information is formatted in a user-friendly format, and the suggestions and diagnostic results are displayed on the device in notification or dashboard format.

[0088] Step 8:

[0089] The device displays notifications and suggestions from the server to the user. Specifically, alerts are displayed on the device screen and detailed feedback is provided in the form of a dashboard. Users can use this information to improve their self-care and lifestyle habits.

[0090] Step 9:

[0091] The user acts based on the suggestions from the server and inputs the results back into the device. For example, if the user takes a suggested walk, the device records the number of steps and time taken. The device also continuously inputs dietary information and other health-related data.

[0092] Step 10:

[0093] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[0094] Step 11:

[0095] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions.

[0096] These steps enable the server, terminals, and users to work together to achieve effective healthcare management.

[0097] Example 1

[0098] 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."

[0099] In conventional healthcare systems, the entire process from collection to analysis and feedback of users' medical information, symptoms, and lifestyle data was not integrated, resulting in insufficient coordination of individual data and feedback. As a result, there were issues with low accuracy of health predictions and suggestions for users, and an inability to provide personalized support. In addition, the safety and reliability of collected data was not ensured, and there was a risk of user data being leaked. There is a need for a comprehensive healthcare management system that can resolve these issues and manage users' health effectively and safely.

[0100] 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.

[0101] In this invention, the server includes a means for encrypting and transmitting collected data via the Internet, a means for storing the received data and performing preprocessing to complete missing values ​​and eliminate outliers, and a means for training a generative AI model using the preprocessed data to learn the user's health status and lifestyle patterns. This integrates the entire process from data collection to analysis, prediction, and feedback, making it possible to provide users with personalized health support in a safe and reliable manner.

[0102] A "terminal" is a device that collects a user's medical information, symptoms, and lifestyle data and transmits them to a server.

[0103] The "server" is a central system that stores and preprocesses collected data and performs data analysis and predictions using generative AI models.

[0104] "Collected Data" refers to a collection of data including a user's medical information, symptoms, and lifestyle data.

[0105] "Means for encrypting and transmitting data over the Internet" refers to the use of encryption technology to securely transmit data over the Internet.

[0106] "Preprocessing means for imputing missing values ​​and removing outliers" is a process for imputing missing data and removing outliers to improve data quality.

[0107] A "generative AI model" is an artificial intelligence model that learns a user's health condition and patterns based on past data and predicts future health risks.

[0108] A "deep learning algorithm" is a machine learning technique that uses large amounts of data to learn complex patterns and make predictions and classifications.

[0109] "Diagnosis and Suggestion" is an assessment of the user's health condition based on the analysis results, and provides advice on necessary medical procedures and lifestyle improvements.

[0110] "Feedback" refers to additional information and behavioral history collected from the user that the system uses to reevaluate and re-learn.

[0111] "Retraining" is the process of updating a generative AI model with new data to improve the accuracy of its predictions.

[0112] "Alert and dashboard format" refers to a notification method that visually presents important notifications and detailed feedback information to users.

[0113] The present invention is a comprehensive healthcare management system that collects, analyzes, and manages a user's medical information, symptoms, and lifestyle data. This system functions in cooperation with terminals (smartphones, tablets, wearable devices, etc.), a server, and users. An embodiment of this system will be described in detail below.

[0114] 1. Data Collection

[0115] The device uses a wearable device and a smartphone app to collect the user's medical information, symptoms, and lifestyle habits. Specifically, the following data is collected:

[0116] Data such as the number of steps taken, heart rate, and sleep time is acquired from wearable devices via wireless communication such as Bluetooth. For example, devices such as Fitbit and Apple Watch are used.

[0117] The smartphone app collects data on food records and symptom reports manually entered by users, specifically the types of food and calories consumed at breakfast.

[0118] 2. Data transmission and storage

[0119] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES, which ensures security during data transmission.

[0120] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Because this data may contain missing values ​​or outliers, the server preprocesses the data. Specifically, it uses the Python libraries pandas and numpy to complete missing values ​​and remove outliers.

[0121] 3. Data analysis and prediction

[0122] The server uses the preprocessed data to train a generative AI model based on a deep learning algorithm (e.g., TensorFlow or PyTorch).

[0123] The server analyzes past data to learn the user's health and lifestyle patterns, which can then be used to predict future health risks (e.g., risk of heart disease).

[0124] The server uses a generative AI model to output prediction results and evaluate the risks the user will face in the future.

[0125] 4. Generating Diagnoses and Recommendations

[0126] The server then diagnoses the user's health condition based on the analysis results and generates appropriate medical treatment and self-care recommendations, including the following specific suggestions:

[0127] "People need to increase their physical activity, so we recommend 30 minutes of walking every day."

[0128] It is recommended to avoid high-calorie meals.

[0129] The generated proposals and diagnostic results are sent to the terminal.

[0130] 5. Notifications and Feedback

[0131] The device notifies the user of the server's suggestions and diagnostic results in the form of alerts and dashboards, providing detailed feedback to the user, which the user can use to improve their own care and lifestyle habits.

[0132] The user then takes action based on the suggestions and again enters the results (for example, whether or not they achieved 30 minutes of walking each day) into the device.

[0133] 6. Re-learning and evaluation

[0134] The server retrains the generative AI model based on user feedback data to improve its accuracy. Specifically, adding new data allows the model to adapt to the latest user data, enabling more accurate predictions and suggestions.

[0135] Prompt Sentence Examples

[0136] Below are some example prompts to input to the generative AI model:

[0137] "Analyze exercise data and dietary habits over the past month to predict future health risks for users."

[0138] "Based on the user's heart rate and step count data, assess their current health status and suggest necessary preventive measures."

[0139] Thus, the present invention is a system that provides individualized and effective healthcare support and assists users in managing their health by having the server, terminal, and user work together.

[0140] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0141] Step 1: Data collection

[0142] The device collects the user's medical information, symptoms, and lifestyle data. This input data includes step counts, heart rate, and sleep time from a wearable device, as well as food logs and symptom reports from a smartphone app.

[0143] Specifically, the device syncs with the wearable device via Bluetooth at a set time each day and collects all data. For example, the device syncs with the device at 8:00 a.m. to obtain the previous day's step count and heart rate data. The device also collects the breakfast information entered by the user into the smartphone app (e.g., a 200-calorie meal).

[0144] Input: Data from wearable devices and smartphone apps

[0145] Output: Collected user data

[0146] Step 2: Data transmission and storage

[0147] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES. The server then stores the received data in a database (for example, MySQL or PostgreSQL).

[0148] Specifically, the device automatically encrypts all collected data at midnight every night and sends it to the server, which then checks the data for security and stores it in a database.

[0149] Input: Collected user data

[0150] Output: Data stored on the server (encrypted and security checked)

[0151] Step 3: Data Preprocessing

[0152] The server performs preprocessing on the received and stored data, such as filling in missing values ​​and removing outliers. Specifically, it cleans the data using Python's pandas and numpy.

[0153] Specifically, the server periodically retrieves the latest data from the database, and if there are any missing values, it fills them in with the average or median, and detects and deletes or corrects any outliers.

[0154] Input: Data stored on the server

[0155] Output: Preprocessed and clean data

[0156] Step 4: Data analysis and prediction

[0157] The server uses the preprocessed data to train a generative AI model that learns the user's health and lifestyle patterns, and uses deep learning algorithms (e.g., TensorFlow and PyTorch) to predict future health risks.

[0158] Specifically, once a week, the server batch-processes the preprocessed data and inputs it into the generative AI model to learn the user's patterns. For example, the model learns that the user is not physically active and outputs a prediction such as "future risk of heart disease increases by 15%."

[0159] Input: Preprocessed data

[0160] Output: Prediction of future health risks for the user

[0161] Step 5: Generate diagnostics and suggestions

[0162] The server then diagnoses the user's health condition based on the analysis results and generates specific medical and self-care recommendations, such as "recommended 30 minutes of walking every day."

[0163] Specifically, once the analysis is complete, the server immediately generates a diagnosis and a recommendation, which it then sends to the device, along with detailed instructions.

[0164] Input: User's future health risk prediction

[0165] Output: Diagnostic results and specific suggestions

[0166] Step 6: Notification and feedback

[0167] The device notifies the user of suggestions and diagnostic results from the server in the form of alerts and dashboards, providing detailed feedback.

[0168] Specifically, the device sends a notification from the server to the user every morning at 8:00. The user then takes action to improve their own health and lifestyle habits based on the notification and enters the results into the device. For example, the device will provide feedback that the user has achieved 30 minutes of walking every day for a week.

[0169] Input: Diagnostic results and specific suggestions

[0170] Output: User notification and user feedback data

[0171] Step 7: Retrain and evaluate

[0172] The server retrains the generative AI model based on user feedback data to improve prediction accuracy.

[0173] Specifically, the server retrieves new data every month, adds it to the generative AI model, and retrains it, allowing the model to adapt to the latest user data and make more accurate predictions and suggestions.

[0174] Input: User feedback data

[0175] Output: A modified and updated generative AI model

[0176] As described above, the system comprehensively manages the user's health and provides personalized support at each step.

[0177] (Application example 1)

[0178] 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."

[0179] The main purpose of conventional healthcare management systems was to collect users' medical information and lifestyle data and monitor their health status. However, it was difficult to detect sudden abnormalities or acute illnesses early, making it difficult to respond adequately. In addition, there were few ways to notify appropriate parties of an emergency after an abnormality was detected. This resulted in a lack of prompt and appropriate response in cases where the user's health status suddenly changed.

[0180] 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.

[0181] In this invention, the server includes a terminal that collects the user's medical information, symptoms, and lifestyle data, a means for storing and preprocessing the collected data, a means for analyzing the preprocessed data and predicting future health risks using a generative AI model, a means for generating a diagnosis and proposal based on the analysis results and notifying the user, a means for sending the user's feedback again to the server and retraining the generative AI model, a means for detecting abnormalities from the analyzed data and sending emergency notifications, and a means for sending notifications to family members and medical professionals. This enables detailed monitoring of the user's health status as well as rapid detection of abnormalities and emergency notification to relevant parties.

[0182] "User" refers to an individual who uses the healthcare management system.

[0183] "Medical Information" refers to data related to your medical care, such as your medical history, medical records, and test results.

[0184] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by the User.

[0185] "Lifestyle data" refers to data related to the user's daily activities and habits, such as diet, exercise, and sleep.

[0186] "Terminal" means a device for collecting a user's medical information, symptoms, and lifestyle data, including smartphones, tablets, and wearable devices.

[0187] "Server" refers to the computer system that stores, pre-processes, and analyzes collected data.

[0188] "Preprocessing" refers to the process of examining and correcting data prior to data analysis, such as filling in missing values ​​and removing outliers.

[0189] A "generative AI model" refers to an artificial intelligence model that uses collected and preprocessed data to learn a user's health condition and lifestyle patterns and predict future health risks.

[0190] "Analysis results" refers to the diagnostic and predictive results obtained by a generative AI model based on preprocessed data.

[0191] "Diagnosis" refers to the process of assessing a user's health status based on the analysis results and determining the need for specific medical interventions or self-care.

[0192] "Suggestions" refer to medical procedures and lifestyle improvements recommended to users based on diagnostic results.

[0193] "Notification means" refers to a method or device for communicating diagnoses and suggestions to the user.

[0194] "Feedback" refers to the user's reactions to the diagnosis or suggestions provided and the actual results of their actions.

[0195] "Retraining" refers to the process of retraining a generative AI model based on newly provided feedback data to improve its prediction accuracy.

[0196] "Abnormal" refers to abnormal values ​​or patterns in predicted health or lifestyle data that are outside the normal range.

[0197] "Emergency notification" refers to warnings and cautionary information that are immediately sent to relevant parties when an abnormality is detected.

[0198] "Family Members" refers to individuals who are close relatives of a User and who are eligible to receive Emergency Notifications.

[0199] "Healthcare Professional" refers to doctors, nurses, and other healthcare professionals who are responsible for managing and improving a user's health.

[0200] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: terminals (smartphones, tablets, wearable devices, etc.), a server, and the user.

[0201] System Overview

[0202] 1. Data Collection

[0203] The device collects the user's medical information, symptoms, and lifestyle data. This data includes steps, heart rate, and sleep time from the wearable device, as well as food logs and symptom reports from a smartphone app. The device periodically syncs with the wearable device and prepares to send the collected data to a server.

[0204] 2. Data transmission and storage

[0205] The device sends the collected data to a server via the internet. The data is encrypted and sent securely. The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[0206] 3. Data analysis and prediction

[0207] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks. The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive or remedial measures.

[0208] 4. Generating Diagnoses and Recommendations

[0209] The server then uses the analysis results to diagnose the user's health and generate appropriate medical and self-care recommendations. If an abnormality is detected from the analyzed data, the server has a built-in mechanism for sending emergency notifications to family members and medical personnel. The server then sends the generated recommendations to the device.

[0210] 5. Notifications and Feedback

[0211] The device notifies the user of the suggestions and diagnostic results from the server. Notifications are provided in the form of alerts and dashboards, providing detailed feedback. The user then takes action to improve their own care and lifestyle based on the suggestions, and enters the results back into the device.

[0212] 6. Re-learning and evaluation

[0213] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data, and adjusts the diagnosis and recommendations in a timely manner according to changes in the user's behavior and health status, providing more personalized support.

[0214] Specific examples

[0215] 1. Data Collection Example

[0216] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from the wearable device worn by the user. The user then inputs details of their meals into the smartphone app, such as the foods they ate for breakfast and their calorie intake.

[0217] 2. Examples of data transmission and storage

[0218] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[0219] 3. Examples of data analysis and prediction

[0220] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[0221] 4. Example of generating a diagnosis and a suggestion

[0222] The server will diagnose that "you need to increase your exercise" and suggest a daily exercise goal (e.g., 30 minutes of walking). If an abnormality is detected, such as an "abnormally high heart rate," an emergency notification will be sent to family members or medical personnel.

[0223] 5. Notification and Feedback Examples

[0224] The device notifies the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day." The user starts exercising and enters the results into the device after one week.

[0225] 6. Re-learning and assessment examples

[0226] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[0227] Prompt Sentence Examples

[0228] An example of a prompt to input to a generative AI model could be, "Please create an application that collects the user's health data and sends an emergency notification if an abnormality is detected."

[0229] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[0230] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0231] Step 1:

[0232] Data collection:

[0233] The device syncs with the user's wearable device to collect medical information, symptoms, and lifestyle data, such as the number of steps taken, heart rate, and sleep time. It receives sensor data from the wearable device as input and stores the data in local storage.

[0234] Step 2:

[0235] Sending data:

[0236] The device sends the collected data to the server via the Internet. The data is encrypted and sent through a secure communication channel. The input is data stored in the device's local storage and sent to the server. The output is the data transferred to the server.

[0237] Step 3:

[0238] Data storage and pre-processing:

[0239] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers. It receives user data sent as input and stores it in a database. The data is cleansed during the preprocessing process, and the output is preprocessed data.

[0240] Step 4:

[0241] Data analysis and prediction:

[0242] The server uses the preprocessed data to train a generative AI model to predict the user's health risk. The preprocessed data is used as input and fed into the generative AI model. The output is a health status assessment result and future health risk prediction data.

[0243] Step 5:

[0244] Generate diagnostics and suggestions:

[0245] The server diagnoses the user's health condition based on the analysis results and generates appropriate medical interventions and self-care suggestions. If an abnormality is detected, it sends an emergency notification to family members and medical professionals. It receives analysis result data as input and generates diagnoses and suggestions. The output is suggestion data and notification information.

[0246] Step 6:

[0247] Notifications and Feedback:

[0248] The device notifies the user of suggestions and diagnostic results from the server. The user takes action to improve their self-care and lifestyle habits based on the suggestions and enters the results into the device. The device receives suggestions and diagnostic result data as input and notifies the user. The output is the user's behavioral data and feedback.

[0249] Step 7:

[0250] Relearn and assess:

[0251] The server retrains the generative AI model based on user feedback data to improve prediction accuracy. It receives newly collected feedback data as input and retrains the generative AI model. The output is an updated generative AI model.

[0252] This provides users with more precise and personalized support at every step of their health management journey.

[0253] 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.

[0254] This invention is a comprehensive healthcare management system that combines a user's medical information, symptoms, and lifestyle data with an emotion engine that recognizes the user's emotions. This system works in cooperation with the terminal (smartphone, tablet, wearable device, etc.), server, and user to comprehensively evaluate the user's health risks and condition.

[0255] System Overview

[0256] 1. Data Collection

[0257] The device collects the user's medical information, symptoms, lifestyle data, and emotional data. Medical information and lifestyle data include steps, heart rate, and sleep time from the wearable device, and food and exercise records from a smartphone app. Emotional data is collected using the camera and microphone on the smartphone and wearable device.

[0258] The terminal periodically synchronizes with the wearable device and prepares locally stored data for transmission to the server.

[0259] 2. Data transmission and storage

[0260] The data collected by the device is sent to a server via the Internet. To protect privacy, the data is encrypted before transmission.

[0261] The server stores the received data in a database. When storing the data, it checks for consistency and fills in or corrects missing or outlier values.

[0262] 3. Data analysis and prediction

[0263] The server analyzes the preprocessed data. It uses a generative AI model to learn the user's health status and lifestyle patterns. At the same time, it uses an emotion engine to analyze the user's emotional data and evaluate its relevance to their health status. This analysis uses deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[0264] 4. Generating Diagnoses and Recommendations

[0265] The server predicts the user's health risks based on the analysis results. It combines information obtained from both health data and emotional data to generate personalized diagnoses and recommendations. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise and emotional data on high stress levels, and provides specific advice on stress management and exercise.

[0266] The server sends the generated proposal to the terminal.

[0267] 5. Notifications and Feedback

[0268] The device will notify the user of suggestions and diagnostic results from the server, in the form of alerts and dashboards, providing detailed feedback to the user.

[0269] Users act on the suggestions and enter their results into the device, which allows for continuous data collection.

[0270] 6. Re-learning and evaluation

[0271] The server retrains the generative AI model based on user feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. The retraining process also uses newly collected emotional data, enabling the next-best suggestions to be made based on the user's emotional state.

[0272] Specific examples

[0273] 1. Data Collection Example

[0274] The device (smartphone) collects the number of steps taken per day (e.g., 10,000 steps) and heart rate from the user's wearable device, and simultaneously analyzes facial expressions using the smartphone's camera to collect emotional data.

[0275] Users enter their meal details into a smartphone app, recording, for example, the foods they ate for breakfast and their calorie intake.

[0276] 2. Examples of data transmission and storage

[0277] The device sends the data collected at night to a server, where it undergoes a security check and is stored in a database.

[0278] 3. Examples of data analysis and prediction

[0279] The server analyzes a month's worth of data and detects that the user is not exercising enough, while the emotion engine recognizes high stress levels. A generative AI model is used to predict the risk of cardiovascular disease.

[0280] 4. Example of generating a diagnosis and a suggestion

[0281] The server diagnoses that "you need to increase your exercise and stress management is important," and suggests daily exercise goals (e.g., walking 30 minutes a day) and stress management methods (e.g., deep breathing exercises and yoga).

[0282] 5. Notification and Feedback Examples

[0283] The device notifies the user, "Because you are at high risk of cardiovascular disease, we recommend that you walk for 30 minutes every day and practice deep breathing exercises."

[0284] The user performs stress management and exercise and enters the results into the device.

[0285] 6. Re-learning and assessment examples

[0286] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[0287] In this way, the present invention provides more comprehensive and personalized healthcare support by linking the server, terminal, and user and using an emotion engine.

[0288] The processing flow will be explained below.

[0289] Step 1:

[0290] The device collects the user's medical information, symptoms, lifestyle habits, and emotional data. It obtains data on the number of steps, heart rate, and sleep time from the wearable device, and collects dietary and exercise records from a smartphone app. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[0291] Step 2:

[0292] The device encrypts the collected data (medical data, lifestyle data, emotional data) and sends it to a server via the Internet. Data transmission uses a secure communication protocol to protect privacy.

[0293] Step 3:

[0294] The server receives the data sent from the terminal. The received data is checked for consistency before being saved in the database. If missing or abnormal values ​​are detected, they are supplemented or corrected.

[0295] Step 4:

[0296] The server begins analysis based on the preprocessing results. A generative AI model is used to learn the user's health status and lifestyle patterns. At the same time, the emotion engine analyzes the emotion data and evaluates the correlation between the emotional state and health data. Deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN) are used in this process.

[0297] Step 5:

[0298] The server then uses the analysis results to predict the user's future health risks. For example, if data on lack of exercise and high stress levels are detected, it predicts the risk of cardiovascular disease. This prediction is made using a generative AI model.

[0299] Step 6:

[0300] The server performs a comprehensive assessment of the user's health and emotional state and generates specific diagnoses and suggestions, such as advice on increasing exercise (e.g., walking 30 minutes daily) and stress management methods (e.g., deep breathing exercises and yoga).

[0301] Step 7:

[0302] The server generates diagnostics and sends recommendations to the device, formatting the information in a user-friendly format (notifications and dashboards).

[0303] Step 8:

[0304] The device receives notifications and suggestions from the server and displays them to the user. Specifically, it displays alerts on the device screen and provides detailed feedback in the form of a dashboard, which the user can use to improve their self-care and lifestyle habits.

[0305] Step 9:

[0306] The user acts based on the suggestions from the server and inputs the results back into the device. For example, the number of steps and time taken when carrying out the suggested walking can be recorded. Changes in emotions and stress levels can also be input.

[0307] Step 10:

[0308] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[0309] Step 11:

[0310] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. During retraining, newly collected emotional data is also used to provide optimal suggestions based on the user's emotional state.

[0311] Through these steps, the server, device, and user work closely together to realize comprehensive and personalized healthcare support using an emotion engine.

[0312] Example 2

[0313] 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."

[0314] Conventional healthcare systems assess health risks based on a user's medical information and lifestyle data, but lack the ability to consider the user's emotional state. This results in low accuracy in health risk assessment and insufficient provision of personalized diagnoses and suggestions.

[0315] 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.

[0316] In this invention, the server includes means for collecting the user's medical information, symptoms, and lifestyle data, means for collecting the user's emotional data using a camera and microphone, means for storing and preprocessing the collected data, means for analyzing the preprocessed data and predicting future health risks using a generative AI model, means for analyzing the user's emotional data using an emotion engine and evaluating its relevance to the health state, means for generating a diagnosis and proposal based on the analysis results and notifying the user, and means for retransmitting the user's feedback to the server and retraining the generative AI model. This enables comprehensive health risk assessment that also takes emotional data into consideration, as well as the provision of individualized diagnoses and proposals.

[0317] "User" is the individual receiving a health risk assessment or diagnosis and providing medical information, lifestyle data, and emotional data.

[0318] "Medical information" refers to any information related to medical care, such as a user's medical history, medication history, and medical examination results.

[0319] "Symptom" means any abnormal physical or mental condition or illness experienced by a User.

[0320] "Lifestyle data" refers to information about a user's daily life, such as exercise, diet, sleep, smoking, and drinking.

[0321] "Emotional data" refers to information about a user's emotional state obtained through facial expressions, tone of voice, choice of words, etc.

[0322] "Means" refers to a method, machine, or software used to accomplish a particular purpose.

[0323] "Camera" refers to a device for capturing images and videos.

[0324] "Microphone" refers to a device for capturing sound.

[0325] "Storage" refers to accumulating collected data on a server or in local storage so that it can be used later.

[0326] "Preprocessing" refers to operations performed to transform collected data into a form suitable for analysis, including data cleansing, normalization, and filtering.

[0327] "Analysis" refers to the process of analyzing data to derive useful information and patterns.

[0328] A "generative AI model" refers to an artificial intelligence model that learns patterns from large amounts of data and automatically performs specific tasks.

[0329] An "emotion engine" refers to an algorithm or software that analyzes emotional data and outputs the results.

[0330] "Diagnosis" refers to assessing a user's health condition and risks based on their data and providing a medical judgment based on that assessment.

[0331] "Suggestion" refers to advice that provides specific guidelines for action or measures to the user based on the diagnostic results.

[0332] "Notification" refers to an action taken to inform the user of information (diagnostic results or suggestions) generated by the system.

[0333] "Feedback" refers to the user responding to the system with the results of the actions they take based on the suggestions.

[0334] "Retraining" refers to the process of using new data and feedback from users to retrain a generative AI model and improve its accuracy and capabilities.

[0335] MODE FOR CARRYING OUT THE INVENTION

[0336] This invention is a comprehensive healthcare management system that collects users' medical information, symptoms, lifestyle habits, and emotional data, and uses a generative AI model and emotion engine to assess the user's health risks and provide personalized diagnoses and recommendations. This system works in collaboration with three parties: devices (smartphones, tablets, wearable devices, etc.), a server, and the user.

[0337] Data collection

[0338] The device collects the user's medical information, symptoms, and lifestyle data (e.g., number of steps taken, heart rate, and sleep duration) from the wearable device, as well as food and exercise records entered by the user through an application installed on a smartphone or tablet.

[0339] The device also collects emotional data using a camera and microphone: the camera analyzes the user's facial expressions, and the microphone analyzes the tone of the voice to understand the user's emotional state.

[0340] For example, if a user inputs the foods and calories they ate for breakfast into a smartphone app, this data is stored locally on the device, and facial expression data is analyzed using the smartphone's camera to understand their emotional state.

[0341] Data transmission and storage

[0342] The device sends all collected data to a server via the internet, and all data is encrypted during transmission to protect privacy.

[0343] The server checks the integrity of the received data before storing it in the database. If any abnormal or missing values ​​are found, the server will supplement or correct them, thereby maintaining the accuracy of the data.

[0344] Data Analysis and Prediction

[0345] The server uses a generative AI model to analyze the pre-processed data, which learns the user's health and lifestyle patterns and predicts future health risks.

[0346] At the same time, an emotion engine is used to analyze the emotion data and assess the correlation between emotional states and health conditions, using deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[0347] Generate diagnostics and suggestions

[0348] The server then evaluates the user's health risk based on the results of the data analysis and generates a diagnosis and recommendations. For example, if the user's step count is low and their heart rate is high, it will determine that they are at high risk for cardiovascular disease. Based on this, it will recommend "walking 30 minutes a day" and "deep breathing exercises."

[0349] The generated proposal is sent from the server to the terminal.

[0350] Notifications and Feedback

[0351] The device notifies the user of suggestions and diagnostic results sent from the server, both in the form of alerts (pop-up notifications) and dashboards (detailed feedback).

[0352] The user accepts the suggestions and enters the results into the device, which then collects feedback.

[0353] Re-learning and assessment

[0354] The server re-analyzes the collected feedback data and re-trains the generative AI model, further improving the model's accuracy and increasing the reliability of future diagnoses and recommendations. Newly collected emotional data is also included in the re-training process.

[0355] Specific examples

[0356] For example, a user may input the foods and calories they ate for breakfast, and emotional data may include facial expression analysis results collected using a camera. All of this data is encrypted and sent to a server. The server analyzes this data, and if it detects a lack of exercise and high stress levels, it will diagnose a high risk of cardiovascular disease and suggest daily exercise goals and stress management methods.

[0357] Prompt Sentence Examples

[0358] "Based on the user's daily steps, heart rate, and dietary habits, evaluate emotional data, analyze stress levels, predict health risks, and generate prompts to suggest specific exercise goals and stress management methods to the user."

[0359] The system works in collaboration between the server, device, and user, leveraging an emotion engine and generative AI models to provide more comprehensive and personalized healthcare support.

[0360] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0361] Step 1:

[0362] Data collection

[0363] Users wear the wearable device, which automatically records medical information and lifestyle data (e.g., number of steps, heart rate, and sleep time).

[0364] Specific operation: The wearable device uses sensors to collect data in real time and transmits it to a device (smartphone or tablet) via Bluetooth or Wi-Fi.

[0365] Users enter their diet and exercise records into a smartphone app, for example, by inputting the foods they ate for breakfast and their calories.

[0366] The device stores the collected data locally, which is then sent to the server in the next step.

[0367] The device uses a camera and microphone to collect emotional data. The camera analyzes facial expressions and the microphone analyzes tone of voice. This emotional data is also stored locally.

[0368] Step 2:

[0369] Data transmission and storage

[0370] The device sends all collected data to a server via the internet, including encrypted user medical information, symptoms, lifestyle data, and emotional data.

[0371] Specific operation: The terminal transmits data overnight or at set time intervals, and encrypts the data during the transmission process.

[0372] The server checks the integrity of the data it receives and fills or corrects any inconsistencies or missing values. The output is a consistent dataset.

[0373] After checking the integrity, the server stores the data in a database, which is then used for analysis in the next step.

[0374] Step 3:

[0375] Data Analysis and Prediction

[0376] The server analyzes the stored pre-processed data, and the input is the user's consistent medical information, lifestyle data, and emotional data.

[0377] How it works: The generative AI model learns the user's health status and lifestyle patterns and predicts future health risks. The output is the predicted health risks.

[0378] The server analyzes the emotional data using an emotion engine. This analysis evaluates how the user's emotional state affects their health status. The output is data showing the relationship between emotional state and health status.

[0379] Step 4:

[0380] Generate diagnostics and suggestions

[0381] The server evaluates the user's health risk based on the data analysis results, and the input is data showing the relationship between predicted health risk and emotional state.

[0382] Specific behavior: The generative AI model performs a diagnosis and generates specific suggestions. For example, if a lack of exercise and high stress levels are detected, it will suggest daily walking and stress management methods. The output is a specific diagnosis and suggestion.

[0383] The generated proposal is sent to the terminal. The input is the diagnosis result and the proposal content, and the output is the proposal sent to the terminal.

[0384] Step 5:

[0385] Notifications and Feedback

[0386] The terminal notifies the user of the generated suggestions. The input is the diagnosis results and suggestions sent from the server.

[0387] Specific behavior: The device provides detailed feedback in the form of alerts and dashboards. The output is a notified suggestion to the user.

[0388] The user takes specific actions based on the suggestions and inputs the results into the terminal. The input is the result of the action taken.

[0389] Step 6:

[0390] Re-learning and assessment

[0391] The server re-parses the feedback data sent by the user. The input is the user's feedback data.

[0392] How it works: The generative AI model is retrained using feedback data. The output is a retrained generative AI model.

[0393] The server uses the retrained model to improve the accuracy of subsequent diagnoses and recommendations, and the output is improved diagnoses and recommendations.

[0394] (Application example 2)

[0395] 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."

[0396] Conventional healthcare management systems lack individualized health management and feedback, making it difficult to accurately provide users with the specific health programs and exercise suggestions they need. In addition, health support at physical stores is inconsistent, making it difficult to provide effective feedback in real time. Furthermore, there is a lack of a system in place to effectively utilize collected data, perform advanced analysis using generative AI models, and continuously predict health risks.

[0397] 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.

[0398] In this invention, the server includes a device that collects a user's medical information, symptoms, and lifestyle data; a means for storing and preprocessing the collected data; a means for analyzing the preprocessed data and predicting future health risks using a generative AI model; a means for generating a diagnosis and recommendation based on the analysis results and notifying the user; a means for sending user feedback back to the server and retraining the generative AI model; a means for collecting data from smart glasses or smartphones so that in-store staff can provide health management support to the user; and a means for providing individualized health programs and exercise recommendations to the user in-store. This enables more personalized health management and real-time feedback for users. It also enables consistent health support in physical stores, and through advanced analysis and continuous improvement using the generative AI model, it becomes possible to effectively predict and manage users' health risks.

[0399] "User's medical information" refers to information about the user's health condition, such as diagnostic results, prescription information, past medical history, and allergy information provided by a medical institution.

[0400] "Symptom" means any physical or mental symptom or sign of illness experienced by a User.

[0401] "Lifestyle data" refers to information about a user's daily activities and habits, including, for example, what they eat, how much sleep they get, and the frequency and type of exercise they do.

[0402] "Device" is a general term for devices that users use on a daily basis and that can collect and transmit data, such as smartphones, tablets, and wearable devices.

[0403] A "server" is a computer system that stores collected data and performs analysis and relearning.

[0404] "Preprocessing" refers to processes such as data cleansing and filtering to prepare collected data in an analyzable format.

[0405] "Generative AI model" is a general term for algorithmic models that are trained using deep learning and machine learning techniques to predict users' health risks.

[0406] "Health risk prediction" refers to analyzing future health conditions and predicting potential health problems based on collected data.

[0407] "Diagnosis" refers to assessing the user's health status based on the analysis results and identifying specific health problems.

[0408] "Suggestions" are specific advice that shows users the actions and improvements they should take to reduce health risks.

[0409] "Feedback" refers to input and responses from users, which are then collected again as data and used for analysis and model retraining.

[0410] "Retraining" is the process of retraining a generative AI model with new data from users to improve its prediction accuracy.

[0411] A "brick and mortar" is a location that provides health management services in a physical facility, such as a fitness center or gym.

[0412] "Staff" refers to the person in charge of providing health management and support to users at physical stores.

[0413] "Smart glasses" are glasses-type devices that display real-time information to the wearer and have the ability to collect data.

[0414] A "smartphone" is a portable multi-function device that can make calls, connect to the Internet, and operate applications.

[0415] A "wellness program" is an exercise and diet plan designed based on a user's health status and goals.

[0416] "Exercise Suggestions" refers to specific exercise or fitness activities recommended to you based on your health.

[0417] This invention is a comprehensive system for users to manage their health. It uses devices such as smartwatches, smartphones, and smart glasses to collect medical information, symptoms, lifestyle habits, and emotional data, and then analyzes the data on a server. Based on the analysis results, the system provides users with personalized health programs and exercise suggestions.

[0418] Hardware Configuration

[0419] The hardware configuration of the system is as follows:

[0420] Smartwatch: Collects data such as steps, heart rate, and sleep time.

[0421] Smart glasses: Collecting emotion data through facial expression analysis.

[0422] Smartphone: A device that aggregates data and sends it to the server.

[0423] Server: Stores data, analyzes it, and retrains the generative AI model.

[0424] Software Configuration

[0425] The software used in the system and its roles are as follows:

[0426] Flask: Used to implement server-side applications.

[0427] Generative AI models (e.g., TensorFlow and PyTorch) are used to analyze users' health risks.

[0428] Database (e.g. MySQL, PostgreSQL): Used to store user data.

[0429] Data collection and preprocessing

[0430] Data obtained from the user's smartwatch (e.g., number of steps, heart rate, sleep time) and facial expression data from the smart glasses are sent to a server via the smartphone. An application is installed on the smartphone, allowing the user to input medical information and lifestyle habits. This data is stored on the server and undergoes preprocessing, which includes data cleansing and formatting.

[0431] Data analysis

[0432] The server analyzes the collected data and uses a generative AI model to predict the user's health risks. Based on the analyzed data, specific recommendations are generated according to the user's current health status and predicted risks. The generative AI model uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[0433] Providing diagnostics and recommendations

[0434] Based on the analysis results, the server generates a diagnosis and suggestions for the user. For example, if the server detects a lack of exercise or a high stress level, it will notify the user of exercise suggestions such as "walking 30 minutes every day" or stress management methods such as "deep breathing exercises." The diagnosis and suggestions are provided to the user's smartphone in the form of notifications and a dashboard.

[0435] Retraining and feedback

[0436] By inputting feedback on the actions taken based on the user's suggestions into the device, the server re-analyzes the data and retrains the generative AI model, allowing the system to continuously improve its accuracy and provide more appropriate diagnoses and suggestions.

[0437] Specific examples

[0438] For example, when a user visits a sports gym, they wear a smartwatch and smart glasses. Heart rate and step count data are collected from the smartwatch, and facial expression data is collected from the smart glasses. The user enters their diet and lifestyle habits into their smartphone, and the data is sent to the server. After analysis, the server makes a specific suggestion, such as "Today's exercise should ideally be 20 minutes of running," and notifies the user's smartphone.

[0439] Prompt Sentence Examples

[0440] Please enter your medical information, lifestyle data, step count data (10,000 steps), heart rate, and facial expression data in the following format:

[0441] Medical information: {medical_data}

[0442] Lifestyle data: {lifestyle_data}

[0443] Step data: {step_data}

[0444] Heart rate: {heart_rate}

[0445] Emotion data: {emotion_data}"

[0446] This prompt is used as input to a generative AI model, which then uses it to generate health predictions and recommendations for the user.

[0447] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0448] Step 1:

[0449] Users wear smartwatches, smartphones, or smart glasses, and the devices begin collecting data.

[0450] Input: Step count, heart rate, sleep duration from smartwatch, facial expression data from smart glasses.

[0451] Output: Collected medical information, symptoms, lifestyle data, and emotional data.

[0452] Specific operation: As users go about their daily lives, the smartwatch automatically collects steps and heart rate, while the smart glasses automatically collect facial expression data.

[0453] Step 2:

[0454] The device transfers the collected data to a smartphone.

[0455] Input: Data from smartwatch and smart glasses.

[0456] Output: A set of data stored on the smartphone.

[0457] How it works: Smartwatches and smart glasses send data to your smartphone via Bluetooth.

[0458] Step 3:

[0459] Users enter medical information and lifestyle data using a smartphone app.

[0460] Input: Your medical information, diet, exercise records, etc.

[0461] Output: Complete dataset (medical information, symptoms, lifestyle data, emotion data).

[0462] What it does: The user opens the smartphone app and manually enters their food and exercise records.

[0463] Step 4:

[0464] The smartphone sends the collected data to a server via the internet.

[0465] Input: A set of data stored on your smartphone.

[0466] Output: Data stored on the server.

[0467] What it does: Your smartphone sends encrypted data over your internet connection and uploads it to a server.

[0468] Step 5:

[0469] The server stores the received data and performs preprocessing.

[0470] Input: Raw data received by the server.

[0471] Output: Preprocessed data (cleaned and formatted data).

[0472] Specific operation: The server performs data cleansing on the received data, such as filling in missing values, correcting outliers, and formatting.

[0473] Step 6:

[0474] The server analyzes the pre-processed data and uses a generative AI model to predict the user's health risks.

[0475] Input: Preprocessed data.

[0476] Output: Health risk prediction results.

[0477] How it works: The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze data and assess health risks using recurrent neural networks (RNNs) or convolutional neural networks (CNNs).

[0478] Step 7:

[0479] The server generates a diagnosis and suggestions based on the analysis results and notifies the user.

[0480] Input: Health risk prediction results.

[0481] Output: Diagnostic results and recommendations.

[0482] Specific operation: The server creates a specific action plan (e.g., walking 30 minutes every day) from the analysis results and sends it to the user's smartphone via the network.

[0483] Step 8:

[0484] The smartphone notifies the user of the diagnosis and suggestions from the server.

[0485] Input: Diagnostic results and suggestions from the server.

[0486] Output: User notification and dashboard display.

[0487] What it does: The phone displays information to the user through notification pop-ups and in-app dashboards.

[0488] Step 9:

[0489] The user takes action based on the suggestions and enters the results into their smartphone.

[0490] Input: The result of the user's action.

[0491] Output: Feedback data.

[0492] Specific actions: The user performs suggested actions such as exercise and stress management, and then enters the results (e.g., type and duration of exercise) into the smartphone app.

[0493] Step 10:

[0494] The smartphone sends feedback data to the server, which then retrains the generated AI model.

[0495] Input: Feedback data from smartphone.

[0496] Output: An updated generative AI model.

[0497] How it works: The smartphone sends feedback data to the server, which then uses this new data to retrain the generative AI model, improving diagnostic accuracy in future visits.

[0498] 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.

[0499] 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.

[0500] 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.

[0501] [Second embodiment]

[0502] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0503] 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.

[0504] 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).

[0505] 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.

[0506] 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.

[0507] 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).

[0508] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0513] 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."

[0514] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: a terminal (smartphone, tablet, wearable device, etc.), a server, and the user.

[0515] System Overview

[0516] 1. Data Collection

[0517] The device collects users' medical information, symptoms, and lifestyle data, including step counts, heart rate, and sleep duration from the wearable device, as well as food logs and symptom reports from a smartphone app.

[0518] The terminal periodically synchronizes with the wearable device and prepares to send the collected data to the server.

[0519] 2. Data transmission and storage

[0520] The device sends the collected data to a server via the Internet, where it is encrypted and securely transmitted.

[0521] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[0522] 3. Data analysis and prediction

[0523] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks.

[0524] The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive and remedial measures.

[0525] 4. Generating Diagnoses and Recommendations

[0526] Based on the analysis results, the server diagnoses the user's health condition and generates suggestions for appropriate medical treatment and self-care.

[0527] The server sends the generated proposal to the terminal.

[0528] 5. Notifications and Feedback

[0529] The device notifies the user of the server's suggestions and diagnostic results, providing detailed feedback in the form of alerts and dashboards.

[0530] The user then takes action to improve their self-care and lifestyle habits based on the suggestions, and then enters the results back into the device.

[0531] 6. Re-learning and evaluation

[0532] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data.

[0533] The server adjusts the diagnosis and recommendations accordingly based on changes in the user's behavior and health status, providing more personalized support.

[0534] Specific examples

[0535] 1. Data Collection Example

[0536] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from a wearable device worn by the user.

[0537] Users enter details of their meals into a smartphone app, such as what they had for breakfast and their calorie intake.

[0538] 2. Examples of data transmission and storage

[0539] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[0540] 3. Examples of data analysis and prediction

[0541] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[0542] 4. Example of generating a diagnosis and a suggestion

[0543] The server diagnoses that "you need to increase your exercise" and suggests a daily exercise goal (e.g., 30 minutes of walking).

[0544] 5. Notification and Feedback Examples

[0545] The device will notify the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day."

[0546] The user begins exercising and enters the results into the device after one week.

[0547] 6. Re-learning and assessment examples

[0548] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[0549] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[0550] The processing flow will be explained below.

[0551] Step 1:

[0552] The device collects the user's medical information, symptoms, and lifestyle data. This includes data from wearable devices (e.g., steps taken, heart rate, sleep duration) and data input from smartphone apps (e.g., dietary details, exercise records). The device periodically acquires this data and temporarily stores it locally.

[0553] Step 2:

[0554] The data collected by the device is sent to a server over the internet, where it is encrypted to protect the user's privacy. The data is sent periodically, usually while connected to Wi-Fi.

[0555] Step 3:

[0556] The server receives the data sent from the device and stores it in a database. When storing the data, it checks for consistency and detects missing or outlier values. Data is supplemented or corrected as necessary.

[0557] Step 4:

[0558] The server analyzes the preprocessed data and uses a generative AI model to learn the user's health and lifestyle patterns. This analysis uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[0559] Step 5:

[0560] The server then predicts the user's health risk based on the analysis results. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise. This prediction is made using a generative AI model that derives future risk from past data.

[0561] Step 6:

[0562] The server generates a diagnosis and recommendations tailored to the user, including specific advice for exercise (e.g., 30 minutes of walking daily), dietary improvements, and stress management methods. The diagnosis and recommendations are personalized and customized for each user.

[0563] Step 7:

[0564] The server generates suggestions and sends diagnostic results to the device. The information is formatted in a user-friendly format, and the suggestions and diagnostic results are displayed on the device in notification or dashboard format.

[0565] Step 8:

[0566] The device displays notifications and suggestions from the server to the user. Specifically, alerts are displayed on the device screen and detailed feedback is provided in the form of a dashboard. Users can use this information to improve their self-care and lifestyle habits.

[0567] Step 9:

[0568] The user acts based on the suggestions from the server and inputs the results back into the device. For example, if the user takes a suggested walk, the device records the number of steps and time taken. The device also continuously inputs dietary information and other health-related data.

[0569] Step 10:

[0570] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[0571] Step 11:

[0572] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions.

[0573] These steps enable the server, terminals, and users to work together to achieve effective healthcare management.

[0574] Example 1

[0575] 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."

[0576] In conventional healthcare systems, the entire process from collection to analysis and feedback of users' medical information, symptoms, and lifestyle data was not integrated, resulting in insufficient coordination of individual data and feedback. As a result, there were issues with low accuracy of health predictions and suggestions for users, and an inability to provide personalized support. In addition, the safety and reliability of collected data was not ensured, and there was a risk of user data being leaked. There is a need for a comprehensive healthcare management system that can resolve these issues and manage users' health effectively and safely.

[0577] 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.

[0578] In this invention, the server includes a means for encrypting and transmitting collected data via the Internet, a means for storing the received data and performing preprocessing to complete missing values ​​and eliminate outliers, and a means for training a generative AI model using the preprocessed data to learn the user's health status and lifestyle patterns. This integrates the entire process from data collection to analysis, prediction, and feedback, making it possible to provide users with personalized health support in a safe and reliable manner.

[0579] A "terminal" is a device that collects a user's medical information, symptoms, and lifestyle data and transmits them to a server.

[0580] The "server" is a central system that stores and preprocesses collected data and performs data analysis and predictions using generative AI models.

[0581] "Collected Data" refers to a collection of data including a user's medical information, symptoms, and lifestyle data.

[0582] "Means for encrypting and transmitting data over the Internet" refers to the use of encryption technology to securely transmit data over the Internet.

[0583] "Preprocessing means for imputing missing values ​​and removing outliers" is a process for imputing missing data and removing outliers to improve data quality.

[0584] A "generative AI model" is an artificial intelligence model that learns a user's health condition and patterns based on past data and predicts future health risks.

[0585] A "deep learning algorithm" is a machine learning technique that uses large amounts of data to learn complex patterns and make predictions and classifications.

[0586] "Diagnosis and Suggestion" is an assessment of the user's health condition based on the analysis results, and provides advice on necessary medical procedures and lifestyle improvements.

[0587] "Feedback" refers to additional information and behavioral history collected from the user that the system uses to reevaluate and re-learn.

[0588] "Retraining" is the process of updating a generative AI model with new data to improve the accuracy of its predictions.

[0589] "Alert and dashboard format" refers to a notification method that visually presents important notifications and detailed feedback information to users.

[0590] The present invention is a comprehensive healthcare management system that collects, analyzes, and manages a user's medical information, symptoms, and lifestyle data. This system functions in cooperation with terminals (smartphones, tablets, wearable devices, etc.), a server, and users. An embodiment of this system will be described in detail below.

[0591] 1. Data Collection

[0592] The device uses a wearable device and a smartphone app to collect the user's medical information, symptoms, and lifestyle habits. Specifically, the following data is collected:

[0593] Data such as the number of steps taken, heart rate, and sleep time is acquired from wearable devices via wireless communication such as Bluetooth. For example, devices such as Fitbit and Apple Watch are used.

[0594] The smartphone app collects data on food records and symptom reports manually entered by users, specifically the types of food and calories consumed at breakfast.

[0595] 2. Data transmission and storage

[0596] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES, which ensures security during data transmission.

[0597] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Because this data may contain missing values ​​or outliers, the server preprocesses the data. Specifically, it uses the Python libraries pandas and numpy to complete missing values ​​and remove outliers.

[0598] 3. Data analysis and prediction

[0599] The server uses the preprocessed data to train a generative AI model based on a deep learning algorithm (e.g., TensorFlow or PyTorch).

[0600] The server analyzes past data to learn the user's health and lifestyle patterns, which can then be used to predict future health risks (e.g., risk of heart disease).

[0601] The server uses a generative AI model to output prediction results and evaluate the risks the user will face in the future.

[0602] 4. Generating Diagnoses and Recommendations

[0603] The server then diagnoses the user's health condition based on the analysis results and generates appropriate medical treatment and self-care recommendations, including the following specific suggestions:

[0604] "People need to increase their physical activity, so we recommend 30 minutes of walking every day."

[0605] It is recommended to avoid high-calorie meals.

[0606] The generated proposals and diagnostic results are sent to the terminal.

[0607] 5. Notifications and Feedback

[0608] The device notifies the user of the server's suggestions and diagnostic results in the form of alerts and dashboards, providing detailed feedback to the user, which the user can use to improve their own care and lifestyle habits.

[0609] The user then takes action based on the suggestions and again enters the results (for example, whether or not they achieved 30 minutes of walking each day) into the device.

[0610] 6. Re-learning and evaluation

[0611] The server retrains the generative AI model based on user feedback data to improve its accuracy. Specifically, adding new data allows the model to adapt to the latest user data, enabling more accurate predictions and suggestions.

[0612] Prompt Sentence Examples

[0613] Below are some example prompts to input to the generative AI model:

[0614] "Analyze exercise data and dietary habits over the past month to predict future health risks for users."

[0615] "Based on the user's heart rate and step count data, assess their current health status and suggest necessary preventive measures."

[0616] Thus, the present invention is a system that provides individualized and effective healthcare support and assists users in managing their health by having the server, terminal, and user work together.

[0617] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0618] Step 1: Data collection

[0619] The device collects the user's medical information, symptoms, and lifestyle data. This input data includes step counts, heart rate, and sleep time from a wearable device, as well as food logs and symptom reports from a smartphone app.

[0620] Specifically, the device syncs with the wearable device via Bluetooth at a set time each day and collects all data. For example, the device syncs with the device at 8:00 a.m. to obtain the previous day's step count and heart rate data. The device also collects the breakfast information entered by the user into the smartphone app (e.g., a 200-calorie meal).

[0621] Input: Data from wearable devices and smartphone apps

[0622] Output: Collected user data

[0623] Step 2: Data transmission and storage

[0624] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES. The server then stores the received data in a database (for example, MySQL or PostgreSQL).

[0625] Specifically, the device automatically encrypts all collected data at midnight every night and sends it to the server, which then checks the data for security and stores it in a database.

[0626] Input: Collected user data

[0627] Output: Data stored on the server (encrypted and security checked)

[0628] Step 3: Data Preprocessing

[0629] The server performs preprocessing on the received and stored data, such as filling in missing values ​​and removing outliers. Specifically, it cleans the data using Python's pandas and numpy.

[0630] Specifically, the server periodically retrieves the latest data from the database, and if there are any missing values, it fills them in with the average or median, and detects and deletes or corrects any outliers.

[0631] Input: Data stored on the server

[0632] Output: Preprocessed and clean data

[0633] Step 4: Data analysis and prediction

[0634] The server uses the preprocessed data to train a generative AI model that learns the user's health and lifestyle patterns, and uses deep learning algorithms (e.g., TensorFlow and PyTorch) to predict future health risks.

[0635] Specifically, once a week, the server batch-processes the preprocessed data and inputs it into the generative AI model to learn the user's patterns. For example, the model learns that the user is not physically active and outputs a prediction such as "future risk of heart disease increases by 15%."

[0636] Input: Preprocessed data

[0637] Output: Prediction of future health risks for the user

[0638] Step 5: Generate diagnostics and suggestions

[0639] The server then diagnoses the user's health condition based on the analysis results and generates specific medical and self-care recommendations, such as "recommended 30 minutes of walking every day."

[0640] Specifically, once the analysis is complete, the server immediately generates a diagnosis and a recommendation, which it then sends to the device, along with detailed instructions.

[0641] Input: User's future health risk prediction

[0642] Output: Diagnostic results and specific suggestions

[0643] Step 6: Notification and feedback

[0644] The device notifies the user of suggestions and diagnostic results from the server in the form of alerts and dashboards, providing detailed feedback.

[0645] Specifically, the device sends a notification from the server to the user every morning at 8:00. The user then takes action to improve their own health and lifestyle habits based on the notification and enters the results into the device. For example, the device will provide feedback that the user has achieved 30 minutes of walking every day for a week.

[0646] Input: Diagnostic results and specific suggestions

[0647] Output: User notification and user feedback data

[0648] Step 7: Retrain and evaluate

[0649] The server retrains the generative AI model based on user feedback data to improve prediction accuracy.

[0650] Specifically, the server retrieves new data every month, adds it to the generative AI model, and retrains it, allowing the model to adapt to the latest user data and make more accurate predictions and suggestions.

[0651] Input: User feedback data

[0652] Output: A modified and updated generative AI model

[0653] As described above, the system comprehensively manages the user's health and provides personalized support at each step.

[0654] (Application example 1)

[0655] 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."

[0656] The main purpose of conventional healthcare management systems was to collect users' medical information and lifestyle data and monitor their health status. However, it was difficult to detect sudden abnormalities or acute illnesses early, making it difficult to respond adequately. In addition, there were few ways to notify appropriate parties of an emergency after an abnormality was detected. This resulted in a lack of prompt and appropriate response in cases where the user's health status suddenly changed.

[0657] 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.

[0658] In this invention, the server includes a terminal that collects the user's medical information, symptoms, and lifestyle data, a means for storing and preprocessing the collected data, a means for analyzing the preprocessed data and predicting future health risks using a generative AI model, a means for generating a diagnosis and proposal based on the analysis results and notifying the user, a means for sending the user's feedback again to the server and retraining the generative AI model, a means for detecting abnormalities from the analyzed data and sending emergency notifications, and a means for sending notifications to family members and medical professionals. This enables detailed monitoring of the user's health status as well as rapid detection of abnormalities and emergency notification to relevant parties.

[0659] "User" refers to an individual who uses the healthcare management system.

[0660] "Medical Information" refers to data related to your medical care, such as your medical history, medical records, and test results.

[0661] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by the User.

[0662] "Lifestyle data" refers to data related to the user's daily activities and habits, such as diet, exercise, and sleep.

[0663] "Terminal" means a device for collecting a user's medical information, symptoms, and lifestyle data, including smartphones, tablets, and wearable devices.

[0664] "Server" refers to the computer system that stores, pre-processes, and analyzes collected data.

[0665] "Preprocessing" refers to the process of examining and correcting data prior to data analysis, such as filling in missing values ​​and removing outliers.

[0666] A "generative AI model" refers to an artificial intelligence model that uses collected and preprocessed data to learn a user's health condition and lifestyle patterns and predict future health risks.

[0667] "Analysis results" refers to the diagnostic and predictive results obtained by a generative AI model based on preprocessed data.

[0668] "Diagnosis" refers to the process of assessing a user's health status based on the analysis results and determining the need for specific medical interventions or self-care.

[0669] "Suggestions" refer to medical procedures and lifestyle improvements recommended to users based on diagnostic results.

[0670] "Notification means" refers to a method or device for communicating diagnoses and suggestions to the user.

[0671] "Feedback" refers to the user's reactions to the diagnosis or suggestions provided and the actual results of their actions.

[0672] "Retraining" refers to the process of retraining a generative AI model based on newly provided feedback data to improve its prediction accuracy.

[0673] "Abnormal" refers to abnormal values ​​or patterns in predicted health or lifestyle data that are outside the normal range.

[0674] "Emergency notification" refers to warnings and cautionary information that are immediately sent to relevant parties when an abnormality is detected.

[0675] "Family Members" refers to individuals who are close relatives of a User and who are eligible to receive Emergency Notifications.

[0676] "Healthcare Professional" refers to doctors, nurses, and other healthcare professionals who are responsible for managing and improving a user's health.

[0677] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: terminals (smartphones, tablets, wearable devices, etc.), a server, and the user.

[0678] System Overview

[0679] 1. Data Collection

[0680] The device collects the user's medical information, symptoms, and lifestyle data. This data includes steps, heart rate, and sleep time from the wearable device, as well as food logs and symptom reports from a smartphone app. The device periodically syncs with the wearable device and prepares to send the collected data to a server.

[0681] 2. Data transmission and storage

[0682] The device sends the collected data to a server via the internet. The data is encrypted and sent securely. The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[0683] 3. Data analysis and prediction

[0684] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks. The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive or remedial measures.

[0685] 4. Generating Diagnoses and Recommendations

[0686] The server then uses the analysis results to diagnose the user's health and generate appropriate medical and self-care recommendations. If an abnormality is detected from the analyzed data, the server has a built-in mechanism for sending emergency notifications to family members and medical personnel. The server then sends the generated recommendations to the device.

[0687] 5. Notifications and Feedback

[0688] The device notifies the user of the suggestions and diagnostic results from the server. Notifications are provided in the form of alerts and dashboards, providing detailed feedback. The user then takes action to improve their own care and lifestyle based on the suggestions, and enters the results back into the device.

[0689] 6. Re-learning and evaluation

[0690] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data, and adjusts the diagnosis and recommendations in a timely manner according to changes in the user's behavior and health status, providing more personalized support.

[0691] Specific examples

[0692] 1. Data Collection Example

[0693] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from the wearable device worn by the user. The user then inputs details of their meals into the smartphone app, such as the foods they ate for breakfast and their calorie intake.

[0694] 2. Examples of data transmission and storage

[0695] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[0696] 3. Examples of data analysis and prediction

[0697] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[0698] 4. Example of generating a diagnosis and a suggestion

[0699] The server will diagnose that "you need to increase your exercise" and suggest a daily exercise goal (e.g., 30 minutes of walking). If an abnormality is detected, such as an "abnormally high heart rate," an emergency notification will be sent to family members or medical personnel.

[0700] 5. Notification and Feedback Examples

[0701] The device notifies the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day." The user starts exercising and enters the results into the device after one week.

[0702] 6. Re-learning and assessment examples

[0703] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[0704] Prompt Sentence Examples

[0705] An example of a prompt to input to a generative AI model could be, "Please create an application that collects the user's health data and sends an emergency notification if an abnormality is detected."

[0706] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[0707] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0708] Step 1:

[0709] Data collection:

[0710] The device syncs with the user's wearable device to collect medical information, symptoms, and lifestyle data, such as the number of steps taken, heart rate, and sleep time. It receives sensor data from the wearable device as input and stores the data in local storage.

[0711] Step 2:

[0712] Sending data:

[0713] The device sends the collected data to the server via the Internet. The data is encrypted and sent through a secure communication channel. The input is data stored in the device's local storage and sent to the server. The output is the data transferred to the server.

[0714] Step 3:

[0715] Data storage and pre-processing:

[0716] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers. It receives user data sent as input and stores it in a database. The data is cleansed during the preprocessing process, and the output is preprocessed data.

[0717] Step 4:

[0718] Data analysis and prediction:

[0719] The server uses the preprocessed data to train a generative AI model to predict the user's health risk. The preprocessed data is used as input and fed into the generative AI model. The output is a health status assessment result and future health risk prediction data.

[0720] Step 5:

[0721] Generate diagnostics and suggestions:

[0722] The server diagnoses the user's health condition based on the analysis results and generates appropriate medical interventions and self-care suggestions. If an abnormality is detected, it sends an emergency notification to family members and medical professionals. It receives analysis result data as input and generates diagnoses and suggestions. The output is suggestion data and notification information.

[0723] Step 6:

[0724] Notifications and Feedback:

[0725] The device notifies the user of suggestions and diagnostic results from the server. The user takes action to improve their self-care and lifestyle habits based on the suggestions and enters the results into the device. The device receives suggestions and diagnostic result data as input and notifies the user. The output is the user's behavioral data and feedback.

[0726] Step 7:

[0727] Relearn and assess:

[0728] The server retrains the generative AI model based on user feedback data to improve prediction accuracy. It receives newly collected feedback data as input and retrains the generative AI model. The output is an updated generative AI model.

[0729] This provides users with more precise and personalized support at every step of their health management journey.

[0730] 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.

[0731] This invention is a comprehensive healthcare management system that combines a user's medical information, symptoms, and lifestyle data with an emotion engine that recognizes the user's emotions. This system works in cooperation with the terminal (smartphone, tablet, wearable device, etc.), server, and user to comprehensively evaluate the user's health risks and condition.

[0732] System Overview

[0733] 1. Data Collection

[0734] The device collects the user's medical information, symptoms, lifestyle data, and emotional data. Medical information and lifestyle data include steps, heart rate, and sleep time from the wearable device, and food and exercise records from a smartphone app. Emotional data is collected using the camera and microphone on the smartphone and wearable device.

[0735] The terminal periodically synchronizes with the wearable device and prepares locally stored data for transmission to the server.

[0736] 2. Data transmission and storage

[0737] The data collected by the device is sent to a server via the Internet. To protect privacy, the data is encrypted before transmission.

[0738] The server stores the received data in a database. When storing the data, it checks for consistency and fills in or corrects missing or outlier values.

[0739] 3. Data analysis and prediction

[0740] The server analyzes the preprocessed data. It uses a generative AI model to learn the user's health status and lifestyle patterns. At the same time, it uses an emotion engine to analyze the user's emotional data and evaluate its relevance to their health status. This analysis uses deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[0741] 4. Generating Diagnoses and Recommendations

[0742] The server predicts the user's health risks based on the analysis results. It combines information obtained from both health data and emotional data to generate personalized diagnoses and recommendations. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise and emotional data on high stress levels, and provides specific advice on stress management and exercise.

[0743] The server sends the generated proposal to the terminal.

[0744] 5. Notifications and Feedback

[0745] The device will notify the user of suggestions and diagnostic results from the server, in the form of alerts and dashboards, providing detailed feedback to the user.

[0746] Users act on the suggestions and enter their results into the device, which allows for continuous data collection.

[0747] 6. Re-learning and evaluation

[0748] The server retrains the generative AI model based on user feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. The retraining process also uses newly collected emotional data, enabling the next-best suggestions to be made based on the user's emotional state.

[0749] Specific examples

[0750] 1. Data Collection Example

[0751] The device (smartphone) collects the number of steps taken per day (e.g., 10,000 steps) and heart rate from the user's wearable device, and simultaneously analyzes facial expressions using the smartphone's camera to collect emotional data.

[0752] Users enter their meal details into a smartphone app, recording, for example, the foods they ate for breakfast and their calorie intake.

[0753] 2. Examples of data transmission and storage

[0754] The device sends the data collected at night to a server, where it undergoes a security check and is stored in a database.

[0755] 3. Examples of data analysis and prediction

[0756] The server analyzes a month's worth of data and detects that the user is not exercising enough, while the emotion engine recognizes high stress levels. A generative AI model is used to predict the risk of cardiovascular disease.

[0757] 4. Example of generating a diagnosis and a suggestion

[0758] The server diagnoses that "you need to increase your exercise and stress management is important," and suggests daily exercise goals (e.g., walking 30 minutes a day) and stress management methods (e.g., deep breathing exercises and yoga).

[0759] 5. Notification and Feedback Examples

[0760] The device notifies the user, "Because you are at high risk of cardiovascular disease, we recommend that you walk for 30 minutes every day and practice deep breathing exercises."

[0761] The user performs stress management and exercise and enters the results into the device.

[0762] 6. Re-learning and assessment examples

[0763] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[0764] In this way, the present invention provides more comprehensive and personalized healthcare support by linking the server, terminal, and user and using an emotion engine.

[0765] The processing flow will be explained below.

[0766] Step 1:

[0767] The device collects the user's medical information, symptoms, lifestyle habits, and emotional data. It obtains data on the number of steps, heart rate, and sleep time from the wearable device, and collects dietary and exercise records from a smartphone app. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[0768] Step 2:

[0769] The device encrypts the collected data (medical data, lifestyle data, emotional data) and sends it to a server via the Internet. Data transmission uses a secure communication protocol to protect privacy.

[0770] Step 3:

[0771] The server receives the data sent from the terminal. The received data is checked for consistency before being saved in the database. If missing or abnormal values ​​are detected, they are supplemented or corrected.

[0772] Step 4:

[0773] The server begins analysis based on the preprocessing results. A generative AI model is used to learn the user's health status and lifestyle patterns. At the same time, the emotion engine analyzes the emotion data and evaluates the correlation between the emotional state and health data. Deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN) are used in this process.

[0774] Step 5:

[0775] The server then uses the analysis results to predict the user's future health risks. For example, if data on lack of exercise and high stress levels are detected, it predicts the risk of cardiovascular disease. This prediction is made using a generative AI model.

[0776] Step 6:

[0777] The server performs a comprehensive assessment of the user's health and emotional state and generates specific diagnoses and suggestions, such as advice on increasing exercise (e.g., walking 30 minutes daily) and stress management methods (e.g., deep breathing exercises and yoga).

[0778] Step 7:

[0779] The server generates diagnostics and sends recommendations to the device, formatting the information in a user-friendly format (notifications and dashboards).

[0780] Step 8:

[0781] The device receives notifications and suggestions from the server and displays them to the user. Specifically, it displays alerts on the device screen and provides detailed feedback in the form of a dashboard, which the user can use to improve their self-care and lifestyle habits.

[0782] Step 9:

[0783] The user acts based on the suggestions from the server and inputs the results back into the device. For example, the number of steps and time taken when carrying out the suggested walking can be recorded. Changes in emotions and stress levels can also be input.

[0784] Step 10:

[0785] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[0786] Step 11:

[0787] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. During retraining, newly collected emotional data is also used to provide optimal suggestions based on the user's emotional state.

[0788] Through these steps, the server, device, and user work closely together to realize comprehensive and personalized healthcare support using an emotion engine.

[0789] Example 2

[0790] 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."

[0791] Conventional healthcare systems assess health risks based on a user's medical information and lifestyle data, but lack the ability to consider the user's emotional state. This results in low accuracy in health risk assessment and insufficient provision of personalized diagnoses and suggestions.

[0792] 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.

[0793] In this invention, the server includes means for collecting the user's medical information, symptoms, and lifestyle data, means for collecting the user's emotional data using a camera and microphone, means for storing and preprocessing the collected data, means for analyzing the preprocessed data and predicting future health risks using a generative AI model, means for analyzing the user's emotional data using an emotion engine and evaluating its relevance to the health state, means for generating a diagnosis and proposal based on the analysis results and notifying the user, and means for retransmitting the user's feedback to the server and retraining the generative AI model. This enables comprehensive health risk assessment that also takes emotional data into consideration, as well as the provision of individualized diagnoses and proposals.

[0794] "User" is the individual receiving a health risk assessment or diagnosis and providing medical information, lifestyle data, and emotional data.

[0795] "Medical information" refers to any information related to medical care, such as a user's medical history, medication history, and medical examination results.

[0796] "Symptom" means any abnormal physical or mental condition or illness experienced by a User.

[0797] "Lifestyle data" refers to information about a user's daily life, such as exercise, diet, sleep, smoking, and drinking.

[0798] "Emotional data" refers to information about a user's emotional state obtained through facial expressions, tone of voice, choice of words, etc.

[0799] "Means" refers to a method, machine, or software used to accomplish a particular purpose.

[0800] "Camera" refers to a device for capturing images and videos.

[0801] "Microphone" refers to a device for capturing sound.

[0802] "Storage" refers to accumulating collected data on a server or in local storage so that it can be used later.

[0803] "Preprocessing" refers to operations performed to transform collected data into a form suitable for analysis, including data cleansing, normalization, and filtering.

[0804] "Analysis" refers to the process of analyzing data to derive useful information and patterns.

[0805] A "generative AI model" refers to an artificial intelligence model that learns patterns from large amounts of data and automatically performs specific tasks.

[0806] An "emotion engine" refers to an algorithm or software that analyzes emotional data and outputs the results.

[0807] "Diagnosis" refers to assessing a user's health condition and risks based on their data and providing a medical judgment based on that assessment.

[0808] "Suggestion" refers to advice that provides specific guidelines for action or measures to the user based on the diagnostic results.

[0809] "Notification" refers to an action taken to inform the user of information (diagnostic results or suggestions) generated by the system.

[0810] "Feedback" refers to the user responding to the system with the results of the actions they take based on the suggestions.

[0811] "Retraining" refers to the process of using new data and feedback from users to retrain a generative AI model and improve its accuracy and capabilities.

[0812] MODE FOR CARRYING OUT THE INVENTION

[0813] This invention is a comprehensive healthcare management system that collects users' medical information, symptoms, lifestyle habits, and emotional data, and uses a generative AI model and emotion engine to assess the user's health risks and provide personalized diagnoses and recommendations. This system works in collaboration with three parties: devices (smartphones, tablets, wearable devices, etc.), a server, and the user.

[0814] Data collection

[0815] The device collects the user's medical information, symptoms, and lifestyle data (e.g., number of steps taken, heart rate, and sleep duration) from the wearable device, as well as food and exercise records entered by the user through an application installed on a smartphone or tablet.

[0816] The device also collects emotional data using a camera and microphone: the camera analyzes the user's facial expressions, and the microphone analyzes the tone of the voice to understand the user's emotional state.

[0817] For example, if a user inputs the foods and calories they ate for breakfast into a smartphone app, this data is stored locally on the device, and facial expression data is analyzed using the smartphone's camera to understand their emotional state.

[0818] Data transmission and storage

[0819] The device sends all collected data to a server via the internet, and all data is encrypted during transmission to protect privacy.

[0820] The server checks the integrity of the received data before storing it in the database. If any abnormal or missing values ​​are found, the server will supplement or correct them, thereby maintaining the accuracy of the data.

[0821] Data Analysis and Prediction

[0822] The server uses a generative AI model to analyze the pre-processed data, which learns the user's health and lifestyle patterns and predicts future health risks.

[0823] At the same time, an emotion engine is used to analyze the emotion data and assess the correlation between emotional states and health conditions, using deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[0824] Generate diagnostics and suggestions

[0825] The server then evaluates the user's health risk based on the results of the data analysis and generates a diagnosis and recommendations. For example, if the user's step count is low and their heart rate is high, it will determine that they are at high risk for cardiovascular disease. Based on this, it will recommend "walking 30 minutes a day" and "deep breathing exercises."

[0826] The generated proposal is sent from the server to the terminal.

[0827] Notifications and Feedback

[0828] The device notifies the user of suggestions and diagnostic results sent from the server, both in the form of alerts (pop-up notifications) and dashboards (detailed feedback).

[0829] The user accepts the suggestions and enters the results into the device, which then collects feedback.

[0830] Re-learning and assessment

[0831] The server re-analyzes the collected feedback data and re-trains the generative AI model, further improving the model's accuracy and increasing the reliability of future diagnoses and recommendations. Newly collected emotional data is also included in the re-training process.

[0832] Specific examples

[0833] For example, a user may input the foods and calories they ate for breakfast, and emotional data may include facial expression analysis results collected using a camera. All of this data is encrypted and sent to a server. The server analyzes this data, and if it detects a lack of exercise and high stress levels, it will diagnose a high risk of cardiovascular disease and suggest daily exercise goals and stress management methods.

[0834] Prompt Sentence Examples

[0835] "Based on the user's daily steps, heart rate, and dietary habits, evaluate emotional data, analyze stress levels, predict health risks, and generate prompts to suggest specific exercise goals and stress management methods to the user."

[0836] The system works in collaboration between the server, device, and user, leveraging an emotion engine and generative AI models to provide more comprehensive and personalized healthcare support.

[0837] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0838] Step 1:

[0839] Data collection

[0840] Users wear the wearable device, which automatically records medical information and lifestyle data (e.g., number of steps, heart rate, and sleep time).

[0841] Specific operation: The wearable device uses sensors to collect data in real time and transmits it to a device (smartphone or tablet) via Bluetooth or Wi-Fi.

[0842] Users enter their diet and exercise records into a smartphone app, for example, by inputting the foods they ate for breakfast and their calories.

[0843] The device stores the collected data locally, which is then sent to the server in the next step.

[0844] The device uses a camera and microphone to collect emotional data. The camera analyzes facial expressions and the microphone analyzes tone of voice. This emotional data is also stored locally.

[0845] Step 2:

[0846] Data transmission and storage

[0847] The device sends all collected data to a server via the internet, including encrypted user medical information, symptoms, lifestyle data, and emotional data.

[0848] Specific operation: The terminal transmits data overnight or at set time intervals, and encrypts the data during the transmission process.

[0849] The server checks the integrity of the data it receives and fills or corrects any inconsistencies or missing values. The output is a consistent dataset.

[0850] After checking the integrity, the server stores the data in a database, which is then used for analysis in the next step.

[0851] Step 3:

[0852] Data Analysis and Prediction

[0853] The server analyzes the stored pre-processed data, and the input is the user's consistent medical information, lifestyle data, and emotional data.

[0854] How it works: The generative AI model learns the user's health status and lifestyle patterns and predicts future health risks. The output is the predicted health risks.

[0855] The server analyzes the emotional data using an emotion engine. This analysis evaluates how the user's emotional state affects their health status. The output is data showing the relationship between emotional state and health status.

[0856] Step 4:

[0857] Generate diagnostics and suggestions

[0858] The server evaluates the user's health risk based on the data analysis results, and the input is data showing the relationship between predicted health risk and emotional state.

[0859] Specific behavior: The generative AI model performs a diagnosis and generates specific suggestions. For example, if a lack of exercise and high stress levels are detected, it will suggest daily walking and stress management methods. The output is a specific diagnosis and suggestion.

[0860] The generated proposal is sent to the terminal. The input is the diagnosis result and the proposal content, and the output is the proposal sent to the terminal.

[0861] Step 5:

[0862] Notifications and Feedback

[0863] The terminal notifies the user of the generated suggestions. The input is the diagnosis results and suggestions sent from the server.

[0864] Specific behavior: The device provides detailed feedback in the form of alerts and dashboards. The output is a notified suggestion to the user.

[0865] The user takes specific actions based on the suggestions and inputs the results into the terminal. The input is the result of the action taken.

[0866] Step 6:

[0867] Re-learning and assessment

[0868] The server re-parses the feedback data sent by the user. The input is the user's feedback data.

[0869] How it works: The generative AI model is retrained using feedback data. The output is a retrained generative AI model.

[0870] The server uses the retrained model to improve the accuracy of subsequent diagnoses and recommendations, and the output is improved diagnoses and recommendations.

[0871] (Application example 2)

[0872] 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."

[0873] Conventional healthcare management systems lack individualized health management and feedback, making it difficult to accurately provide users with the specific health programs and exercise suggestions they need. In addition, health support at physical stores is inconsistent, making it difficult to provide effective feedback in real time. Furthermore, there is a lack of a system in place to effectively utilize collected data, perform advanced analysis using generative AI models, and continuously predict health risks.

[0874] 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.

[0875] In this invention, the server includes a device that collects a user's medical information, symptoms, and lifestyle data; a means for storing and preprocessing the collected data; a means for analyzing the preprocessed data and predicting future health risks using a generative AI model; a means for generating a diagnosis and recommendation based on the analysis results and notifying the user; a means for sending user feedback back to the server and retraining the generative AI model; a means for collecting data from smart glasses or smartphones so that in-store staff can provide health management support to the user; and a means for providing individualized health programs and exercise recommendations to the user in-store. This enables more personalized health management and real-time feedback for users. It also enables consistent health support in physical stores, and through advanced analysis and continuous improvement using the generative AI model, it becomes possible to effectively predict and manage users' health risks.

[0876] "User's medical information" refers to information about the user's health condition, such as diagnostic results, prescription information, past medical history, and allergy information provided by a medical institution.

[0877] "Symptom" means any physical or mental symptom or sign of illness experienced by a User.

[0878] "Lifestyle data" refers to information about a user's daily activities and habits, including, for example, what they eat, how much sleep they get, and the frequency and type of exercise they do.

[0879] "Device" is a general term for devices that users use on a daily basis and that can collect and transmit data, such as smartphones, tablets, and wearable devices.

[0880] A "server" is a computer system that stores collected data and performs analysis and relearning.

[0881] "Preprocessing" refers to processes such as data cleansing and filtering to prepare collected data in an analyzable format.

[0882] "Generative AI model" is a general term for algorithmic models that are trained using deep learning and machine learning techniques to predict users' health risks.

[0883] "Health risk prediction" refers to analyzing future health conditions and predicting potential health problems based on collected data.

[0884] "Diagnosis" refers to assessing the user's health status based on the analysis results and identifying specific health problems.

[0885] "Suggestions" are specific advice that shows users the actions and improvements they should take to reduce health risks.

[0886] "Feedback" refers to input and responses from users, which are then collected again as data and used for analysis and model retraining.

[0887] "Retraining" is the process of retraining a generative AI model with new data from users to improve its prediction accuracy.

[0888] A "brick and mortar" is a location that provides health management services in a physical facility, such as a fitness center or gym.

[0889] "Staff" refers to the person in charge of providing health management and support to users at physical stores.

[0890] "Smart glasses" are glasses-type devices that display real-time information to the wearer and have the ability to collect data.

[0891] A "smartphone" is a portable multi-function device that can make calls, connect to the Internet, and operate applications.

[0892] A "wellness program" is an exercise and diet plan designed based on a user's health status and goals.

[0893] "Exercise Suggestions" refers to specific exercise or fitness activities recommended to you based on your health.

[0894] This invention is a comprehensive system for users to manage their health. It uses devices such as smartwatches, smartphones, and smart glasses to collect medical information, symptoms, lifestyle habits, and emotional data, and then analyzes the data on a server. Based on the analysis results, the system provides users with personalized health programs and exercise suggestions.

[0895] Hardware Configuration

[0896] The hardware configuration of the system is as follows:

[0897] Smartwatch: Collects data such as steps, heart rate, and sleep time.

[0898] Smart glasses: Collecting emotion data through facial expression analysis.

[0899] Smartphone: A device that aggregates data and sends it to the server.

[0900] Server: Stores data, analyzes it, and retrains the generative AI model.

[0901] Software Configuration

[0902] The software used in the system and its roles are as follows:

[0903] Flask: Used to implement server-side applications.

[0904] Generative AI models (e.g., TensorFlow and PyTorch) are used to analyze users' health risks.

[0905] Database (e.g. MySQL, PostgreSQL): Used to store user data.

[0906] Data collection and preprocessing

[0907] Data obtained from the user's smartwatch (e.g., number of steps, heart rate, sleep time) and facial expression data from the smart glasses are sent to a server via the smartphone. An application is installed on the smartphone, allowing the user to input medical information and lifestyle habits. This data is stored on the server and undergoes preprocessing, which includes data cleansing and formatting.

[0908] Data analysis

[0909] The server analyzes the collected data and uses a generative AI model to predict the user's health risks. Based on the analyzed data, specific recommendations are generated according to the user's current health status and predicted risks. The generative AI model uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[0910] Providing diagnostics and recommendations

[0911] Based on the analysis results, the server generates a diagnosis and suggestions for the user. For example, if the server detects a lack of exercise or a high stress level, it will notify the user of exercise suggestions such as "walking 30 minutes every day" or stress management methods such as "deep breathing exercises." The diagnosis and suggestions are provided to the user's smartphone in the form of notifications and a dashboard.

[0912] Retraining and feedback

[0913] By inputting feedback on the actions taken based on the user's suggestions into the device, the server re-analyzes the data and retrains the generative AI model, allowing the system to continuously improve its accuracy and provide more appropriate diagnoses and suggestions.

[0914] Specific examples

[0915] For example, when a user visits a sports gym, they wear a smartwatch and smart glasses. Heart rate and step count data are collected from the smartwatch, and facial expression data is collected from the smart glasses. The user enters their diet and lifestyle habits into their smartphone, and the data is sent to the server. After analysis, the server makes a specific suggestion, such as "Today's exercise should ideally be 20 minutes of running," and notifies the user's smartphone.

[0916] Prompt Sentence Examples

[0917] Please enter your medical information, lifestyle data, step count data (10,000 steps), heart rate, and facial expression data in the following format:

[0918] Medical information: {medical_data}

[0919] Lifestyle data: {lifestyle_data}

[0920] Step data: {step_data}

[0921] Heart rate: {heart_rate}

[0922] Emotion data: {emotion_data}"

[0923] This prompt is used as input to a generative AI model, which then uses it to generate health predictions and recommendations for the user.

[0924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0925] Step 1:

[0926] Users wear smartwatches, smartphones, or smart glasses, and the devices begin collecting data.

[0927] Input: Step count, heart rate, sleep duration from smartwatch, facial expression data from smart glasses.

[0928] Output: Collected medical information, symptoms, lifestyle data, and emotional data.

[0929] Specific operation: As users go about their daily lives, the smartwatch automatically collects steps and heart rate, while the smart glasses automatically collect facial expression data.

[0930] Step 2:

[0931] The device transfers the collected data to a smartphone.

[0932] Input: Data from smartwatch and smart glasses.

[0933] Output: A set of data stored on the smartphone.

[0934] How it works: Smartwatches and smart glasses send data to your smartphone via Bluetooth.

[0935] Step 3:

[0936] Users enter medical information and lifestyle data using a smartphone app.

[0937] Input: Your medical information, diet, exercise records, etc.

[0938] Output: Complete dataset (medical information, symptoms, lifestyle data, emotion data).

[0939] What it does: The user opens the smartphone app and manually enters their food and exercise records.

[0940] Step 4:

[0941] The smartphone sends the collected data to a server via the internet.

[0942] Input: A set of data stored on your smartphone.

[0943] Output: Data stored on the server.

[0944] What it does: Your smartphone sends encrypted data over your internet connection and uploads it to a server.

[0945] Step 5:

[0946] The server stores the received data and performs preprocessing.

[0947] Input: Raw data received by the server.

[0948] Output: Preprocessed data (cleaned and formatted data).

[0949] Specific operation: The server performs data cleansing on the received data, such as filling in missing values, correcting outliers, and formatting.

[0950] Step 6:

[0951] The server analyzes the pre-processed data and uses a generative AI model to predict the user's health risks.

[0952] Input: Preprocessed data.

[0953] Output: Health risk prediction results.

[0954] How it works: The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze data and assess health risks using recurrent neural networks (RNNs) or convolutional neural networks (CNNs).

[0955] Step 7:

[0956] The server generates a diagnosis and suggestions based on the analysis results and notifies the user.

[0957] Input: Health risk prediction results.

[0958] Output: Diagnostic results and recommendations.

[0959] Specific operation: The server creates a specific action plan (e.g., walking 30 minutes every day) from the analysis results and sends it to the user's smartphone via the network.

[0960] Step 8:

[0961] The smartphone notifies the user of the diagnosis and suggestions from the server.

[0962] Input: Diagnostic results and suggestions from the server.

[0963] Output: User notification and dashboard display.

[0964] What it does: The phone displays information to the user through notification pop-ups and in-app dashboards.

[0965] Step 9:

[0966] The user takes action based on the suggestions and enters the results into their smartphone.

[0967] Input: The result of the user's action.

[0968] Output: Feedback data.

[0969] Specific actions: The user performs suggested actions such as exercise and stress management, and then enters the results (e.g., type and duration of exercise) into the smartphone app.

[0970] Step 10:

[0971] The smartphone sends feedback data to the server, which then retrains the generated AI model.

[0972] Input: Feedback data from smartphone.

[0973] Output: An updated generative AI model.

[0974] How it works: The smartphone sends feedback data to the server, which then uses this new data to retrain the generative AI model, improving diagnostic accuracy in future visits.

[0975] 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.

[0976] 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.

[0977] 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.

[0978] [Third embodiment]

[0979] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0980] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0981] 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).

[0982] 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.

[0983] 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.

[0984] 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).

[0985] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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."

[0991] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: a terminal (smartphone, tablet, wearable device, etc.), a server, and the user.

[0992] System Overview

[0993] 1. Data Collection

[0994] The device collects users' medical information, symptoms, and lifestyle data, including step counts, heart rate, and sleep duration from the wearable device, as well as food logs and symptom reports from a smartphone app.

[0995] The terminal periodically synchronizes with the wearable device and prepares to send the collected data to the server.

[0996] 2. Data transmission and storage

[0997] The device sends the collected data to a server via the Internet, where it is encrypted and securely transmitted.

[0998] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[0999] 3. Data analysis and prediction

[1000] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks.

[1001] The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive and remedial measures.

[1002] 4. Generating Diagnoses and Recommendations

[1003] Based on the analysis results, the server diagnoses the user's health condition and generates suggestions for appropriate medical treatment and self-care.

[1004] The server sends the generated proposal to the terminal.

[1005] 5. Notifications and Feedback

[1006] The device notifies the user of the server's suggestions and diagnostic results, providing detailed feedback in the form of alerts and dashboards.

[1007] The user then takes action to improve their self-care and lifestyle habits based on the suggestions, and then enters the results back into the device.

[1008] 6. Re-learning and evaluation

[1009] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data.

[1010] The server adjusts the diagnosis and recommendations accordingly based on changes in the user's behavior and health status, providing more personalized support.

[1011] Specific examples

[1012] 1. Data Collection Example

[1013] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from a wearable device worn by the user.

[1014] Users enter details of their meals into a smartphone app, such as what they had for breakfast and their calorie intake.

[1015] 2. Examples of data transmission and storage

[1016] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[1017] 3. Examples of data analysis and prediction

[1018] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[1019] 4. Example of generating a diagnosis and a suggestion

[1020] The server diagnoses that "you need to increase your exercise" and suggests a daily exercise goal (e.g., 30 minutes of walking).

[1021] 5. Notification and Feedback Examples

[1022] The device will notify the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day."

[1023] The user begins exercising and enters the results into the device after one week.

[1024] 6. Re-learning and assessment examples

[1025] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[1026] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[1027] The processing flow will be explained below.

[1028] Step 1:

[1029] The device collects the user's medical information, symptoms, and lifestyle data. This includes data from wearable devices (e.g., steps taken, heart rate, sleep duration) and data input from smartphone apps (e.g., dietary details, exercise records). The device periodically acquires this data and temporarily stores it locally.

[1030] Step 2:

[1031] The data collected by the device is sent to a server over the internet, where it is encrypted to protect the user's privacy. The data is sent periodically, usually while connected to Wi-Fi.

[1032] Step 3:

[1033] The server receives the data sent from the device and stores it in a database. When storing the data, it checks for consistency and detects missing or outlier values. Data is supplemented or corrected as necessary.

[1034] Step 4:

[1035] The server analyzes the preprocessed data and uses a generative AI model to learn the user's health and lifestyle patterns. This analysis uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[1036] Step 5:

[1037] The server then predicts the user's health risk based on the analysis results. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise. This prediction is made using a generative AI model that derives future risk from past data.

[1038] Step 6:

[1039] The server generates a diagnosis and recommendations tailored to the user, including specific advice for exercise (e.g., 30 minutes of walking daily), dietary improvements, and stress management methods. The diagnosis and recommendations are personalized and customized for each user.

[1040] Step 7:

[1041] The server generates suggestions and sends diagnostic results to the device. The information is formatted in a user-friendly format, and the suggestions and diagnostic results are displayed on the device in notification or dashboard format.

[1042] Step 8:

[1043] The device displays notifications and suggestions from the server to the user. Specifically, alerts are displayed on the device screen and detailed feedback is provided in the form of a dashboard. Users can use this information to improve their self-care and lifestyle habits.

[1044] Step 9:

[1045] The user acts based on the suggestions from the server and inputs the results back into the device. For example, if the user takes a suggested walk, the device records the number of steps and time taken. The device also continuously inputs dietary information and other health-related data.

[1046] Step 10:

[1047] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[1048] Step 11:

[1049] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions.

[1050] These steps enable the server, terminals, and users to work together to achieve effective healthcare management.

[1051] Example 1

[1052] 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."

[1053] In conventional healthcare systems, the entire process from collection to analysis and feedback of users' medical information, symptoms, and lifestyle data was not integrated, resulting in insufficient coordination of individual data and feedback. As a result, there were issues with low accuracy of health predictions and suggestions for users, and an inability to provide personalized support. In addition, the safety and reliability of collected data was not ensured, and there was a risk of user data being leaked. There is a need for a comprehensive healthcare management system that can resolve these issues and manage users' health effectively and safely.

[1054] 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.

[1055] In this invention, the server includes a means for encrypting and transmitting collected data via the Internet, a means for storing the received data and performing preprocessing to complete missing values ​​and eliminate outliers, and a means for training a generative AI model using the preprocessed data to learn the user's health status and lifestyle patterns. This integrates the entire process from data collection to analysis, prediction, and feedback, making it possible to provide users with personalized health support in a safe and reliable manner.

[1056] A "terminal" is a device that collects a user's medical information, symptoms, and lifestyle data and transmits them to a server.

[1057] The "server" is a central system that stores and preprocesses collected data and performs data analysis and predictions using generative AI models.

[1058] "Collected Data" refers to a collection of data including a user's medical information, symptoms, and lifestyle data.

[1059] "Means for encrypting and transmitting data over the Internet" refers to the use of encryption technology to securely transmit data over the Internet.

[1060] "Preprocessing means for imputing missing values ​​and removing outliers" is a process for imputing missing data and removing outliers to improve data quality.

[1061] A "generative AI model" is an artificial intelligence model that learns a user's health condition and patterns based on past data and predicts future health risks.

[1062] A "deep learning algorithm" is a machine learning technique that uses large amounts of data to learn complex patterns and make predictions and classifications.

[1063] "Diagnosis and Suggestion" is an assessment of the user's health condition based on the analysis results, and provides advice on necessary medical procedures and lifestyle improvements.

[1064] "Feedback" refers to additional information and behavioral history collected from the user that the system uses to reevaluate and re-learn.

[1065] "Retraining" is the process of updating a generative AI model with new data to improve the accuracy of its predictions.

[1066] "Alert and dashboard format" refers to a notification method that visually presents important notifications and detailed feedback information to users.

[1067] The present invention is a comprehensive healthcare management system that collects, analyzes, and manages a user's medical information, symptoms, and lifestyle data. This system functions in cooperation with terminals (smartphones, tablets, wearable devices, etc.), a server, and users. An embodiment of this system will be described in detail below.

[1068] 1. Data Collection

[1069] The device uses a wearable device and a smartphone app to collect the user's medical information, symptoms, and lifestyle habits. Specifically, the following data is collected:

[1070] Data such as the number of steps taken, heart rate, and sleep time is acquired from wearable devices via wireless communication such as Bluetooth. For example, devices such as Fitbit and Apple Watch are used.

[1071] The smartphone app collects data on food records and symptom reports manually entered by users, specifically the types of food and calories consumed at breakfast.

[1072] 2. Data transmission and storage

[1073] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES, which ensures security during data transmission.

[1074] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Because this data may contain missing values ​​or outliers, the server preprocesses the data. Specifically, it uses the Python libraries pandas and numpy to complete missing values ​​and remove outliers.

[1075] 3. Data analysis and prediction

[1076] The server uses the preprocessed data to train a generative AI model based on a deep learning algorithm (e.g., TensorFlow or PyTorch).

[1077] The server analyzes past data to learn the user's health and lifestyle patterns, which can then be used to predict future health risks (e.g., risk of heart disease).

[1078] The server uses a generative AI model to output prediction results and evaluate the risks the user will face in the future.

[1079] 4. Generating Diagnoses and Recommendations

[1080] The server then diagnoses the user's health condition based on the analysis results and generates appropriate medical treatment and self-care recommendations, including the following specific suggestions:

[1081] "People need to increase their physical activity, so we recommend 30 minutes of walking every day."

[1082] It is recommended to avoid high-calorie meals.

[1083] The generated proposals and diagnostic results are sent to the terminal.

[1084] 5. Notifications and Feedback

[1085] The device notifies the user of the server's suggestions and diagnostic results in the form of alerts and dashboards, providing detailed feedback to the user, which the user can use to improve their own care and lifestyle habits.

[1086] The user then takes action based on the suggestions and again enters the results (for example, whether or not they achieved 30 minutes of walking each day) into the device.

[1087] 6. Re-learning and evaluation

[1088] The server retrains the generative AI model based on user feedback data to improve its accuracy. Specifically, adding new data allows the model to adapt to the latest user data, enabling more accurate predictions and suggestions.

[1089] Prompt Sentence Examples

[1090] Below are some example prompts to input to the generative AI model:

[1091] "Analyze exercise data and dietary habits over the past month to predict future health risks for users."

[1092] "Based on the user's heart rate and step count data, assess their current health status and suggest necessary preventive measures."

[1093] Thus, the present invention is a system that provides individualized and effective healthcare support and assists users in managing their health by having the server, terminal, and user work together.

[1094] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1095] Step 1: Data collection

[1096] The device collects the user's medical information, symptoms, and lifestyle data. This input data includes step counts, heart rate, and sleep time from a wearable device, as well as food logs and symptom reports from a smartphone app.

[1097] Specifically, the device syncs with the wearable device via Bluetooth at a set time each day and collects all data. For example, the device syncs with the device at 8:00 a.m. to obtain the previous day's step count and heart rate data. The device also collects the breakfast information entered by the user into the smartphone app (e.g., a 200-calorie meal).

[1098] Input: Data from wearable devices and smartphone apps

[1099] Output: Collected user data

[1100] Step 2: Data transmission and storage

[1101] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES. The server then stores the received data in a database (for example, MySQL or PostgreSQL).

[1102] Specifically, the device automatically encrypts all collected data at midnight every night and sends it to the server, which then checks the data for security and stores it in a database.

[1103] Input: Collected user data

[1104] Output: Data stored on the server (encrypted and security checked)

[1105] Step 3: Data Preprocessing

[1106] The server performs preprocessing on the received and stored data, such as filling in missing values ​​and removing outliers. Specifically, it cleans the data using Python's pandas and numpy.

[1107] Specifically, the server periodically retrieves the latest data from the database, and if there are any missing values, it fills them in with the average or median, and detects and deletes or corrects any outliers.

[1108] Input: Data stored on the server

[1109] Output: Preprocessed and clean data

[1110] Step 4: Data analysis and prediction

[1111] The server uses the preprocessed data to train a generative AI model that learns the user's health and lifestyle patterns, and uses deep learning algorithms (e.g., TensorFlow and PyTorch) to predict future health risks.

[1112] Specifically, once a week, the server batch-processes the preprocessed data and inputs it into the generative AI model to learn the user's patterns. For example, the model learns that the user is not physically active and outputs a prediction such as "future risk of heart disease increases by 15%."

[1113] Input: Preprocessed data

[1114] Output: Prediction of future health risks for the user

[1115] Step 5: Generate diagnostics and suggestions

[1116] The server then diagnoses the user's health condition based on the analysis results and generates specific medical and self-care recommendations, such as "recommended 30 minutes of walking every day."

[1117] Specifically, once the analysis is complete, the server immediately generates a diagnosis and a recommendation, which it then sends to the device, along with detailed instructions.

[1118] Input: User's future health risk prediction

[1119] Output: Diagnostic results and specific suggestions

[1120] Step 6: Notification and feedback

[1121] The device notifies the user of suggestions and diagnostic results from the server in the form of alerts and dashboards, providing detailed feedback.

[1122] Specifically, the device sends a notification from the server to the user every morning at 8:00. The user then takes action to improve their own health and lifestyle habits based on the notification and enters the results into the device. For example, the device will provide feedback that the user has achieved 30 minutes of walking every day for a week.

[1123] Input: Diagnostic results and specific suggestions

[1124] Output: User notification and user feedback data

[1125] Step 7: Retrain and evaluate

[1126] The server retrains the generative AI model based on user feedback data to improve prediction accuracy.

[1127] Specifically, the server retrieves new data every month, adds it to the generative AI model, and retrains it, allowing the model to adapt to the latest user data and make more accurate predictions and suggestions.

[1128] Input: User feedback data

[1129] Output: A modified and updated generative AI model

[1130] As described above, the system comprehensively manages the user's health and provides personalized support at each step.

[1131] (Application example 1)

[1132] 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."

[1133] The main purpose of conventional healthcare management systems was to collect users' medical information and lifestyle data and monitor their health status. However, it was difficult to detect sudden abnormalities or acute illnesses early, making it difficult to respond adequately. In addition, there were few ways to notify appropriate parties of an emergency after an abnormality was detected. This resulted in a lack of prompt and appropriate response in cases where the user's health status suddenly changed.

[1134] 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.

[1135] In this invention, the server includes a terminal that collects the user's medical information, symptoms, and lifestyle data, a means for storing and preprocessing the collected data, a means for analyzing the preprocessed data and predicting future health risks using a generative AI model, a means for generating a diagnosis and proposal based on the analysis results and notifying the user, a means for sending the user's feedback again to the server and retraining the generative AI model, a means for detecting abnormalities from the analyzed data and sending emergency notifications, and a means for sending notifications to family members and medical professionals. This enables detailed monitoring of the user's health status as well as rapid detection of abnormalities and emergency notification to relevant parties.

[1136] "User" refers to an individual who uses the healthcare management system.

[1137] "Medical Information" refers to data related to your medical care, such as your medical history, medical records, and test results.

[1138] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by the User.

[1139] "Lifestyle data" refers to data related to the user's daily activities and habits, such as diet, exercise, and sleep.

[1140] "Terminal" means a device for collecting a user's medical information, symptoms, and lifestyle data, including smartphones, tablets, and wearable devices.

[1141] "Server" refers to the computer system that stores, pre-processes, and analyzes collected data.

[1142] "Preprocessing" refers to the process of examining and correcting data prior to data analysis, such as filling in missing values ​​and removing outliers.

[1143] A "generative AI model" refers to an artificial intelligence model that uses collected and preprocessed data to learn a user's health condition and lifestyle patterns and predict future health risks.

[1144] "Analysis results" refers to the diagnostic and predictive results obtained by a generative AI model based on preprocessed data.

[1145] "Diagnosis" refers to the process of assessing a user's health status based on the analysis results and determining the need for specific medical interventions or self-care.

[1146] "Suggestions" refer to medical procedures and lifestyle improvements recommended to users based on diagnostic results.

[1147] "Notification means" refers to a method or device for communicating diagnoses and suggestions to the user.

[1148] "Feedback" refers to the user's reactions to the diagnosis or suggestions provided and the actual results of their actions.

[1149] "Retraining" refers to the process of retraining a generative AI model based on newly provided feedback data to improve its prediction accuracy.

[1150] "Abnormal" refers to abnormal values ​​or patterns in predicted health or lifestyle data that are outside the normal range.

[1151] "Emergency notification" refers to warnings and cautionary information that are immediately sent to relevant parties when an abnormality is detected.

[1152] "Family Members" refers to individuals who are close relatives of a User and who are eligible to receive Emergency Notifications.

[1153] "Healthcare Professional" refers to doctors, nurses, and other healthcare professionals who are responsible for managing and improving a user's health.

[1154] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: terminals (smartphones, tablets, wearable devices, etc.), a server, and the user.

[1155] System Overview

[1156] 1. Data Collection

[1157] The device collects the user's medical information, symptoms, and lifestyle data. This data includes steps, heart rate, and sleep time from the wearable device, as well as food logs and symptom reports from a smartphone app. The device periodically syncs with the wearable device and prepares to send the collected data to a server.

[1158] 2. Data transmission and storage

[1159] The device sends the collected data to a server via the internet. The data is encrypted and sent securely. The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[1160] 3. Data analysis and prediction

[1161] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks. The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive or remedial measures.

[1162] 4. Generating Diagnoses and Recommendations

[1163] The server then uses the analysis results to diagnose the user's health and generate appropriate medical and self-care recommendations. If an abnormality is detected from the analyzed data, the server has a built-in mechanism for sending emergency notifications to family members and medical personnel. The server then sends the generated recommendations to the device.

[1164] 5. Notifications and Feedback

[1165] The device notifies the user of the suggestions and diagnostic results from the server. Notifications are provided in the form of alerts and dashboards, providing detailed feedback. The user then takes action to improve their own care and lifestyle based on the suggestions, and enters the results back into the device.

[1166] 6. Re-learning and evaluation

[1167] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data, and adjusts the diagnosis and recommendations in a timely manner according to changes in the user's behavior and health status, providing more personalized support.

[1168] Specific examples

[1169] 1. Data Collection Example

[1170] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from the wearable device worn by the user. The user then inputs details of their meals into the smartphone app, such as the foods they ate for breakfast and their calorie intake.

[1171] 2. Examples of data transmission and storage

[1172] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[1173] 3. Examples of data analysis and prediction

[1174] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[1175] 4. Example of generating a diagnosis and a suggestion

[1176] The server will diagnose that "you need to increase your exercise" and suggest a daily exercise goal (e.g., 30 minutes of walking). If an abnormality is detected, such as an "abnormally high heart rate," an emergency notification will be sent to family members or medical personnel.

[1177] 5. Notification and Feedback Examples

[1178] The device notifies the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day." The user starts exercising and enters the results into the device after one week.

[1179] 6. Re-learning and assessment examples

[1180] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[1181] Prompt Sentence Examples

[1182] An example of a prompt to input to a generative AI model could be, "Please create an application that collects the user's health data and sends an emergency notification if an abnormality is detected."

[1183] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[1184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1185] Step 1:

[1186] Data collection:

[1187] The device syncs with the user's wearable device to collect medical information, symptoms, and lifestyle data, such as the number of steps taken, heart rate, and sleep time. It receives sensor data from the wearable device as input and stores the data in local storage.

[1188] Step 2:

[1189] Sending data:

[1190] The device sends the collected data to the server via the Internet. The data is encrypted and sent through a secure communication channel. The input is data stored in the device's local storage and sent to the server. The output is the data transferred to the server.

[1191] Step 3:

[1192] Data storage and pre-processing:

[1193] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers. It receives user data sent as input and stores it in a database. The data is cleansed during the preprocessing process, and the output is preprocessed data.

[1194] Step 4:

[1195] Data analysis and prediction:

[1196] The server uses the preprocessed data to train a generative AI model to predict the user's health risk. The preprocessed data is used as input and fed into the generative AI model. The output is a health status assessment result and future health risk prediction data.

[1197] Step 5:

[1198] Generate diagnostics and suggestions:

[1199] The server diagnoses the user's health condition based on the analysis results and generates appropriate medical interventions and self-care suggestions. If an abnormality is detected, it sends an emergency notification to family members and medical professionals. It receives analysis result data as input and generates diagnoses and suggestions. The output is suggestion data and notification information.

[1200] Step 6:

[1201] Notifications and Feedback:

[1202] The device notifies the user of suggestions and diagnostic results from the server. The user takes action to improve their self-care and lifestyle habits based on the suggestions and enters the results into the device. The device receives suggestions and diagnostic result data as input and notifies the user. The output is the user's behavioral data and feedback.

[1203] Step 7:

[1204] Relearn and assess:

[1205] The server retrains the generative AI model based on user feedback data to improve prediction accuracy. It receives newly collected feedback data as input and retrains the generative AI model. The output is an updated generative AI model.

[1206] This provides users with more precise and personalized support at every step of their health management journey.

[1207] 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.

[1208] This invention is a comprehensive healthcare management system that combines a user's medical information, symptoms, and lifestyle data with an emotion engine that recognizes the user's emotions. This system works in cooperation with the terminal (smartphone, tablet, wearable device, etc.), server, and user to comprehensively evaluate the user's health risks and condition.

[1209] System Overview

[1210] 1. Data Collection

[1211] The device collects the user's medical information, symptoms, lifestyle data, and emotional data. Medical information and lifestyle data include steps, heart rate, and sleep time from the wearable device, and food and exercise records from a smartphone app. Emotional data is collected using the camera and microphone on the smartphone and wearable device.

[1212] The terminal periodically synchronizes with the wearable device and prepares locally stored data for transmission to the server.

[1213] 2. Data transmission and storage

[1214] The data collected by the device is sent to a server via the Internet. To protect privacy, the data is encrypted before transmission.

[1215] The server stores the received data in a database. When storing the data, it checks for consistency and fills in or corrects missing or outlier values.

[1216] 3. Data analysis and prediction

[1217] The server analyzes the preprocessed data. It uses a generative AI model to learn the user's health status and lifestyle patterns. At the same time, it uses an emotion engine to analyze the user's emotional data and evaluate its relevance to their health status. This analysis uses deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[1218] 4. Generating Diagnoses and Recommendations

[1219] The server predicts the user's health risks based on the analysis results. It combines information obtained from both health data and emotional data to generate personalized diagnoses and recommendations. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise and emotional data on high stress levels, and provides specific advice on stress management and exercise.

[1220] The server sends the generated proposal to the terminal.

[1221] 5. Notifications and Feedback

[1222] The device will notify the user of suggestions and diagnostic results from the server, in the form of alerts and dashboards, providing detailed feedback to the user.

[1223] Users act on the suggestions and enter their results into the device, which allows for continuous data collection.

[1224] 6. Re-learning and evaluation

[1225] The server retrains the generative AI model based on user feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. The retraining process also uses newly collected emotional data, enabling the next-best suggestions to be made based on the user's emotional state.

[1226] Specific examples

[1227] 1. Data Collection Example

[1228] The device (smartphone) collects the number of steps taken per day (e.g., 10,000 steps) and heart rate from the user's wearable device, and simultaneously analyzes facial expressions using the smartphone's camera to collect emotional data.

[1229] Users enter their meal details into a smartphone app, recording, for example, the foods they ate for breakfast and their calorie intake.

[1230] 2. Examples of data transmission and storage

[1231] The device sends the data collected at night to a server, where it undergoes a security check and is stored in a database.

[1232] 3. Examples of data analysis and prediction

[1233] The server analyzes a month's worth of data and detects that the user is not exercising enough, while the emotion engine recognizes high stress levels. A generative AI model is used to predict the risk of cardiovascular disease.

[1234] 4. Example of generating a diagnosis and a suggestion

[1235] The server diagnoses that "you need to increase your exercise and stress management is important," and suggests daily exercise goals (e.g., walking 30 minutes a day) and stress management methods (e.g., deep breathing exercises and yoga).

[1236] 5. Notification and Feedback Examples

[1237] The device notifies the user, "Because you are at high risk of cardiovascular disease, we recommend that you walk for 30 minutes every day and practice deep breathing exercises."

[1238] The user performs stress management and exercise and enters the results into the device.

[1239] 6. Re-learning and assessment examples

[1240] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[1241] In this way, the present invention provides more comprehensive and personalized healthcare support by linking the server, terminal, and user and using an emotion engine.

[1242] The processing flow will be explained below.

[1243] Step 1:

[1244] The device collects the user's medical information, symptoms, lifestyle habits, and emotional data. It obtains data on the number of steps, heart rate, and sleep time from the wearable device, and collects dietary and exercise records from a smartphone app. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[1245] Step 2:

[1246] The device encrypts the collected data (medical data, lifestyle data, emotional data) and sends it to a server via the Internet. Data transmission uses a secure communication protocol to protect privacy.

[1247] Step 3:

[1248] The server receives the data sent from the terminal. The received data is checked for consistency before being saved in the database. If missing or abnormal values ​​are detected, they are supplemented or corrected.

[1249] Step 4:

[1250] The server begins analysis based on the preprocessing results. A generative AI model is used to learn the user's health status and lifestyle patterns. At the same time, the emotion engine analyzes the emotion data and evaluates the correlation between the emotional state and health data. Deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN) are used in this process.

[1251] Step 5:

[1252] The server then uses the analysis results to predict the user's future health risks. For example, if data on lack of exercise and high stress levels are detected, it predicts the risk of cardiovascular disease. This prediction is made using a generative AI model.

[1253] Step 6:

[1254] The server performs a comprehensive assessment of the user's health and emotional state and generates specific diagnoses and suggestions, such as advice on increasing exercise (e.g., walking 30 minutes daily) and stress management methods (e.g., deep breathing exercises and yoga).

[1255] Step 7:

[1256] The server generates diagnostics and sends recommendations to the device, formatting the information in a user-friendly format (notifications and dashboards).

[1257] Step 8:

[1258] The device receives notifications and suggestions from the server and displays them to the user. Specifically, it displays alerts on the device screen and provides detailed feedback in the form of a dashboard, which the user can use to improve their self-care and lifestyle habits.

[1259] Step 9:

[1260] The user acts based on the suggestions from the server and inputs the results back into the device. For example, the number of steps and time taken when carrying out the suggested walking can be recorded. Changes in emotions and stress levels can also be input.

[1261] Step 10:

[1262] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[1263] Step 11:

[1264] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. During retraining, newly collected emotional data is also used to provide optimal suggestions based on the user's emotional state.

[1265] Through these steps, the server, device, and user work closely together to realize comprehensive and personalized healthcare support using an emotion engine.

[1266] Example 2

[1267] 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."

[1268] Conventional healthcare systems assess health risks based on a user's medical information and lifestyle data, but lack the ability to consider the user's emotional state. This results in low accuracy in health risk assessment and insufficient provision of personalized diagnoses and suggestions.

[1269] 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.

[1270] In this invention, the server includes means for collecting the user's medical information, symptoms, and lifestyle data, means for collecting the user's emotional data using a camera and microphone, means for storing and preprocessing the collected data, means for analyzing the preprocessed data and predicting future health risks using a generative AI model, means for analyzing the user's emotional data using an emotion engine and evaluating its relevance to the health state, means for generating a diagnosis and proposal based on the analysis results and notifying the user, and means for retransmitting the user's feedback to the server and retraining the generative AI model. This enables comprehensive health risk assessment that also takes emotional data into consideration, as well as the provision of individualized diagnoses and proposals.

[1271] "User" is the individual receiving a health risk assessment or diagnosis and providing medical information, lifestyle data, and emotional data.

[1272] "Medical information" refers to any information related to medical care, such as a user's medical history, medication history, and medical examination results.

[1273] "Symptom" means any abnormal physical or mental condition or illness experienced by a User.

[1274] "Lifestyle data" refers to information about a user's daily life, such as exercise, diet, sleep, smoking, and drinking.

[1275] "Emotional data" refers to information about a user's emotional state obtained through facial expressions, tone of voice, choice of words, etc.

[1276] "Means" refers to a method, machine, or software used to accomplish a particular purpose.

[1277] "Camera" refers to a device for capturing images and videos.

[1278] "Microphone" refers to a device for capturing sound.

[1279] "Storage" refers to accumulating collected data on a server or in local storage so that it can be used later.

[1280] "Preprocessing" refers to operations performed to transform collected data into a form suitable for analysis, including data cleansing, normalization, and filtering.

[1281] "Analysis" refers to the process of analyzing data to derive useful information and patterns.

[1282] A "generative AI model" refers to an artificial intelligence model that learns patterns from large amounts of data and automatically performs specific tasks.

[1283] An "emotion engine" refers to an algorithm or software that analyzes emotional data and outputs the results.

[1284] "Diagnosis" refers to assessing a user's health condition and risks based on their data and providing a medical judgment based on that assessment.

[1285] "Suggestion" refers to advice that provides specific guidelines for action or measures to the user based on the diagnostic results.

[1286] "Notification" refers to an action taken to inform the user of information (diagnostic results or suggestions) generated by the system.

[1287] "Feedback" refers to the user responding to the system with the results of the actions they take based on the suggestions.

[1288] "Retraining" refers to the process of using new data and feedback from users to retrain a generative AI model and improve its accuracy and capabilities.

[1289] MODE FOR CARRYING OUT THE INVENTION

[1290] This invention is a comprehensive healthcare management system that collects users' medical information, symptoms, lifestyle habits, and emotional data, and uses a generative AI model and emotion engine to assess the user's health risks and provide personalized diagnoses and recommendations. This system works in collaboration with three parties: devices (smartphones, tablets, wearable devices, etc.), a server, and the user.

[1291] Data collection

[1292] The device collects the user's medical information, symptoms, and lifestyle data (e.g., number of steps taken, heart rate, and sleep duration) from the wearable device, as well as food and exercise records entered by the user through an application installed on a smartphone or tablet.

[1293] The device also collects emotional data using a camera and microphone: the camera analyzes the user's facial expressions, and the microphone analyzes the tone of the voice to understand the user's emotional state.

[1294] For example, if a user inputs the foods and calories they ate for breakfast into a smartphone app, this data is stored locally on the device, and facial expression data is analyzed using the smartphone's camera to understand their emotional state.

[1295] Data transmission and storage

[1296] The device sends all collected data to a server via the internet, and all data is encrypted during transmission to protect privacy.

[1297] The server checks the integrity of the received data before storing it in the database. If any abnormal or missing values ​​are found, the server will supplement or correct them, thereby maintaining the accuracy of the data.

[1298] Data Analysis and Prediction

[1299] The server uses a generative AI model to analyze the pre-processed data, which learns the user's health and lifestyle patterns and predicts future health risks.

[1300] At the same time, an emotion engine is used to analyze the emotion data and assess the correlation between emotional states and health conditions, using deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[1301] Generate diagnostics and suggestions

[1302] The server then evaluates the user's health risk based on the results of the data analysis and generates a diagnosis and recommendations. For example, if the user's step count is low and their heart rate is high, it will determine that they are at high risk for cardiovascular disease. Based on this, it will recommend "walking 30 minutes a day" and "deep breathing exercises."

[1303] The generated proposal is sent from the server to the terminal.

[1304] Notifications and Feedback

[1305] The device notifies the user of suggestions and diagnostic results sent from the server, both in the form of alerts (pop-up notifications) and dashboards (detailed feedback).

[1306] The user accepts the suggestions and enters the results into the device, which then collects feedback.

[1307] Re-learning and assessment

[1308] The server re-analyzes the collected feedback data and re-trains the generative AI model, further improving the model's accuracy and increasing the reliability of future diagnoses and recommendations. Newly collected emotional data is also included in the re-training process.

[1309] Specific examples

[1310] For example, a user may input the foods and calories they ate for breakfast, and emotional data may include facial expression analysis results collected using a camera. All of this data is encrypted and sent to a server. The server analyzes this data, and if it detects a lack of exercise and high stress levels, it will diagnose a high risk of cardiovascular disease and suggest daily exercise goals and stress management methods.

[1311] Prompt Sentence Examples

[1312] "Based on the user's daily steps, heart rate, and dietary habits, evaluate emotional data, analyze stress levels, predict health risks, and generate prompts to suggest specific exercise goals and stress management methods to the user."

[1313] The system works in collaboration between the server, device, and user, leveraging an emotion engine and generative AI models to provide more comprehensive and personalized healthcare support.

[1314] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1315] Step 1:

[1316] Data collection

[1317] Users wear the wearable device, which automatically records medical information and lifestyle data (e.g., number of steps, heart rate, and sleep time).

[1318] Specific operation: The wearable device uses sensors to collect data in real time and transmits it to a device (smartphone or tablet) via Bluetooth or Wi-Fi.

[1319] Users enter their diet and exercise records into a smartphone app, for example, by inputting the foods they ate for breakfast and their calories.

[1320] The device stores the collected data locally, which is then sent to the server in the next step.

[1321] The device uses a camera and microphone to collect emotional data. The camera analyzes facial expressions and the microphone analyzes tone of voice. This emotional data is also stored locally.

[1322] Step 2:

[1323] Data transmission and storage

[1324] The device sends all collected data to a server via the internet, including encrypted user medical information, symptoms, lifestyle data, and emotional data.

[1325] Specific operation: The terminal transmits data overnight or at set time intervals, and encrypts the data during the transmission process.

[1326] The server checks the integrity of the data it receives and fills or corrects any inconsistencies or missing values. The output is a consistent dataset.

[1327] After checking the integrity, the server stores the data in a database, which is then used for analysis in the next step.

[1328] Step 3:

[1329] Data Analysis and Prediction

[1330] The server analyzes the stored pre-processed data, and the input is the user's consistent medical information, lifestyle data, and emotional data.

[1331] How it works: The generative AI model learns the user's health status and lifestyle patterns and predicts future health risks. The output is the predicted health risks.

[1332] The server analyzes the emotional data using an emotion engine. This analysis evaluates how the user's emotional state affects their health status. The output is data showing the relationship between emotional state and health status.

[1333] Step 4:

[1334] Generate diagnostics and suggestions

[1335] The server evaluates the user's health risk based on the data analysis results, and the input is data showing the relationship between predicted health risk and emotional state.

[1336] Specific behavior: The generative AI model performs a diagnosis and generates specific suggestions. For example, if a lack of exercise and high stress levels are detected, it will suggest daily walking and stress management methods. The output is a specific diagnosis and suggestion.

[1337] The generated proposal is sent to the terminal. The input is the diagnosis result and the proposal content, and the output is the proposal sent to the terminal.

[1338] Step 5:

[1339] Notifications and Feedback

[1340] The terminal notifies the user of the generated suggestions. The input is the diagnosis results and suggestions sent from the server.

[1341] Specific behavior: The device provides detailed feedback in the form of alerts and dashboards. The output is a notified suggestion to the user.

[1342] The user takes specific actions based on the suggestions and inputs the results into the terminal. The input is the result of the action taken.

[1343] Step 6:

[1344] Re-learning and assessment

[1345] The server re-parses the feedback data sent by the user. The input is the user's feedback data.

[1346] How it works: The generative AI model is retrained using feedback data. The output is a retrained generative AI model.

[1347] The server uses the retrained model to improve the accuracy of subsequent diagnoses and recommendations, and the output is improved diagnoses and recommendations.

[1348] (Application example 2)

[1349] 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."

[1350] Conventional healthcare management systems lack individualized health management and feedback, making it difficult to accurately provide users with the specific health programs and exercise suggestions they need. In addition, health support at physical stores is inconsistent, making it difficult to provide effective feedback in real time. Furthermore, there is a lack of a system in place to effectively utilize collected data, perform advanced analysis using generative AI models, and continuously predict health risks.

[1351] 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.

[1352] In this invention, the server includes a device that collects a user's medical information, symptoms, and lifestyle data; a means for storing and preprocessing the collected data; a means for analyzing the preprocessed data and predicting future health risks using a generative AI model; a means for generating a diagnosis and recommendation based on the analysis results and notifying the user; a means for sending user feedback back to the server and retraining the generative AI model; a means for collecting data from smart glasses or smartphones so that in-store staff can provide health management support to the user; and a means for providing individualized health programs and exercise recommendations to the user in-store. This enables more personalized health management and real-time feedback for users. It also enables consistent health support in physical stores, and through advanced analysis and continuous improvement using the generative AI model, it becomes possible to effectively predict and manage users' health risks.

[1353] "User's medical information" refers to information about the user's health condition, such as diagnostic results, prescription information, past medical history, and allergy information provided by a medical institution.

[1354] "Symptom" means any physical or mental symptom or sign of illness experienced by a User.

[1355] "Lifestyle data" refers to information about a user's daily activities and habits, including, for example, what they eat, how much sleep they get, and the frequency and type of exercise they do.

[1356] "Device" is a general term for devices that users use on a daily basis and that can collect and transmit data, such as smartphones, tablets, and wearable devices.

[1357] A "server" is a computer system that stores collected data and performs analysis and relearning.

[1358] "Preprocessing" refers to processes such as data cleansing and filtering to prepare collected data in an analyzable format.

[1359] "Generative AI model" is a general term for algorithmic models that are trained using deep learning and machine learning techniques to predict users' health risks.

[1360] "Health risk prediction" refers to analyzing future health conditions and predicting potential health problems based on collected data.

[1361] "Diagnosis" refers to assessing the user's health status based on the analysis results and identifying specific health problems.

[1362] "Suggestions" are specific advice that shows users the actions and improvements they should take to reduce health risks.

[1363] "Feedback" refers to input and responses from users, which are then collected again as data and used for analysis and model retraining.

[1364] "Retraining" is the process of retraining a generative AI model with new data from users to improve its prediction accuracy.

[1365] A "brick and mortar" is a location that provides health management services in a physical facility, such as a fitness center or gym.

[1366] "Staff" refers to the person in charge of providing health management and support to users at physical stores.

[1367] "Smart glasses" are glasses-type devices that display real-time information to the wearer and have the ability to collect data.

[1368] A "smartphone" is a portable multi-function device that can make calls, connect to the Internet, and operate applications.

[1369] A "wellness program" is an exercise and diet plan designed based on a user's health status and goals.

[1370] "Exercise Suggestions" refers to specific exercise or fitness activities recommended to you based on your health.

[1371] This invention is a comprehensive system for users to manage their health. It uses devices such as smartwatches, smartphones, and smart glasses to collect medical information, symptoms, lifestyle habits, and emotional data, and then analyzes the data on a server. Based on the analysis results, the system provides users with personalized health programs and exercise suggestions.

[1372] Hardware Configuration

[1373] The hardware configuration of the system is as follows:

[1374] Smartwatch: Collects data such as steps, heart rate, and sleep time.

[1375] Smart glasses: Collecting emotion data through facial expression analysis.

[1376] Smartphone: A device that aggregates data and sends it to the server.

[1377] Server: Stores data, analyzes it, and retrains the generative AI model.

[1378] Software Configuration

[1379] The software used in the system and its roles are as follows:

[1380] Flask: Used to implement server-side applications.

[1381] Generative AI models (e.g., TensorFlow and PyTorch) are used to analyze users' health risks.

[1382] Database (e.g. MySQL, PostgreSQL): Used to store user data.

[1383] Data collection and preprocessing

[1384] Data obtained from the user's smartwatch (e.g., number of steps, heart rate, sleep time) and facial expression data from the smart glasses are sent to a server via the smartphone. An application is installed on the smartphone, allowing the user to input medical information and lifestyle habits. This data is stored on the server and undergoes preprocessing, which includes data cleansing and formatting.

[1385] Data analysis

[1386] The server analyzes the collected data and uses a generative AI model to predict the user's health risks. Based on the analyzed data, specific recommendations are generated according to the user's current health status and predicted risks. The generative AI model uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[1387] Providing diagnostics and recommendations

[1388] Based on the analysis results, the server generates a diagnosis and suggestions for the user. For example, if the server detects a lack of exercise or a high stress level, it will notify the user of exercise suggestions such as "walking 30 minutes every day" or stress management methods such as "deep breathing exercises." The diagnosis and suggestions are provided to the user's smartphone in the form of notifications and a dashboard.

[1389] Retraining and feedback

[1390] By inputting feedback on the actions taken based on the user's suggestions into the device, the server re-analyzes the data and retrains the generative AI model, allowing the system to continuously improve its accuracy and provide more appropriate diagnoses and suggestions.

[1391] Specific examples

[1392] For example, when a user visits a sports gym, they wear a smartwatch and smart glasses. Heart rate and step count data are collected from the smartwatch, and facial expression data is collected from the smart glasses. The user enters their diet and lifestyle habits into their smartphone, and the data is sent to the server. After analysis, the server makes a specific suggestion, such as "Today's exercise should ideally be 20 minutes of running," and notifies the user's smartphone.

[1393] Prompt Sentence Examples

[1394] Please enter your medical information, lifestyle data, step count data (10,000 steps), heart rate, and facial expression data in the following format:

[1395] Medical information: {medical_data}

[1396] Lifestyle data: {lifestyle_data}

[1397] Step data: {step_data}

[1398] Heart rate: {heart_rate}

[1399] Emotion data: {emotion_data}"

[1400] This prompt is used as input to a generative AI model, which then uses it to generate health predictions and recommendations for the user.

[1401] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1402] Step 1:

[1403] Users wear smartwatches, smartphones, or smart glasses, and the devices begin collecting data.

[1404] Input: Step count, heart rate, sleep duration from smartwatch, facial expression data from smart glasses.

[1405] Output: Collected medical information, symptoms, lifestyle data, and emotional data.

[1406] Specific operation: As users go about their daily lives, the smartwatch automatically collects steps and heart rate, while the smart glasses automatically collect facial expression data.

[1407] Step 2:

[1408] The device transfers the collected data to a smartphone.

[1409] Input: Data from smartwatch and smart glasses.

[1410] Output: A set of data stored on the smartphone.

[1411] How it works: Smartwatches and smart glasses send data to your smartphone via Bluetooth.

[1412] Step 3:

[1413] Users enter medical information and lifestyle data using a smartphone app.

[1414] Input: Your medical information, diet, exercise records, etc.

[1415] Output: Complete dataset (medical information, symptoms, lifestyle data, emotion data).

[1416] What it does: The user opens the smartphone app and manually enters their food and exercise records.

[1417] Step 4:

[1418] The smartphone sends the collected data to a server via the internet.

[1419] Input: A set of data stored on your smartphone.

[1420] Output: Data stored on the server.

[1421] What it does: Your smartphone sends encrypted data over your internet connection and uploads it to a server.

[1422] Step 5:

[1423] The server stores the received data and performs preprocessing.

[1424] Input: Raw data received by the server.

[1425] Output: Preprocessed data (cleaned and formatted data).

[1426] Specific operation: The server performs data cleansing on the received data, such as filling in missing values, correcting outliers, and formatting.

[1427] Step 6:

[1428] The server analyzes the pre-processed data and uses a generative AI model to predict the user's health risks.

[1429] Input: Preprocessed data.

[1430] Output: Health risk prediction results.

[1431] How it works: The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze data and assess health risks using recurrent neural networks (RNNs) or convolutional neural networks (CNNs).

[1432] Step 7:

[1433] The server generates a diagnosis and suggestions based on the analysis results and notifies the user.

[1434] Input: Health risk prediction results.

[1435] Output: Diagnostic results and recommendations.

[1436] Specific operation: The server creates a specific action plan (e.g., walking 30 minutes every day) from the analysis results and sends it to the user's smartphone via the network.

[1437] Step 8:

[1438] The smartphone notifies the user of the diagnosis and suggestions from the server.

[1439] Input: Diagnostic results and suggestions from the server.

[1440] Output: User notification and dashboard display.

[1441] What it does: The phone displays information to the user through notification pop-ups and in-app dashboards.

[1442] Step 9:

[1443] The user takes action based on the suggestions and enters the results into their smartphone.

[1444] Input: The result of the user's action.

[1445] Output: Feedback data.

[1446] Specific actions: The user performs suggested actions such as exercise and stress management, and then enters the results (e.g., type and duration of exercise) into the smartphone app.

[1447] Step 10:

[1448] The smartphone sends feedback data to the server, which then retrains the generated AI model.

[1449] Input: Feedback data from smartphone.

[1450] Output: An updated generative AI model.

[1451] How it works: The smartphone sends feedback data to the server, which then uses this new data to retrain the generative AI model, improving diagnostic accuracy in future visits.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] [Fourth embodiment]

[1456] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1457] 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.

[1458] 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).

[1459] 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.

[1460] 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.

[1461] 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).

[1462] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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."

[1469] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: a terminal (smartphone, tablet, wearable device, etc.), a server, and the user.

[1470] System Overview

[1471] 1. Data Collection

[1472] The device collects users' medical information, symptoms, and lifestyle data, including step counts, heart rate, and sleep duration from the wearable device, as well as food logs and symptom reports from a smartphone app.

[1473] The terminal periodically synchronizes with the wearable device and prepares to send the collected data to the server.

[1474] 2. Data transmission and storage

[1475] The device sends the collected data to a server via the Internet, where it is encrypted and securely transmitted.

[1476] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[1477] 3. Data analysis and prediction

[1478] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks.

[1479] The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive and remedial measures.

[1480] 4. Generating Diagnoses and Recommendations

[1481] Based on the analysis results, the server diagnoses the user's health condition and generates suggestions for appropriate medical treatment and self-care.

[1482] The server sends the generated proposal to the terminal.

[1483] 5. Notifications and Feedback

[1484] The device notifies the user of the server's suggestions and diagnostic results, providing detailed feedback in the form of alerts and dashboards.

[1485] The user then takes action to improve their self-care and lifestyle habits based on the suggestions, and then enters the results back into the device.

[1486] 6. Re-learning and evaluation

[1487] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data.

[1488] The server adjusts the diagnosis and recommendations accordingly based on changes in the user's behavior and health status, providing more personalized support.

[1489] Specific examples

[1490] 1. Data Collection Example

[1491] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from a wearable device worn by the user.

[1492] Users enter details of their meals into a smartphone app, such as what they had for breakfast and their calorie intake.

[1493] 2. Examples of data transmission and storage

[1494] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[1495] 3. Examples of data analysis and prediction

[1496] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[1497] 4. Example of generating a diagnosis and a suggestion

[1498] The server diagnoses that "you need to increase your exercise" and suggests a daily exercise goal (e.g., 30 minutes of walking).

[1499] 5. Notification and Feedback Examples

[1500] The device will notify the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day."

[1501] The user begins exercising and enters the results into the device after one week.

[1502] 6. Re-learning and assessment examples

[1503] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[1504] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[1505] The processing flow will be explained below.

[1506] Step 1:

[1507] The device collects the user's medical information, symptoms, and lifestyle data. This includes data from wearable devices (e.g., steps taken, heart rate, sleep duration) and data input from smartphone apps (e.g., dietary details, exercise records). The device periodically acquires this data and temporarily stores it locally.

[1508] Step 2:

[1509] The data collected by the device is sent to a server over the internet, where it is encrypted to protect the user's privacy. The data is sent periodically, usually while connected to Wi-Fi.

[1510] Step 3:

[1511] The server receives the data sent from the device and stores it in a database. When storing the data, it checks for consistency and detects missing or outlier values. Data is supplemented or corrected as necessary.

[1512] Step 4:

[1513] The server analyzes the preprocessed data and uses a generative AI model to learn the user's health and lifestyle patterns. This analysis uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[1514] Step 5:

[1515] The server then predicts the user's health risk based on the analysis results. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise. This prediction is made using a generative AI model that derives future risk from past data.

[1516] Step 6:

[1517] The server generates a diagnosis and recommendations tailored to the user, including specific advice for exercise (e.g., 30 minutes of walking daily), dietary improvements, and stress management methods. The diagnosis and recommendations are personalized and customized for each user.

[1518] Step 7:

[1519] The server generates suggestions and sends diagnostic results to the device. The information is formatted in a user-friendly format, and the suggestions and diagnostic results are displayed on the device in notification or dashboard format.

[1520] Step 8:

[1521] The device displays notifications and suggestions from the server to the user. Specifically, alerts are displayed on the device screen and detailed feedback is provided in the form of a dashboard. Users can use this information to improve their self-care and lifestyle habits.

[1522] Step 9:

[1523] The user acts based on the suggestions from the server and inputs the results back into the device. For example, if the user takes a suggested walk, the device records the number of steps and time taken. The device also continuously inputs dietary information and other health-related data.

[1524] Step 10:

[1525] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[1526] Step 11:

[1527] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions.

[1528] These steps enable the server, terminals, and users to work together to achieve effective healthcare management.

[1529] Example 1

[1530] 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."

[1531] In conventional healthcare systems, the entire process from collection to analysis and feedback of users' medical information, symptoms, and lifestyle data was not integrated, resulting in insufficient coordination of individual data and feedback. As a result, there were issues with low accuracy of health predictions and suggestions for users, and an inability to provide personalized support. In addition, the safety and reliability of collected data was not ensured, and there was a risk of user data being leaked. There is a need for a comprehensive healthcare management system that can resolve these issues and manage users' health effectively and safely.

[1532] 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.

[1533] In this invention, the server includes a means for encrypting and transmitting collected data via the Internet, a means for storing the received data and performing preprocessing to complete missing values ​​and eliminate outliers, and a means for training a generative AI model using the preprocessed data to learn the user's health status and lifestyle patterns. This integrates the entire process from data collection to analysis, prediction, and feedback, making it possible to provide users with personalized health support in a safe and reliable manner.

[1534] A "terminal" is a device that collects a user's medical information, symptoms, and lifestyle data and transmits them to a server.

[1535] The "server" is a central system that stores and preprocesses collected data and performs data analysis and predictions using generative AI models.

[1536] "Collected Data" refers to a collection of data including a user's medical information, symptoms, and lifestyle data.

[1537] "Means for encrypting and transmitting data over the Internet" refers to the use of encryption technology to securely transmit data over the Internet.

[1538] "Preprocessing means for imputing missing values ​​and removing outliers" is a process for imputing missing data and removing outliers to improve data quality.

[1539] A "generative AI model" is an artificial intelligence model that learns a user's health condition and patterns based on past data and predicts future health risks.

[1540] A "deep learning algorithm" is a machine learning technique that uses large amounts of data to learn complex patterns and make predictions and classifications.

[1541] "Diagnosis and Suggestion" is an assessment of the user's health condition based on the analysis results, and provides advice on necessary medical procedures and lifestyle improvements.

[1542] "Feedback" refers to additional information and behavioral history collected from the user that the system uses to reevaluate and re-learn.

[1543] "Retraining" is the process of updating a generative AI model with new data to improve the accuracy of its predictions.

[1544] "Alert and dashboard format" refers to a notification method that visually presents important notifications and detailed feedback information to users.

[1545] The present invention is a comprehensive healthcare management system that collects, analyzes, and manages a user's medical information, symptoms, and lifestyle data. This system functions in cooperation with terminals (smartphones, tablets, wearable devices, etc.), a server, and users. An embodiment of this system will be described in detail below.

[1546] 1. Data Collection

[1547] The device uses a wearable device and a smartphone app to collect the user's medical information, symptoms, and lifestyle habits. Specifically, the following data is collected:

[1548] Data such as the number of steps taken, heart rate, and sleep time is acquired from wearable devices via wireless communication such as Bluetooth. For example, devices such as Fitbit and Apple Watch are used.

[1549] The smartphone app collects data on food records and symptom reports manually entered by users, specifically the types of food and calories consumed at breakfast.

[1550] 2. Data transmission and storage

[1551] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES, which ensures security during data transmission.

[1552] The server stores the received data in a database (e.g., MySQL or PostgreSQL). Because this data may contain missing values ​​or outliers, the server preprocesses the data. Specifically, it uses the Python libraries pandas and numpy to complete missing values ​​and remove outliers.

[1553] 3. Data analysis and prediction

[1554] The server uses the preprocessed data to train a generative AI model based on a deep learning algorithm (e.g., TensorFlow or PyTorch).

[1555] The server analyzes past data to learn the user's health and lifestyle patterns, which can then be used to predict future health risks (e.g., risk of heart disease).

[1556] The server uses a generative AI model to output prediction results and evaluate the risks the user will face in the future.

[1557] 4. Generating Diagnoses and Recommendations

[1558] The server then diagnoses the user's health condition based on the analysis results and generates appropriate medical treatment and self-care recommendations, including the following specific suggestions:

[1559] "People need to increase their physical activity, so we recommend 30 minutes of walking every day."

[1560] It is recommended to avoid high-calorie meals.

[1561] The generated proposals and diagnostic results are sent to the terminal.

[1562] 5. Notifications and Feedback

[1563] The device notifies the user of the server's suggestions and diagnostic results in the form of alerts and dashboards, providing detailed feedback to the user, which the user can use to improve their own care and lifestyle habits.

[1564] The user then takes action based on the suggestions and again enters the results (for example, whether or not they achieved 30 minutes of walking each day) into the device.

[1565] 6. Re-learning and evaluation

[1566] The server retrains the generative AI model based on user feedback data to improve its accuracy. Specifically, adding new data allows the model to adapt to the latest user data, enabling more accurate predictions and suggestions.

[1567] Prompt Sentence Examples

[1568] Below are some example prompts to input to the generative AI model:

[1569] "Analyze exercise data and dietary habits over the past month to predict future health risks for users."

[1570] "Based on the user's heart rate and step count data, assess their current health status and suggest necessary preventive measures."

[1571] Thus, the present invention is a system that provides individualized and effective healthcare support and assists users in managing their health by having the server, terminal, and user work together.

[1572] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1573] Step 1: Data collection

[1574] The device collects the user's medical information, symptoms, and lifestyle data. This input data includes step counts, heart rate, and sleep time from a wearable device, as well as food logs and symptom reports from a smartphone app.

[1575] Specifically, the device syncs with the wearable device via Bluetooth at a set time each day and collects all data. For example, the device syncs with the device at 8:00 a.m. to obtain the previous day's step count and heart rate data. The device also collects the breakfast information entered by the user into the smartphone app (e.g., a 200-calorie meal).

[1576] Input: Data from wearable devices and smartphone apps

[1577] Output: Collected user data

[1578] Step 2: Data transmission and storage

[1579] The device encrypts the collected data and sends it to a server via the Internet. Specifically, the data is encrypted using encryption technology such as AES. The server then stores the received data in a database (for example, MySQL or PostgreSQL).

[1580] Specifically, the device automatically encrypts all collected data at midnight every night and sends it to the server, which then checks the data for security and stores it in a database.

[1581] Input: Collected user data

[1582] Output: Data stored on the server (encrypted and security checked)

[1583] Step 3: Data Preprocessing

[1584] The server performs preprocessing on the received and stored data, such as filling in missing values ​​and removing outliers. Specifically, it cleans the data using Python's pandas and numpy.

[1585] Specifically, the server periodically retrieves the latest data from the database, and if there are any missing values, it fills them in with the average or median, and detects and deletes or corrects any outliers.

[1586] Input: Data stored on the server

[1587] Output: Preprocessed and clean data

[1588] Step 4: Data analysis and prediction

[1589] The server uses the preprocessed data to train a generative AI model that learns the user's health and lifestyle patterns, and uses deep learning algorithms (e.g., TensorFlow and PyTorch) to predict future health risks.

[1590] Specifically, once a week, the server batch-processes the preprocessed data and inputs it into the generative AI model to learn the user's patterns. For example, the model learns that the user is not physically active and outputs a prediction such as "future risk of heart disease increases by 15%."

[1591] Input: Preprocessed data

[1592] Output: Prediction of future health risks for the user

[1593] Step 5: Generate diagnostics and suggestions

[1594] The server then diagnoses the user's health condition based on the analysis results and generates specific medical and self-care recommendations, such as "recommended 30 minutes of walking every day."

[1595] Specifically, once the analysis is complete, the server immediately generates a diagnosis and a recommendation, which it then sends to the device, along with detailed instructions.

[1596] Input: User's future health risk prediction

[1597] Output: Diagnostic results and specific suggestions

[1598] Step 6: Notification and feedback

[1599] The device notifies the user of suggestions and diagnostic results from the server in the form of alerts and dashboards, providing detailed feedback.

[1600] Specifically, the device sends a notification from the server to the user every morning at 8:00. The user then takes action to improve their own health and lifestyle habits based on the notification and enters the results into the device. For example, the device will provide feedback that the user has achieved 30 minutes of walking every day for a week.

[1601] Input: Diagnostic results and specific suggestions

[1602] Output: User notification and user feedback data

[1603] Step 7: Retrain and evaluate

[1604] The server retrains the generative AI model based on user feedback data to improve prediction accuracy.

[1605] Specifically, the server retrieves new data every month, adds it to the generative AI model, and retrains it, allowing the model to adapt to the latest user data and make more accurate predictions and suggestions.

[1606] Input: User feedback data

[1607] Output: A modified and updated generative AI model

[1608] As described above, the system comprehensively manages the user's health and provides personalized support at each step.

[1609] (Application example 1)

[1610] 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."

[1611] The main purpose of conventional healthcare management systems was to collect users' medical information and lifestyle data and monitor their health status. However, it was difficult to detect sudden abnormalities or acute illnesses early, making it difficult to respond adequately. In addition, there were few ways to notify appropriate parties of an emergency after an abnormality was detected. This resulted in a lack of prompt and appropriate response in cases where the user's health status suddenly changed.

[1612] 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.

[1613] In this invention, the server includes a terminal that collects the user's medical information, symptoms, and lifestyle data, a means for storing and preprocessing the collected data, a means for analyzing the preprocessed data and predicting future health risks using a generative AI model, a means for generating a diagnosis and proposal based on the analysis results and notifying the user, a means for sending the user's feedback again to the server and retraining the generative AI model, a means for detecting abnormalities from the analyzed data and sending emergency notifications, and a means for sending notifications to family members and medical professionals. This enables detailed monitoring of the user's health status as well as rapid detection of abnormalities and emergency notification to relevant parties.

[1614] "User" refers to an individual who uses the healthcare management system.

[1615] "Medical Information" refers to data related to your medical care, such as your medical history, medical records, and test results.

[1616] "Symptoms" refers to any physical or mental abnormality or discomfort experienced by the User.

[1617] "Lifestyle data" refers to data related to the user's daily activities and habits, such as diet, exercise, and sleep.

[1618] "Terminal" means a device for collecting a user's medical information, symptoms, and lifestyle data, including smartphones, tablets, and wearable devices.

[1619] "Server" refers to the computer system that stores, pre-processes, and analyzes collected data.

[1620] "Preprocessing" refers to the process of examining and correcting data prior to data analysis, such as filling in missing values ​​and removing outliers.

[1621] A "generative AI model" refers to an artificial intelligence model that uses collected and preprocessed data to learn a user's health condition and lifestyle patterns and predict future health risks.

[1622] "Analysis results" refers to the diagnostic and predictive results obtained by a generative AI model based on preprocessed data.

[1623] "Diagnosis" refers to the process of assessing a user's health status based on the analysis results and determining the need for specific medical interventions or self-care.

[1624] "Suggestions" refer to medical procedures and lifestyle improvements recommended to users based on diagnostic results.

[1625] "Notification means" refers to a method or device for communicating diagnoses and suggestions to the user.

[1626] "Feedback" refers to the user's reactions to the diagnosis or suggestions provided and the actual results of their actions.

[1627] "Retraining" refers to the process of retraining a generative AI model based on newly provided feedback data to improve its prediction accuracy.

[1628] "Abnormal" refers to abnormal values ​​or patterns in predicted health or lifestyle data that are outside the normal range.

[1629] "Emergency notification" refers to warnings and cautionary information that are immediately sent to relevant parties when an abnormality is detected.

[1630] "Family Members" refers to individuals who are close relatives of a User and who are eligible to receive Emergency Notifications.

[1631] "Healthcare Professional" refers to doctors, nurses, and other healthcare professionals who are responsible for managing and improving a user's health.

[1632] This invention is a comprehensive healthcare management system that collects, analyzes, and manages users' medical information, symptoms, and lifestyle data. This system works in cooperation with three parties: terminals (smartphones, tablets, wearable devices, etc.), a server, and the user.

[1633] System Overview

[1634] 1. Data Collection

[1635] The device collects the user's medical information, symptoms, and lifestyle data. This data includes steps, heart rate, and sleep time from the wearable device, as well as food logs and symptom reports from a smartphone app. The device periodically syncs with the wearable device and prepares to send the collected data to a server.

[1636] 2. Data transmission and storage

[1637] The device sends the collected data to a server via the internet. The data is encrypted and sent securely. The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers.

[1638] 3. Data analysis and prediction

[1639] The server uses the preprocessed data to train a generative AI model, which can learn the user's health and lifestyle patterns and predict future health risks. The server uses deep learning algorithms to assess the user's health status and recommend necessary preventive or remedial measures.

[1640] 4. Generating Diagnoses and Recommendations

[1641] The server then uses the analysis results to diagnose the user's health and generate appropriate medical and self-care recommendations. If an abnormality is detected from the analyzed data, the server has a built-in mechanism for sending emergency notifications to family members and medical personnel. The server then sends the generated recommendations to the device.

[1642] 5. Notifications and Feedback

[1643] The device notifies the user of the suggestions and diagnostic results from the server. Notifications are provided in the form of alerts and dashboards, providing detailed feedback. The user then takes action to improve their own care and lifestyle based on the suggestions, and enters the results back into the device.

[1644] 6. Re-learning and evaluation

[1645] The server improves the accuracy of predictions by retraining the generative AI model based on user feedback data, and adjusts the diagnosis and recommendations in a timely manner according to changes in the user's behavior and health status, providing more personalized support.

[1646] Specific examples

[1647] 1. Data Collection Example

[1648] The terminal (smartphone) collects data on the number of steps taken per day (10,000 steps) and heart rate from the wearable device worn by the user. The user then inputs details of their meals into the smartphone app, such as the foods they ate for breakfast and their calorie intake.

[1649] 2. Examples of data transmission and storage

[1650] The device sends the data collected overnight to a server, where it is stored in a database after a security check.

[1651] 3. Examples of data analysis and prediction

[1652] The server analyzes data from a month to detect whether the user is physically inactive, and uses a generative AI model to predict whether the user is at increased risk of cardiovascular disease in the future.

[1653] 4. Example of generating a diagnosis and a suggestion

[1654] The server will diagnose that "you need to increase your exercise" and suggest a daily exercise goal (e.g., 30 minutes of walking). If an abnormality is detected, such as an "abnormally high heart rate," an emergency notification will be sent to family members or medical personnel.

[1655] 5. Notification and Feedback Examples

[1656] The device notifies the user, "You are at high risk of cardiovascular disease, so we recommend walking 30 minutes every day." The user starts exercising and enters the results into the device after one week.

[1657] 6. Re-learning and assessment examples

[1658] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[1659] Prompt Sentence Examples

[1660] An example of a prompt to input to a generative AI model could be, "Please create an application that collects the user's health data and sends an emergency notification if an abnormality is detected."

[1661] In this way, the present invention provides effective personalized healthcare support by having the server, terminal, and user work together to help users manage their health.

[1662] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1663] Step 1:

[1664] Data collection:

[1665] The device syncs with the user's wearable device to collect medical information, symptoms, and lifestyle data, such as the number of steps taken, heart rate, and sleep time. It receives sensor data from the wearable device as input and stores the data in local storage.

[1666] Step 2:

[1667] Sending data:

[1668] The device sends the collected data to the server via the Internet. The data is encrypted and sent through a secure communication channel. The input is data stored in the device's local storage and sent to the server. The output is the data transferred to the server.

[1669] Step 3:

[1670] Data storage and pre-processing:

[1671] The server stores the received data in a database and performs preprocessing such as filling in missing values ​​and eliminating outliers. It receives user data sent as input and stores it in a database. The data is cleansed during the preprocessing process, and the output is preprocessed data.

[1672] Step 4:

[1673] Data analysis and prediction:

[1674] The server uses the preprocessed data to train a generative AI model to predict the user's health risk. The preprocessed data is used as input and fed into the generative AI model. The output is a health status assessment result and future health risk prediction data.

[1675] Step 5:

[1676] Generate diagnostics and suggestions:

[1677] The server diagnoses the user's health condition based on the analysis results and generates appropriate medical interventions and self-care suggestions. If an abnormality is detected, it sends an emergency notification to family members and medical professionals. It receives analysis result data as input and generates diagnoses and suggestions. The output is suggestion data and notification information.

[1678] Step 6:

[1679] Notifications and Feedback:

[1680] The device notifies the user of suggestions and diagnostic results from the server. The user takes action to improve their self-care and lifestyle habits based on the suggestions and enters the results into the device. The device receives suggestions and diagnostic result data as input and notifies the user. The output is the user's behavioral data and feedback.

[1681] Step 7:

[1682] Relearn and assess:

[1683] The server retrains the generative AI model based on user feedback data to improve prediction accuracy. It receives newly collected feedback data as input and retrains the generative AI model. The output is an updated generative AI model.

[1684] This provides users with more precise and personalized support at every step of their health management journey.

[1685] 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.

[1686] This invention is a comprehensive healthcare management system that combines a user's medical information, symptoms, and lifestyle data with an emotion engine that recognizes the user's emotions. This system works in cooperation with the terminal (smartphone, tablet, wearable device, etc.), server, and user to comprehensively evaluate the user's health risks and condition.

[1687] System Overview

[1688] 1. Data Collection

[1689] The device collects the user's medical information, symptoms, lifestyle data, and emotional data. Medical information and lifestyle data include steps, heart rate, and sleep time from the wearable device, and food and exercise records from a smartphone app. Emotional data is collected using the camera and microphone on the smartphone and wearable device.

[1690] The terminal periodically synchronizes with the wearable device and prepares locally stored data for transmission to the server.

[1691] 2. Data transmission and storage

[1692] The data collected by the device is sent to a server via the Internet. To protect privacy, the data is encrypted before transmission.

[1693] The server stores the received data in a database. When storing the data, it checks for consistency and fills in or corrects missing or outlier values.

[1694] 3. Data analysis and prediction

[1695] The server analyzes the preprocessed data. It uses a generative AI model to learn the user's health status and lifestyle patterns. At the same time, it uses an emotion engine to analyze the user's emotional data and evaluate its relevance to their health status. This analysis uses deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[1696] 4. Generating Diagnoses and Recommendations

[1697] The server predicts the user's health risks based on the analysis results. It combines information obtained from both health data and emotional data to generate personalized diagnoses and recommendations. For example, it predicts the risk of cardiovascular disease based on data on lack of exercise and emotional data on high stress levels, and provides specific advice on stress management and exercise.

[1698] The server sends the generated proposal to the terminal.

[1699] 5. Notifications and Feedback

[1700] The device will notify the user of suggestions and diagnostic results from the server, in the form of alerts and dashboards, providing detailed feedback to the user.

[1701] Users act on the suggestions and enter their results into the device, which allows for continuous data collection.

[1702] 6. Re-learning and evaluation

[1703] The server retrains the generative AI model based on user feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. The retraining process also uses newly collected emotional data, enabling the next-best suggestions to be made based on the user's emotional state.

[1704] Specific examples

[1705] 1. Data Collection Example

[1706] The device (smartphone) collects the number of steps taken per day (e.g., 10,000 steps) and heart rate from the user's wearable device, and simultaneously analyzes facial expressions using the smartphone's camera to collect emotional data.

[1707] Users enter their meal details into a smartphone app, recording, for example, the foods they ate for breakfast and their calorie intake.

[1708] 2. Examples of data transmission and storage

[1709] The device sends the data collected at night to a server, where it undergoes a security check and is stored in a database.

[1710] 3. Examples of data analysis and prediction

[1711] The server analyzes a month's worth of data and detects that the user is not exercising enough, while the emotion engine recognizes high stress levels. A generative AI model is used to predict the risk of cardiovascular disease.

[1712] 4. Example of generating a diagnosis and a suggestion

[1713] The server diagnoses that "you need to increase your exercise and stress management is important," and suggests daily exercise goals (e.g., walking 30 minutes a day) and stress management methods (e.g., deep breathing exercises and yoga).

[1714] 5. Notification and Feedback Examples

[1715] The device notifies the user, "Because you are at high risk of cardiovascular disease, we recommend that you walk for 30 minutes every day and practice deep breathing exercises."

[1716] The user performs stress management and exercise and enters the results into the device.

[1717] 6. Re-learning and assessment examples

[1718] The server updates the generative AI model based on the new data collected, improving its accuracy, which leads to better diagnoses and recommendations in the future.

[1719] In this way, the present invention provides more comprehensive and personalized healthcare support by linking the server, terminal, and user and using an emotion engine.

[1720] The processing flow will be explained below.

[1721] Step 1:

[1722] The device collects the user's medical information, symptoms, lifestyle habits, and emotional data. It obtains data on the number of steps, heart rate, and sleep time from the wearable device, and collects dietary and exercise records from a smartphone app. It also uses a camera and microphone to analyze the user's facial expressions and tone of voice to collect emotional data.

[1723] Step 2:

[1724] The device encrypts the collected data (medical data, lifestyle data, emotional data) and sends it to a server via the Internet. Data transmission uses a secure communication protocol to protect privacy.

[1725] Step 3:

[1726] The server receives the data sent from the terminal. The received data is checked for consistency before being saved in the database. If missing or abnormal values ​​are detected, they are supplemented or corrected.

[1727] Step 4:

[1728] The server begins analysis based on the preprocessing results. A generative AI model is used to learn the user's health status and lifestyle patterns. At the same time, the emotion engine analyzes the emotion data and evaluates the correlation between the emotional state and health data. Deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN) are used in this process.

[1729] Step 5:

[1730] The server then uses the analysis results to predict the user's future health risks. For example, if data on lack of exercise and high stress levels are detected, it predicts the risk of cardiovascular disease. This prediction is made using a generative AI model.

[1731] Step 6:

[1732] The server performs a comprehensive assessment of the user's health and emotional state and generates specific diagnoses and suggestions, such as advice on increasing exercise (e.g., walking 30 minutes daily) and stress management methods (e.g., deep breathing exercises and yoga).

[1733] Step 7:

[1734] The server generates diagnostics and sends recommendations to the device, formatting the information in a user-friendly format (notifications and dashboards).

[1735] Step 8:

[1736] The device receives notifications and suggestions from the server and displays them to the user. Specifically, it displays alerts on the device screen and provides detailed feedback in the form of a dashboard, which the user can use to improve their self-care and lifestyle habits.

[1737] Step 9:

[1738] The user acts based on the suggestions from the server and inputs the results back into the device. For example, the number of steps and time taken when carrying out the suggested walking can be recorded. Changes in emotions and stress levels can also be input.

[1739] Step 10:

[1740] The device will then send any new feedback data collected from the user back to the server, allowing the server to re-analyze the data based on the latest data.

[1741] Step 11:

[1742] The server retrains the generative AI model based on newly acquired feedback data, improving the model's accuracy and increasing the reliability of future diagnoses and suggestions. During retraining, newly collected emotional data is also used to provide optimal suggestions based on the user's emotional state.

[1743] Through these steps, the server, device, and user work closely together to realize comprehensive and personalized healthcare support using an emotion engine.

[1744] Example 2

[1745] 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."

[1746] Conventional healthcare systems assess health risks based on a user's medical information and lifestyle data, but lack the ability to consider the user's emotional state. This results in low accuracy in health risk assessment and insufficient provision of personalized diagnoses and suggestions.

[1747] 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.

[1748] In this invention, the server includes means for collecting the user's medical information, symptoms, and lifestyle data, means for collecting the user's emotional data using a camera and microphone, means for storing and preprocessing the collected data, means for analyzing the preprocessed data and predicting future health risks using a generative AI model, means for analyzing the user's emotional data using an emotion engine and evaluating its relevance to the health state, means for generating a diagnosis and proposal based on the analysis results and notifying the user, and means for retransmitting the user's feedback to the server and retraining the generative AI model. This enables comprehensive health risk assessment that also takes emotional data into consideration, as well as the provision of individualized diagnoses and proposals.

[1749] "User" is the individual receiving a health risk assessment or diagnosis and providing medical information, lifestyle data, and emotional data.

[1750] "Medical information" refers to any information related to medical care, such as a user's medical history, medication history, and medical examination results.

[1751] "Symptom" means any abnormal physical or mental condition or illness experienced by a User.

[1752] "Lifestyle data" refers to information about a user's daily life, such as exercise, diet, sleep, smoking, and drinking.

[1753] "Emotional data" refers to information about a user's emotional state obtained through facial expressions, tone of voice, choice of words, etc.

[1754] "Means" refers to a method, machine, or software used to accomplish a particular purpose.

[1755] "Camera" refers to a device for capturing images and videos.

[1756] "Microphone" refers to a device for capturing sound.

[1757] "Storage" refers to accumulating collected data on a server or in local storage so that it can be used later.

[1758] "Preprocessing" refers to operations performed to transform collected data into a form suitable for analysis, including data cleansing, normalization, and filtering.

[1759] "Analysis" refers to the process of analyzing data to derive useful information and patterns.

[1760] A "generative AI model" refers to an artificial intelligence model that learns patterns from large amounts of data and automatically performs specific tasks.

[1761] An "emotion engine" refers to an algorithm or software that analyzes emotional data and outputs the results.

[1762] "Diagnosis" refers to assessing a user's health condition and risks based on their data and providing a medical judgment based on that assessment.

[1763] "Suggestion" refers to advice that provides specific guidelines for action or measures to the user based on the diagnostic results.

[1764] "Notification" refers to an action taken to inform the user of information (diagnostic results or suggestions) generated by the system.

[1765] "Feedback" refers to the user responding to the system with the results of the actions they take based on the suggestions.

[1766] "Retraining" refers to the process of using new data and feedback from users to retrain a generative AI model and improve its accuracy and capabilities.

[1767] MODE FOR CARRYING OUT THE INVENTION

[1768] This invention is a comprehensive healthcare management system that collects users' medical information, symptoms, lifestyle habits, and emotional data, and uses a generative AI model and emotion engine to assess the user's health risks and provide personalized diagnoses and recommendations. This system works in collaboration with three parties: devices (smartphones, tablets, wearable devices, etc.), a server, and the user.

[1769] Data collection

[1770] The device collects the user's medical information, symptoms, and lifestyle data (e.g., number of steps taken, heart rate, and sleep duration) from the wearable device, as well as food and exercise records entered by the user through an application installed on a smartphone or tablet.

[1771] The device also collects emotional data using a camera and microphone: the camera analyzes the user's facial expressions, and the microphone analyzes the tone of the voice to understand the user's emotional state.

[1772] For example, if a user inputs the foods and calories they ate for breakfast into a smartphone app, this data is stored locally on the device, and facial expression data is analyzed using the smartphone's camera to understand their emotional state.

[1773] Data transmission and storage

[1774] The device sends all collected data to a server via the internet, and all data is encrypted during transmission to protect privacy.

[1775] The server checks the integrity of the received data before storing it in the database. If any abnormal or missing values ​​are found, the server will supplement or correct them, thereby maintaining the accuracy of the data.

[1776] Data Analysis and Prediction

[1777] The server uses a generative AI model to analyze the pre-processed data, which learns the user's health and lifestyle patterns and predicts future health risks.

[1778] At the same time, an emotion engine is used to analyze the emotion data and assess the correlation between emotional states and health conditions, using deep learning algorithms such as recurrent neural networks (RNNs) and convolutional neural networks (CNNs).

[1779] Generate diagnostics and suggestions

[1780] The server then evaluates the user's health risk based on the results of the data analysis and generates a diagnosis and recommendations. For example, if the user's step count is low and their heart rate is high, it will determine that they are at high risk for cardiovascular disease. Based on this, it will recommend "walking 30 minutes a day" and "deep breathing exercises."

[1781] The generated proposal is sent from the server to the terminal.

[1782] Notifications and Feedback

[1783] The device notifies the user of suggestions and diagnostic results sent from the server, both in the form of alerts (pop-up notifications) and dashboards (detailed feedback).

[1784] The user accepts the suggestions and enters the results into the device, which then collects feedback.

[1785] Re-learning and assessment

[1786] The server re-analyzes the collected feedback data and re-trains the generative AI model, further improving the model's accuracy and increasing the reliability of future diagnoses and recommendations. Newly collected emotional data is also included in the re-training process.

[1787] Specific examples

[1788] For example, a user may input the foods and calories they ate for breakfast, and emotional data may include facial expression analysis results collected using a camera. All of this data is encrypted and sent to a server. The server analyzes this data, and if it detects a lack of exercise and high stress levels, it will diagnose a high risk of cardiovascular disease and suggest daily exercise goals and stress management methods.

[1789] Prompt Sentence Examples

[1790] "Based on the user's daily steps, heart rate, and dietary habits, evaluate emotional data, analyze stress levels, predict health risks, and generate prompts to suggest specific exercise goals and stress management methods to the user."

[1791] The system works in collaboration between the server, device, and user, leveraging an emotion engine and generative AI models to provide more comprehensive and personalized healthcare support.

[1792] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1793] Step 1:

[1794] Data collection

[1795] Users wear the wearable device, which automatically records medical information and lifestyle data (e.g., number of steps, heart rate, and sleep time).

[1796] Specific operation: The wearable device uses sensors to collect data in real time and transmits it to a device (smartphone or tablet) via Bluetooth or Wi-Fi.

[1797] Users enter their diet and exercise records into a smartphone app, for example, by inputting the foods they ate for breakfast and their calories.

[1798] The device stores the collected data locally, which is then sent to the server in the next step.

[1799] The device uses a camera and microphone to collect emotional data. The camera analyzes facial expressions and the microphone analyzes tone of voice. This emotional data is also stored locally.

[1800] Step 2:

[1801] Data transmission and storage

[1802] The device sends all collected data to a server via the internet, including encrypted user medical information, symptoms, lifestyle data, and emotional data.

[1803] Specific operation: The terminal transmits data overnight or at set time intervals, and encrypts the data during the transmission process.

[1804] The server checks the integrity of the data it receives and fills or corrects any inconsistencies or missing values. The output is a consistent dataset.

[1805] After checking the integrity, the server stores the data in a database, which is then used for analysis in the next step.

[1806] Step 3:

[1807] Data Analysis and Prediction

[1808] The server analyzes the stored pre-processed data, and the input is the user's consistent medical information, lifestyle data, and emotional data.

[1809] How it works: The generative AI model learns the user's health status and lifestyle patterns and predicts future health risks. The output is the predicted health risks.

[1810] The server analyzes the emotional data using an emotion engine. This analysis evaluates how the user's emotional state affects their health status. The output is data showing the relationship between emotional state and health status.

[1811] Step 4:

[1812] Generate diagnostics and suggestions

[1813] The server evaluates the user's health risk based on the data analysis results, and the input is data showing the relationship between predicted health risk and emotional state.

[1814] Specific behavior: The generative AI model performs a diagnosis and generates specific suggestions. For example, if a lack of exercise and high stress levels are detected, it will suggest daily walking and stress management methods. The output is a specific diagnosis and suggestion.

[1815] The generated proposal is sent to the terminal. The input is the diagnosis result and the proposal content, and the output is the proposal sent to the terminal.

[1816] Step 5:

[1817] Notifications and Feedback

[1818] The terminal notifies the user of the generated suggestions. The input is the diagnosis results and suggestions sent from the server.

[1819] Specific behavior: The device provides detailed feedback in the form of alerts and dashboards. The output is a notified suggestion to the user.

[1820] The user takes specific actions based on the suggestions and inputs the results into the terminal. The input is the result of the action taken.

[1821] Step 6:

[1822] Re-learning and assessment

[1823] The server re-parses the feedback data sent by the user. The input is the user's feedback data.

[1824] How it works: The generative AI model is retrained using feedback data. The output is a retrained generative AI model.

[1825] The server uses the retrained model to improve the accuracy of subsequent diagnoses and recommendations, and the output is improved diagnoses and recommendations.

[1826] (Application example 2)

[1827] 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."

[1828] Conventional healthcare management systems lack individualized health management and feedback, making it difficult to accurately provide users with the specific health programs and exercise suggestions they need. In addition, health support at physical stores is inconsistent, making it difficult to provide effective feedback in real time. Furthermore, there is a lack of a system in place to effectively utilize collected data, perform advanced analysis using generative AI models, and continuously predict health risks.

[1829] 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.

[1830] In this invention, the server includes a device that collects a user's medical information, symptoms, and lifestyle data; a means for storing and preprocessing the collected data; a means for analyzing the preprocessed data and predicting future health risks using a generative AI model; a means for generating a diagnosis and recommendation based on the analysis results and notifying the user; a means for sending user feedback back to the server and retraining the generative AI model; a means for collecting data from smart glasses or smartphones so that in-store staff can provide health management support to the user; and a means for providing individualized health programs and exercise recommendations to the user in-store. This enables more personalized health management and real-time feedback for users. It also enables consistent health support in physical stores, and through advanced analysis and continuous improvement using the generative AI model, it becomes possible to effectively predict and manage users' health risks.

[1831] "User's medical information" refers to information about the user's health condition, such as diagnostic results, prescription information, past medical history, and allergy information provided by a medical institution.

[1832] "Symptom" means any physical or mental symptom or sign of illness experienced by a User.

[1833] "Lifestyle data" refers to information about a user's daily activities and habits, including, for example, what they eat, how much sleep they get, and the frequency and type of exercise they do.

[1834] "Device" is a general term for devices that users use on a daily basis and that can collect and transmit data, such as smartphones, tablets, and wearable devices.

[1835] A "server" is a computer system that stores collected data and performs analysis and relearning.

[1836] "Preprocessing" refers to processes such as data cleansing and filtering to prepare collected data in an analyzable format.

[1837] "Generative AI model" is a general term for algorithmic models that are trained using deep learning and machine learning techniques to predict users' health risks.

[1838] "Health risk prediction" refers to analyzing future health conditions and predicting potential health problems based on collected data.

[1839] "Diagnosis" refers to assessing the user's health status based on the analysis results and identifying specific health problems.

[1840] "Suggestions" are specific advice that shows users the actions and improvements they should take to reduce health risks.

[1841] "Feedback" refers to input and responses from users, which are then collected again as data and used for analysis and model retraining.

[1842] "Retraining" is the process of retraining a generative AI model with new data from users to improve its prediction accuracy.

[1843] A "brick and mortar" is a location that provides health management services in a physical facility, such as a fitness center or gym.

[1844] "Staff" refers to the person in charge of providing health management and support to users at physical stores.

[1845] "Smart glasses" are glasses-type devices that display real-time information to the wearer and have the ability to collect data.

[1846] A "smartphone" is a portable multi-function device that can make calls, connect to the Internet, and operate applications.

[1847] A "wellness program" is an exercise and diet plan designed based on a user's health status and goals.

[1848] "Exercise Suggestions" refers to specific exercise or fitness activities recommended to you based on your health.

[1849] This invention is a comprehensive system for users to manage their health. It uses devices such as smartwatches, smartphones, and smart glasses to collect medical information, symptoms, lifestyle habits, and emotional data, and then analyzes the data on a server. Based on the analysis results, the system provides users with personalized health programs and exercise suggestions.

[1850] Hardware Configuration

[1851] The hardware configuration of the system is as follows:

[1852] Smartwatch: Collects data such as steps, heart rate, and sleep time.

[1853] Smart glasses: Collecting emotion data through facial expression analysis.

[1854] Smartphone: A device that aggregates data and sends it to the server.

[1855] Server: Stores data, analyzes it, and retrains the generative AI model.

[1856] Software Configuration

[1857] The software used in the system and its roles are as follows:

[1858] Flask: Used to implement server-side applications.

[1859] Generative AI models (e.g., TensorFlow and PyTorch) are used to analyze users' health risks.

[1860] Database (e.g. MySQL, PostgreSQL): Used to store user data.

[1861] Data collection and preprocessing

[1862] Data obtained from the user's smartwatch (e.g., number of steps, heart rate, sleep time) and facial expression data from the smart glasses are sent to a server via the smartphone. An application is installed on the smartphone, allowing the user to input medical information and lifestyle habits. This data is stored on the server and undergoes preprocessing, which includes data cleansing and formatting.

[1863] Data analysis

[1864] The server analyzes the collected data and uses a generative AI model to predict the user's health risks. Based on the analyzed data, specific recommendations are generated according to the user's current health status and predicted risks. The generative AI model uses deep learning algorithms such as recurrent neural networks (RNN) and convolutional neural networks (CNN).

[1865] Providing diagnostics and recommendations

[1866] Based on the analysis results, the server generates a diagnosis and suggestions for the user. For example, if the server detects a lack of exercise or a high stress level, it will notify the user of exercise suggestions such as "walking 30 minutes every day" or stress management methods such as "deep breathing exercises." The diagnosis and suggestions are provided to the user's smartphone in the form of notifications and a dashboard.

[1867] Retraining and feedback

[1868] By inputting feedback on the actions taken based on the user's suggestions into the device, the server re-analyzes the data and retrains the generative AI model, allowing the system to continuously improve its accuracy and provide more appropriate diagnoses and suggestions.

[1869] Specific examples

[1870] For example, when a user visits a sports gym, they wear a smartwatch and smart glasses. Heart rate and step count data are collected from the smartwatch, and facial expression data is collected from the smart glasses. The user enters their diet and lifestyle habits into their smartphone, and the data is sent to the server. After analysis, the server makes a specific suggestion, such as "Today's exercise should ideally be 20 minutes of running," and notifies the user's smartphone.

[1871] Prompt Sentence Examples

[1872] Please enter your medical information, lifestyle data, step count data (10,000 steps), heart rate, and facial expression data in the following format:

[1873] Medical information: {medical_data}

[1874] Lifestyle data: {lifestyle_data}

[1875] Step data: {step_data}

[1876] Heart rate: {heart_rate}

[1877] Emotion data: {emotion_data}"

[1878] This prompt is used as input to a generative AI model, which then uses it to generate health predictions and recommendations for the user.

[1879] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1880] Step 1:

[1881] Users wear smartwatches, smartphones, or smart glasses, and the devices begin collecting data.

[1882] Input: Step count, heart rate, sleep duration from smartwatch, facial expression data from smart glasses.

[1883] Output: Collected medical information, symptoms, lifestyle data, and emotional data.

[1884] Specific operation: As users go about their daily lives, the smartwatch automatically collects steps and heart rate, while the smart glasses automatically collect facial expression data.

[1885] Step 2:

[1886] The device transfers the collected data to a smartphone.

[1887] Input: Data from smartwatch and smart glasses.

[1888] Output: A set of data stored on the smartphone.

[1889] How it works: Smartwatches and smart glasses send data to your smartphone via Bluetooth.

[1890] Step 3:

[1891] Users enter medical information and lifestyle data using a smartphone app.

[1892] Input: Your medical information, diet, exercise records, etc.

[1893] Output: Complete dataset (medical information, symptoms, lifestyle data, emotion data).

[1894] What it does: The user opens the smartphone app and manually enters their food and exercise records.

[1895] Step 4:

[1896] The smartphone sends the collected data to a server via the internet.

[1897] Input: A set of data stored on your smartphone.

[1898] Output: Data stored on the server.

[1899] What it does: Your smartphone sends encrypted data over your internet connection and uploads it to a server.

[1900] Step 5:

[1901] The server stores the received data and performs preprocessing.

[1902] Input: Raw data received by the server.

[1903] Output: Preprocessed data (cleaned and formatted data).

[1904] Specific operation: The server performs data cleansing on the received data, such as filling in missing values, correcting outliers, and formatting.

[1905] Step 6:

[1906] The server analyzes the pre-processed data and uses a generative AI model to predict the user's health risks.

[1907] Input: Preprocessed data.

[1908] Output: Health risk prediction results.

[1909] How it works: The server uses generative AI models (e.g., TensorFlow or PyTorch) to analyze data and assess health risks using recurrent neural networks (RNNs) or convolutional neural networks (CNNs).

[1910] Step 7:

[1911] The server generates a diagnosis and suggestions based on the analysis results and notifies the user.

[1912] Input: Health risk prediction results.

[1913] Output: Diagnostic results and recommendations.

[1914] Specific operation: The server creates a specific action plan (e.g., walking 30 minutes every day) from the analysis results and sends it to the user's smartphone via the network.

[1915] Step 8:

[1916] The smartphone notifies the user of the diagnosis and suggestions from the server.

[1917] Input: Diagnostic results and suggestions from the server.

[1918] Output: User notification and dashboard display.

[1919] What it does: The phone displays information to the user through notification pop-ups and in-app dashboards.

[1920] Step 9:

[1921] The user takes action based on the suggestions and enters the results into their smartphone.

[1922] Input: The result of the user's action.

[1923] Output: Feedback data.

[1924] Specific actions: The user performs suggested actions such as exercise and stress management, and then enters the results (e.g., type and duration of exercise) into the smartphone app.

[1925] Step 10:

[1926] The smartphone sends feedback data to the server, which then retrains the generated AI model.

[1927] Input: Feedback data from smartphone.

[1928] Output: An updated generative AI model.

[1929] How it works: The smartphone sends feedback data to the server, which then uses this new data to retrain the generative AI model, improving diagnostic accuracy in future visits.

[1930] 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.

[1931] 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.

[1932] 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.

[1933] 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.

[1934] 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.

[1935] 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.

[1936] 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 f...

Claims

1. a device that collects the user's medical information, symptoms, and lifestyle data; a server that stores and pre-processes the collected data; A means to analyze pre-processed data and use generative AI models to predict future health risks; A means for generating and notifying the user of diagnoses and suggestions based on the analysis results; A system that includes a means for sending user feedback back to the server and retraining the generative AI model.

2. 10. The system of claim 1, further comprising a server that learns the user's health and lifestyle patterns based on the collected data.

3. 2. The system of claim 1, wherein the terminal that notifies the user of the diagnosis and suggestions includes means for providing detailed feedback in the form of notifications and dashboards.

Images