system

Abstract

Provide a system. A means for uploading health checkup results; A means for analyzing the uploaded medical examination results; A means for generating personalized health advice using a generative AI model based on the analyzed health checkup results; means for providing the generated personalized health advice to the user; A system including:

Description

[Technical Field]

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

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

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

[0004] Conventional health management systems have difficulty providing personalized advice tailored to the health status of individual users, and have been unable to provide people with the specific guidance they need to maintain and improve their health. As a result, users are forced to try to improve their health on their own, making effective health management difficult. [Means for solving the problem]

[0005] To solve the above problems, the present invention provides the following means. First, a dedicated means is provided to allow users to upload their health checkup results. Next, a means is provided to analyze the uploaded health checkup results and input the analysis results into a generative AI model. The generative AI model generates personalized health advice based on the analyzed data and provides this advice to the user. The system also includes a means for the user to input daily dietary information, a means for calculating calorie intake and nutritional balance based on the input dietary information, and a means for generating a personalized meal plan based on the calculated data. Furthermore, the system also includes a means for the user to set fitness goals, and a means for generating an appropriate exercise plan based on the set goals and health data, which is then displayed to the user. This allows users to receive comprehensive and personalized health management and effectively improve their health.

[0006] "Health checkup results" refers to numerical values ​​and data that indicate the user's health condition based on tests conducted at a medical institution.

[0007] "Uploading means" refers to the functionality or interface that allows users to send their own data to the system via the Internet.

[0008] "Means of analysis" refers to the algorithms or software used to interpret the input data and extract the necessary information.

[0009] A "generative AI model" is a computational model that uses artificial intelligence to analyze input data and generate personalized advice and plans.

[0010] "Health advice" refers to specific improvements or instructions provided based on the user's health condition.

[0011] "Means for providing to the user" refers to the functions and interfaces for presenting the generated information in a form that the user can check.

[0012] "Means for inputting meal contents" refers to an interface or device that allows a user to input daily meal contents into the system.

[0013] "Means for calculating calorie intake and nutritional balance" refers to algorithms or software that calculate the amount of calories burned and nutrient intake based on the dietary information entered.

[0014] "Means for generating personalized meal plans" refers to functionality or software that creates optimal meal menus based on the user's health status and goals.

[0015] A "fitness goal" is a specific goal a user sets to improve their physical health (e.g., losing weight or gaining muscle).

[0016] "Means for generating an appropriate exercise plan" refers to functions or software for creating an optimal exercise menu based on the user's health condition and goals.

[0017] "Means for displaying to the user" refers to an interface or device for displaying the generated exercise plan and advice in a form that the user can confirm. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention provides a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[0040] Program processing details

[0041] 1. User uploads health checkup results

[0042] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[0043] 2. Sending health check results to the server

[0044] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[0045] 3. Analysis of health examination results

[0046] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[0047] 4. Use of generative AI models

[0048] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[0049] 5. Providing health advice

[0050] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[0051] Nutritional management function

[0052] 6. User input of meal details

[0053] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[0054] 7. Sending meal details to the server

[0055] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[0056] 8. Calculating calorie intake and nutritional balance

[0057] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[0058] 9. Generate personalized meal plans

[0059] The server then generates a personalized meal plan based on the calculated data, which is optimized based on the user's health status and goals. For example, a user with a vitamin C deficiency may be recommended to increase their intake of certain fruits and vegetables.

[0060] Generate a training plan

[0061] 10. User-defined fitness goals

[0062] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[0063] 11. Generate exercise plans based on your goals and health data

[0064] The server generates an appropriate exercise plan based on the user's goals and health checkup data. The plan includes exercise content (e.g., aerobic exercise three times a week) that is appropriate for the user's abilities and goals.

[0065] 12. Providing exercise plans

[0066] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[0067] Mental health support function

[0068] 13. User input of stress and sleep data

[0069] Users input their stress levels and sleep status into a dedicated application.

[0070] 14. Sending stress and sleep data to a server

[0071] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[0072] 15. Generating mental health advice

[0073] The server generates mental health advice based on stress levels and sleep data, for example, recommending relaxation meditation or deep breathing techniques for users with high stress levels.

[0074] 16. Providing Advice

[0075] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[0076] Specific examples

[0077] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[0078] 1. User Actions

[0079] Upload the health check results to a dedicated application.

[0080] 2. Device Operation

[0081] The uploaded health check results are sent to the server.

[0082] 3. Server Processing

[0083] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[0084] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[0085] 4. Server Actions

[0086] The generated advice is saved in the user's profile and sent to the terminal.

[0087] 5. Terminal Operation

[0088] Display health advice to the user.

[0089] As described above, the system of the present invention provides personalized health advice based on the user's health data and supports a comprehensive health improvement plan.

[0090] The processing flow will be explained below.

[0091] Step 1:

[0092] The user uploads the health check results to a dedicated application on their mobile device.

[0093] Step 2:

[0094] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[0095] Step 3:

[0096] The terminal sends the adapted file to the server.

[0097] Step 4:

[0098] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[0099] Step 5:

[0100] The server inputs the extracted data into the generative AI model and begins analysis.

[0101] Step 6:

[0102] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[0103] Step 7:

[0104] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[0105] Step 8:

[0106] The terminal displays the health advice received from the server to the user.

[0107] Step 9:

[0108] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[0109] Step 10:

[0110] The terminal transmits the meal data entered by the user to the server.

[0111] Step 11:

[0112] The server stores the received dietary data and calculates the calorie intake and the balance of each nutrient.

[0113] Step 12:

[0114] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[0115] Step 13:

[0116] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[0117] Step 14:

[0118] The device displays the meal plan to the user and provides reminders for implementation.

[0119] Step 15:

[0120] Users set fitness goals and input them into the system through a terminal.

[0121] Step 16:

[0122] The server generates an appropriate exercise plan based on the user's set goals and health data.

[0123] Step 17:

[0124] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[0125] Step 18:

[0126] The device displays the exercise plan to the user and provides functionality for tracking progress.

[0127] Step 19:

[0128] Users input their stress levels and sleep status into a dedicated application.

[0129] Step 20:

[0130] The terminal transmits the stress and sleep data input by the user to the server.

[0131] Step 21:

[0132] The server generates advice on stress management and sleep improvement based on the received data.

[0133] Step 22:

[0134] The server stores the generated advice in the user's profile and transmits it to the terminal.

[0135] Step 23:

[0136] The device displays stress management and sleep improvement advice to the user and provides a reminder function for implementation.

[0137] Example 1

[0138] 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."

[0139] Conventional health management systems are limited in their ability to analyze biometric data and provide individualized advice, making it difficult for users to achieve comprehensive health management. Furthermore, there is a lack of systems that can provide integrated support for diet, exercise, and even mental health. As a result, personalized advice and plans based on individual health conditions have not been adequately generated.

[0140] 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.

[0141] In this invention, the server includes means for uploading health checkup results, means for transmitting the uploaded health checkup results to the server, means for analyzing the received health checkup results, means for generating personalized health advice based on the analyzed health checkup results using a generative AI model, means for providing the generated personalized health advice to the user, means for the user to input daily meal contents, means for calculating calorie intake and nutrient balance based on the input meal contents, means for generating a personalized meal plan based on the calculated data, means for transmitting the input meal contents to the server, means for the user to set fitness goals, means for generating an appropriate exercise plan based on the set goals and health data, means for displaying the generated exercise plan to the user, means for the user to input stress levels and sleep states, means for transmitting the input stress and sleep data to the server, means for analyzing the received stress and sleep data, means for generating mental health advice based on the analysis results, and means for providing the generated mental health advice to the user, thereby enabling comprehensive and personalized health management.

[0142] "Health checkup results" are records of health status measurements taken at medical institutions, etc., and include blood test results and physical measurement data.

[0143] "Server" means a computer system that receives, analyzes, and stores data sent by users, and generates and provides necessary information and advice to users.

[0144] "Uploading" refers to the act of a user importing data such as health checkup results and dietary details into the system from their own device.

[0145] "Analysis" is the process by which the server performs statistical and computational processing on the data it receives, identifying outliers and analyzing trends.

[0146] "Generative AI model" means an artificial intelligence model used by the server to generate health advice and plans based on data, including machine learning algorithms.

[0147] "Personalized health advice" is information that suggests specific recommended actions or improvements based on each user's health condition.

[0148] "Meal contents" refers to detailed information such as the names of ingredients that the user regularly consumes, the amount of intake, and cooking methods.

[0149] "Calories intake" refers to the total amount of calories taken into the body by the user through food.

[0150] "Nutritional balance" refers to the balance of nutrients such as protein, lipids, carbohydrates, vitamins, and minerals contained in the user's diet.

[0151] A "meal plan" is a meal plan that is optimized based on the user's health status and goals.

[0152] "Fitness goals" are specific examples of goals related to physical health and exercise that a user sets, including weight loss and muscle gain.

[0153] An "exercise plan" is an exercise program designed based on a user's health data and fitness goals.

[0154] "Stress level" refers to the degree of mental and physical tension or strain felt by the user.

[0155] "Sleep state" is information relating to the quality and quantity of the user's sleep.

[0156] "Mental health advice" is specific advice for improving mental health that is suggested based on the user's stress level and sleep state.

[0157] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[0158] Hardware and software used

[0159] 1. Server: Receives, analyzes, stores data, and generates advice.

[0160] 2. Terminal: Provides an interface for users to enter data and view advice.

[0161] 3. Generative AI model: A machine learning algorithm that generates personalized advice based on health checkup results and other user data.

[0162] Data processing and calculation

[0163] Uploading and analyzing health checkup results

[0164] Users upload their health checkup results using a dedicated application. The device then sends the file uploaded by the user to a server. This file includes blood test results and physical measurement data. The server performs error checks on the received data and analyzes it using an analytical algorithm. This analyzed data is then input into a generative AI model, which generates personalized health advice.

[0165] For example, if a user has a high ALT (liver function index) value, the generative AI model will generate health advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[0166] Nutritional management function

[0167] Users input their daily dietary information into a dedicated application. This information includes the names of ingredients, the amount of each ingredient, and cooking methods. The device then sends this data to a server, which then calculates the balance of calories and nutrients (protein, fat, carbohydrates, vitamins, and minerals) and generates a personalized meal plan based on the results.

[0168] For example, a user who is deficient in vitamin C will be provided with a meal plan that encourages consumption of orange fruits and green vegetables.

[0169] Training plan generation function

[0170] Users use a dedicated app to set fitness goals, such as weight loss or muscle gain. The device then sends these goals to a server, which then generates a personalized exercise plan based on the user's goals and health data.

[0171] For example, a user looking to lose weight may be offered an exercise plan that includes aerobic exercise.

[0172] Mental health support function

[0173] Users use the app to input their stress levels and sleep patterns, and the device sends this data to a server that analyzes it and generates mental health advice.

[0174] For example, users with high stress levels may be encouraged to meditate or take deep breaths to relax.

[0175] Examples of specific examples and prompts

[0176] For example, if you want to upload your health checkup results and generate the necessary advice from them, you could input the following prompts into the generative AI model:

[0177] "Create dietary and lifestyle advice for users whose ALT levels exceed normal levels."

[0178] Based on this prompt, the generative AI model will provide the user with appropriate health advice. In this way, the system provides personalized advice based on the user's health data, supporting comprehensive health management.

[0179] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0180] Step 1:

[0181] The user logs in to the dedicated application and clicks the "Upload health checkup results" button. Next, they select the health checkup results file (PDF or CSV format) they want to upload and import it into the system. The input is the health checkup results file, and the output is a notification that the file has been uploaded. This operation imports the file into the system.

[0182] Step 2:

[0183] The terminal sends the health check result file uploaded by the user to the server. At this time, the terminal checks the format and size of the file and checks for transmission errors. The input is the uploaded file, and the output is the file sent to the server. Once the terminal sends the file to the server, it proceeds to the next processing step.

[0184] Step 3:

[0185] The server inputs the received health check result file into the analysis algorithm. The algorithm analyzes blood test results (e.g., ALT, AST, blood glucose levels) and physical measurement data (e.g., weight, height, BMI, etc.). The input is the health check result file, and the output is the analyzed data. The server analyzes the data and extracts abnormal values ​​and data requiring attention.

[0186] Step 4:

[0187] The server inputs the analysis results into a generative AI model, which generates personalized health advice based on the given data. The input is the analyzed data, and the output is personalized health advice. For example, specific advice such as "Since your ALT is high, increase your intake of green and yellow vegetables and limit your alcohol intake" may be generated.

[0188] Step 5:

[0189] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is personalized health advice, and the output is saving it in the user's profile and sending it to the terminal. The server prepares the advice to provide to the user.

[0190] Step 6:

[0191] The terminal receives the generated health advice and notifies the user. When the user logs in to the application, they can view the latest health advice. The input is the health advice sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the advice.

[0192] Step 7:

[0193] Users input their daily dietary information into a dedicated application. The dietary information includes the names of ingredients, the amount of food consumed, and cooking methods. The input is the daily dietary information, and the output is a notification that the dietary data has been entered. This operation imports the dietary data into the system.

[0194] Step 8:

[0195] The terminal transmits the input meal details to the server. The input is meal data, and the output is transmission to the server. The terminal provides the meal details data to the server.

[0196] Step 9:

[0197] The server calculates the calorie intake and balance of each nutrient (protein, fat, carbohydrates, vitamins, minerals) based on the input dietary data. The input is dietary data, and the output is the calculated calorie intake and nutritional balance. The server calculates and analyzes the data.

[0198] Step 10:

[0199] The server generates an individualized meal plan based on the calculated data and sends it to the device. The input is the calculation result, and the output is an individualized meal plan. For example, if a user is deficient in vitamin C, a plan recommending fruits and vegetables rich in vitamin C will be generated.

[0200] Step 11:

[0201] The terminal receives the generated individual meal plan and notifies the user. When the user logs in to the application, they can view the latest meal plan. The input is the meal plan sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the meal plan.

[0202] Step 12:

[0203] The user sets fitness goals using a dedicated application. Fitness goals can include weight loss or muscle gain. The input is the fitness goal, and the output is a notification that the goal has been entered. This operation imports the fitness goal into the system.

[0204] Step 13:

[0205] The terminal transmits the set fitness goal to the server. The input is the fitness goal and the output is the transmission to the server. The terminal provides the goal data to the server.

[0206] Step 14:

[0207] The server generates an appropriate exercise plan based on the user's fitness goals and health data (e.g., weight, height, and past exercise habits). The input is the fitness goals and health data, and the output is the exercise plan. The server analyzes the data and designs the exercise plan.

[0208] Step 15:

[0209] The server sends the generated exercise plan to the device and saves it in the user's profile. The input is the exercise plan, and the output is sending it to the device and saving it in the profile. The server is ready to provide the plan.

[0210] Step 16:

[0211] The device receives the generated exercise plan and notifies the user. When the user logs in to the application, they can check the latest exercise plan. The input is the exercise plan sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the plan.

[0212] Step 17:

[0213] The user uses the application to input their own stress level and sleep state. The input is the stress level and sleep state, and the output is a notification that the data has been input. This operation inputs the stress and sleep data into the system.

[0214] Step 18:

[0215] The terminal transmits the input stress and sleep data to the server. The input is stress and sleep data, and the output is transmission to the server. The terminal provides data to the server.

[0216] Step 19:

[0217] The server analyzes the received stress and sleep data and generates mental health advice. The input is stress and sleep data, and the output is mental health advice. For example, a user with a high stress level may be recommended to meditate or take deep breaths to relax.

[0218] Step 20:

[0219] The server generates mental health advice, stores it in the user's profile, and sends it to the device. The input is the mental health advice, and the output is sending it to the device and saving it in the profile. The server is ready to provide the advice.

[0220] Step 21:

[0221] The device receives the generated mental health advice and notifies the user. When the user logs in to the application, they can view the latest mental health advice. The input is the mental health advice sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the advice.

[0222] Through the above processing steps, the system provides personalized advice based on the user's health data and supports comprehensive health management.

[0223] (Application example 1)

[0224] 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."

[0225] Effective individual health management is extremely important in modern society, but existing systems have difficulty providing sufficient personalized health advice and reminders. Furthermore, the generation of nutritional management and training plans based on health checkup results is not automated, leaving users to manage these themselves. Furthermore, mental health support functions based on stress and sleep data are often not integrated. To solve these issues, a more comprehensive and automated health management system is needed.

[0226] 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.

[0227] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, and means for notifying the user of the generated advice and reminders. This allows the user to receive detailed health advice based on the health checkup results and accompanying reminders.

[0228] The system further includes a means for a user to input daily meal contents, a means for calculating calorie intake and nutritional balance based on the input meal contents, a means for generating an individual meal plan based on the calculated data, and a means for providing a reminder function based on advice.

[0229] The device further includes a means for allowing a user to set fitness goals, a means for generating an appropriate exercise plan based on the set goals and health data, a means for displaying the generated exercise plan to the user, and a means for providing a reminder function based on the exercise plan, thereby enabling the user to efficiently manage their overall health.

[0230] "Health checkup results" refer to various health indicators and numerical data obtained as a result of health checkups conducted at medical institutions or testing facilities.

[0231] "Individualized health advice" refers to health guidance and instructions that are optimized for each individual based on individual data such as the user's health checkup results and lifestyle.

[0232] "Uploading means" refers to the process or technology by which a user submits medical examination results in the form of a digital file to the system.

[0233] "Means of analysis" refers to the technology or algorithms that process the uploaded health check result data and extract the necessary information.

[0234] A "generative AI model" is a model that uses artificial intelligence technology to find patterns and relationships from input data and generate appropriate output.

[0235] A "reminder" is a notification function that notifies the user of a specific time or action.

[0236] The "nutritional management function" is a function that records and analyzes the user's diet and adjusts the nutritional balance.

[0237] The "training plan generation function" is a function that creates an exercise plan based on the user's fitness goals and health data.

[0238] The "mental health support function" is a function for supporting the user's psychological health and provides advice that is useful for stress management and improving sleep.

[0239] The "smart notification function" is a function that notifies users of health advice and reminders in real time.

[0240] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. This system is implemented as a smartphone application and operates in conjunction with a backend running on a server.

[0241] Hardware and software used

[0242] Hardware: Smartphone

[0243] software:

[0244] Frontend: React Native (for cross-platform app development)

[0245] Backend: Node.js, Python (AI model)

[0246] Database: MongoDB

[0247] Cloud services: AWS (registered trademark) (data processing and storage)

[0248] Processing Details

[0249] Uploading and analyzing health checkup results

[0250] Users upload their health checkup results in PDF or CSV format using their smartphones. The uploaded file is sent to a Node.js-based server through a front-end application using React Native. The server analyzes the received file and extracts the necessary health indicators.

[0251] Generative AI model generates advice

[0252] The analyzed data is input into a generative AI model, a Python-based AI model. This model generates personalized health advice based on the input data. For example, if the liver function score is high, specific advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption" is generated.

[0253] Providing health advice

[0254] The generated advice is stored in MongoDB and linked to the user's profile. A front-end application periodically retrieves this data and notifies the user. A smart notification feature also sets reminders and helps the user take the suggested actions.

[0255] Nutrition management and training plan generation functions

[0256] Users enter their daily dietary habits and fitness goals into the application. This data is then sent to the server and analyzed. Based on the analysis results, calorie intake and nutritional balance are calculated and an individualized meal plan is generated. An exercise plan based on the user's fitness goals is also generated and provided to the user. Reminders are also set for these plans to help the user continue to manage their health.

[0257] Specific example explanation

[0258] For example, if a user uploads their medical checkup results and finds that their liver function indicator, ALT, is high, the following specific steps will be taken:

[0259] 1. The user uploads the health check result file.

[0260] 2. The server receives the file and analyzes it.

[0261] 3. Based on the analysis results, the generated AI model generates advice such as "increase your intake of green and yellow vegetables and limit your alcohol intake."

[0262] 4. The server saves the generated advice in the user's profile and the application notifies the user.

[0263] Prompt Sentence Examples

[0264] An example of a text prompt is:

[0265] "Generate personalized health advice based on the user's health check results. The following data indicates high liver function values.

[0266] Liver function: High

[0267] Blood sugar: normal

[0268] Any advice generated should include specific dietary restrictions or lifestyle changes."

[0269] In this way, the system of the present invention utilizes data obtained from health checkup results in a multifaceted manner to support comprehensive health management.

[0270] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0271] Step 1:

[0272] Users upload their health checkup results using a smartphone application.

[0273] In this example, the user opens the app, selects a PDF or CSV format health checkup result file, and presses the send button. The input health checkup result file is sent to the server via the application.

[0274] Step 2:

[0275] The terminal sends the uploaded health check result file to the server.

[0276] The device receives the file and sends a POST request to the specified API endpoint. The input is a diagnostic result file in PDF or CSV format, which is then sent to the server.

[0277] Step 3:

[0278] The server receives the file and checks for errors.

[0279] The server checks the format and content of the received file and performs an error check. After the error check, it temporarily saves it for analysis. The input is the diagnostic result file, and the output is an error report or a confirmation message to proceed with the analysis.

[0280] Step 4:

[0281] The server analyzes the health check results and extracts the necessary health indicators.

[0282] The server uses an analysis algorithm to analyze the files and extract numerical data such as blood test results and physical measurement data. The input is the diagnostic result file, and the output is health index data.

[0283] Step 5:

[0284] The server inputs the analyzed data into a generative AI model.

[0285] The server passes the extracted health index data to a generative AI model to generate personalized health advice. The input is the health index data, and the output is the health advice.

[0286] Step 6:

[0287] The server stores the generated health advice in a database.

[0288] The server stores the generated advice in a database linked to the user's profile. The input is the health advice and the output is a message confirming the data storage.

[0289] Step 7:

[0290] The server notifies the device of advice and reminders.

[0291] The server sends the saved advice to the device and notifies the user via instant messaging or notification. The input is health advice, and the output is notification to the user device.

[0292] Step 8:

[0293] Users enter their daily diet and fitness goals into the app.

[0294] Users input and submit their dietary information and fitness goals through the app. The input is their daily dietary information and fitness goals, and the output is data sent to the server via the application.

[0295] Step 9:

[0296] The server analyzes the entered data and generates personalized meal and exercise plans.

[0297] The server analyzes data on daily dietary habits and fitness goals, calculates calorie intake and nutritional balance, and generates appropriate meal and exercise plans. The input is daily dietary habits and fitness goals, and the output is an individual plan.

[0298] Step 10:

[0299] The device displays the generated plan to the user and sets reminders.

[0300] The terminal displays the individual plan received from the server to the user and sets reminders. The input is the generated plan, and the output is the plan displayed to the user and the set reminders.

[0301] 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.

[0302] This invention integrates a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans, as well as an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[0303] Program processing details

[0304] 1. User uploads health checkup results

[0305] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[0306] 2. Sending health check results to the server

[0307] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[0308] 3. Analysis of health examination results

[0309] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[0310] 4. Use of generative AI models

[0311] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[0312] 5. Providing health advice

[0313] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[0314] Emotion engine integration

[0315] 6. User Emotion Recognition

[0316] The emotion engine has the ability to recognize emotions in real time from the user's facial expressions, tone of voice, etc. When the user uses the dedicated application, emotional data is collected through the built-in camera and microphone.

[0317] 7. Transmission and analysis of emotional data

[0318] The device transmits the captured emotion data to a server, which uses an emotion engine to analyze the data and store the recognized emotional state in the user's profile.

[0319] 8. Adjusting advice based on emotions

[0320] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice on taking immediate action.

[0321] Nutritional management function

[0322] 9. User input of meal details

[0323] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[0324] 10. Sending meal details to the server

[0325] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[0326] 11. Calculating calorie intake and nutritional balance

[0327] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[0328] 12. Generate personalized meal plans

[0329] The server then generates a personalized meal plan based on the calculated data. This plan is optimized based on the user's health status and goals. It also incorporates emotional data, recommending foods with a relaxing effect if the user is under high stress.

[0330] Generate a training plan

[0331] 13. User-defined fitness goals

[0332] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[0333] 14. Generate exercise plans based on your goals and health data

[0334] The server generates an appropriate exercise plan based on the user's goals and health data. The plan is also tailored to take emotional data into account. For example, if the user feels tired, a plan including relaxing yoga and light stretching will be suggested.

[0335] 15. Providing exercise plans

[0336] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[0337] Mental health support function

[0338] 16. User input of stress and sleep data

[0339] Users input their stress levels and sleep status into a dedicated application.

[0340] 17. Sending stress and sleep data to a server

[0341] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[0342] 18. Generating mental health advice

[0343] The server generates mental health advice based on stress levels, sleep data, and emotional data. For example, a user experiencing high stress might be recommended meditation, deep breathing techniques, or listening to relaxing music.

[0344] 19. Providing Advice

[0345] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[0346] Specific examples

[0347] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[0348] 1. User Actions

[0349] Upload the health check results to a dedicated application.

[0350] 2. Device Operation

[0351] The uploaded health check results are sent to the server.

[0352] 3. Server Processing

[0353] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[0354] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[0355] 4. User Emotion Recognition

[0356] The emotion engine detects stress from the user's facial expression.

[0357] 5. Server Actions

[0358] The generated advice reflects emotional data and also provides stress management techniques.

[0359] The advice is saved in the user's profile and sent to the device.

[0360] 6. Terminal Operation

[0361] Displaying health and stress management advice to the user.

[0362] As described above, the system of the present invention integrates a user's health data and emotional data to provide more personalized health advice and support a comprehensive health improvement plan.

[0363] The processing flow will be explained below.

[0364] Step 1:

[0365] The user uploads the health check results to a dedicated application on their mobile device.

[0366] Step 2:

[0367] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[0368] Step 3:

[0369] The terminal sends the adapted file to the server.

[0370] Step 4:

[0371] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[0372] Step 5:

[0373] The server inputs the extracted data into the generative AI model and begins analysis.

[0374] Step 6:

[0375] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[0376] Step 7:

[0377] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[0378] Step 8:

[0379] The terminal displays the health advice received from the server to the user.

[0380] Step 9:

[0381] The emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data in real time.

[0382] Step 10:

[0383] The terminal transmits the acquired emotion data to the server.

[0384] Step 11:

[0385] The server receives the analysis results of the emotion engine and identifies the user's emotional state, for example, if the user is feeling stressed, that state is saved in the profile.

[0386] Step 12:

[0387] The server takes into account the user's emotional state and adjusts the health advice provided by the generative AI model: for example, if stress levels are high, advice encouraging relaxation will be added.

[0388] Step 13:

[0389] The server stores the adjusted health advice again in the user's profile and transmits it to the terminal.

[0390] Step 14:

[0391] The terminal displays the tailored health advice to the user.

[0392] Step 15:

[0393] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[0394] Step 16:

[0395] The terminal transmits the input meal details to the server.

[0396] Step 17:

[0397] The server stores the received dietary data and calculates the balance of ingested calories and each nutrient (e.g., protein, fat, carbohydrates, vitamins, and minerals).

[0398] Step 18:

[0399] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[0400] Step 19:

[0401] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[0402] Step 20:

[0403] The device displays the meal plan to the user and provides reminders for implementation.

[0404] Step 21:

[0405] Users set fitness goals and input them into the system through a terminal.

[0406] Step 22:

[0407] The server generates an appropriate exercise plan based on the user's set goals and health data, and the plan is adjusted to take emotional data into account.

[0408] Step 23:

[0409] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[0410] Step 24:

[0411] The device displays the exercise plan to the user and provides functionality for tracking progress.

[0412] Step 25:

[0413] Users input their stress levels and sleep status into a dedicated application.

[0414] Step 26:

[0415] The terminal transmits the input data to the server.

[0416] Step 27:

[0417] The server analyzes the received stress and sleep data and generates mental health advice taking into account emotional data.

[0418] Step 28:

[0419] The server stores the generated mental health advice in the user's profile and sends it to the terminal.

[0420] Step 29:

[0421] The device displays mental health advice to the user and provides reminders for action.

[0422] These are the specific processing steps of this system that integrates an emotion engine, allowing users to receive more personalized health care.

[0423] Example 2

[0424] 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."

[0425] Conventional health management systems analyze users' health checkup results and provide health advice based on them, but because they do not take the user's emotional state into consideration, the advice is often ineffective. Furthermore, because a user's emotional state has a significant impact on health behavior, advice that ignores this has the problem of being difficult to implement.

[0426] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for recognizing the user's emotions and acquiring emotional data, means for transmitting the acquired emotional data to the server for analysis, and means for adjusting the generated health advice based on the user's emotional data. This makes it possible to consider the user's health state and emotional state in an integrated manner, thereby enabling the provision of more effective and easy-to-follow health advice.

[0427] The "health checkup result uploading means" is a means for a user to send health checkup results to the system.

[0428] The "medical examination result transmission means" is a means for the terminal to transmit the medical examination results uploaded by the user to the server.

[0429] The "health checkup result analysis means" is a means for analyzing the health checkup results received by the server.

[0430] A "generative AI model" is an AI model that generates individual health advice based on analyzed health checkup results.

[0431] A "means for generating personalized health advice using a generative AI model" is a means for generating personalized health advice from data analyzed using a generative AI model.

[0432] The "health advice providing means" is a means for providing the generated individual health advice to the user.

[0433] The "emotion recognition means" is a means for recognizing the user's emotions based on their facial expressions and voice tones.

[0434] The "emotion data acquisition means" is a means for acquiring the user's emotion data.

[0435] The "emotion data transmission means" is a means for transmitting the acquired emotion data to the server.

[0436] "Emotion data analysis means" is a means by which the server analyzes emotion data.

[0437] The "means for adjusting advice based on emotion data" is a means for adjusting the generated health advice based on the emotion data of the user.

[0438] The "meal content input means" is a means for a user to input daily meal content into the system.

[0439] The "calorie intake calculation means" is a means for calculating calorie intake based on the input meal contents.

[0440] The "nutritional balance calculation means" is a means for calculating the balance of nutrients based on the input meal contents.

[0441] "Meal plan generator" means a means for generating an individualized meal plan based on the calculated data.

[0442] The "fitness goal setting means" is a means for a user to set a fitness goal in the system.

[0443] The "exercise plan generation means" is a means for generating an appropriate exercise plan based on the set goals and health data.

[0444] The "exercise plan providing means" is a means for providing the generated exercise plan to the user.

[0445] The "exercise plan adjustment means" is a means for adjusting the generated exercise plan based on the user's emotional data.

[0446] The "stress data input means" is a means for a user to input a stress level into the system.

[0447] The "sleep data input means" is a means for the user to input sleep status into the system.

[0448] The "stress and sleep data transmission means" is a means for transmitting input stress and sleep data to a server.

[0449] The "mental health advice generation means" is a means for generating mental health advice based on stress levels, sleep data, and emotional data.

[0450] The "mental health advice providing means" is a means for providing the generated mental health advice to the user.

[0451] This invention integrates an emotion engine that recognizes the user's emotions into a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system includes a generative AI model, a nutrition management function, a training plan generation function, and a mental health support function.

[0452] Hardware and software used

[0453] Dedicated applications (e.g., HealthApp): Tools that allow users to upload and enter health checkup results and dietary information.

[0454] Server (e.g., central data server): Analyzes and stores data, runs generative AI models, and analyzes emotion data.

[0455] Generative AI model (e.g., GPT-4®): An AI model for generating personalized health advice.

[0456] Emotion engine (e.g., EmotionDetector): Recognizes emotions by analyzing the user's facial expressions and tone of voice.

[0457] Analysis algorithms (e.g., HealthAnalyzer, CalorieCounter): Analyze health checkup results, dietary data, and exercise data.

[0458] Specific operation of the system

[0459] 1. Upload your health checkup results

[0460] Users open the dedicated application, select and upload their health check results (in PDF or CSV format).

[0461] The device sends the uploaded health check results to the server, which performs error checks to verify the integrity of the received data.

[0462] 2. Analysis of health examination results

[0463] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[0464] The analysis results are input into a generative AI model, which generates personalized health advice. For example, a user with high liver function scores might be advised to increase their intake of green and yellow vegetables and limit alcohol consumption.

[0465] 3. Providing health advice

[0466] The server saves the generated health advice in the user's profile and sends it to the device, which displays the advice to the user.

[0467] 4. Functions of the Emotion Engine

[0468] When a user uses a dedicated application, emotional data such as facial expressions and voice tone is acquired through the built-in camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state.

[0469] The device sends the acquired emotion data to the server, which uses an emotion engine to analyze the emotion data and saves it in the user's profile.

[0470] 5. Adjusting advice based on emotions

[0471] The server then adjusts the health advice generated by the generative AI model based on the user's emotional data. For example, if a user is experiencing high stress, it will also provide them with stress management techniques.

[0472] 6. Nutritional management function

[0473] Users input their daily dietary information into a dedicated application, which records the names of ingredients, the amount consumed, cooking methods, and other information.

[0474] The terminal transmits the entered meal details to the server.

[0475] The server calculates calorie intake and nutritional balance based on the received dietary data. Based on the calculation results, a personalized meal plan is generated. The plan is optimized based on the user's health status and goals, and also takes emotional data into account.

[0476] 7. Generate a training plan

[0477] Users set fitness goals and input them into the system through a terminal, such as "weight loss" or "muscle gain."

[0478] The server generates an appropriate exercise plan based on the user's goals and health data, taking emotional data into account and suggesting light exercise if the user feels tired, for example.

[0479] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the plan to the user and provides the ability to track progress.

[0480] 8. Mental health support function

[0481] Users input their stress levels and sleep status into a dedicated application.

[0482] The terminal transmits the input data to the server.

[0483] The server generates mental health advice based on stress, sleep, and emotional data. For example, users with high stress levels may be recommended meditation or deep breathing techniques.

[0484] Specific examples

[0485] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[0486] Users upload their health checkup results to a dedicated application.

[0487] The terminal transmits the diagnosis results to the server.

[0488] The server analyzes the data and generates personalized health advice using a generative AI model, such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[0489] The emotion engine detects stress from the user's facial expression.

[0490] The server reflects emotional data in its advice and also provides stress management techniques.

[0491] The device displays health and stress management advice to the user.

[0492] Example prompts to input to the generative AI model

[0493] "Based on the user's health checkup results, generate dietary advice for those with high liver function. Also, take stress management methods into consideration when generating advice."

[0494] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0495] Step 1: Upload your health check results

[0496] The user opens a dedicated application (e.g., HealthApp) and selects and uploads their own health checkup results. The user's health checkup result file (PDF or CSV format) is provided as input.

[0497] The terminal receives the uploaded health checkup results, checks their consistency, and then transmits them to the server. The output is the health checkup result data transmitted to the server.

[0498] Step 2: Submit your health check results

[0499] The terminal transmits the uploaded health checkup results to the server, and the health checkup result data stored in the terminal is provided as input.

[0500] The server stores the received medical examination results for analysis and performs error checking. As an output, medical examination result data that can be used for analysis is obtained.

[0501] Step 3: Analysis of health check results

[0502] The server analyzes the received health checkup results using an analysis algorithm (e.g., HealthAnalyzer). Health checkup result data is provided as input.

[0503] The analysis includes numerical data such as blood test results and anthropometric data, and health status is assessed from these data. The output is the analyzed health status data.

[0504] Step 4: Use the generative AI model

[0505] The server inputs the analyzed data into a generative AI model (e.g., GPT-4), which provides the analyzed health status data as input.

[0506] The generative AI model generates personalized health advice based on the data. For example, if the liver function score is high, the generated advice would be "increase your intake of green and yellow vegetables and limit alcohol consumption." The output is personalized health advice.

[0507] Step 5: Providing health advice

[0508] The server stores the generated health advice in the user's profile and sends it to the terminal, which provides the generated health advice data as input.

[0509] The terminal displays the received health advice to the user, and as an output, the user can view the displayed health advice.

[0510] Step 6: Emotion Recognition

[0511] The emotion engine recognizes emotions in real time from the user's facial expressions and voice tone. Inputs include facial expression data and voice data captured through the built-in camera and microphone.

[0512] The terminal transmits the acquired emotion data to the server, and the emotion data transmitted to the server is obtained as an output.

[0513] Step 7: Send and analyze emotion data

[0514] The terminal transmits the acquired emotion data to the server, which provides the emotion data stored in the terminal as input.

[0515] The server analyzes these data using an emotion engine and stores the recognized emotional state in the user's profile. The output is the analyzed emotion data.

[0516] Step 8: Adjust your advice based on emotions

[0517] The server adjusts the health advice generated by the generative AI model based on the user's emotional state, and receives as input the generated health advice data and the analyzed emotional data.

[0518] For example, a user experiencing high stress may also be offered stress management techniques. The output is tailored health advice.

[0519] Step 9: Enter your meal details

[0520] Users input their daily dietary information into a dedicated application, providing detailed dietary data such as ingredient names, intake amounts, and cooking methods.

[0521] The terminal transmits the input meal details to the server, and the meal data transmitted to the server is obtained as an output.

[0522] Step 10: Sending meal details to the server

[0523] The terminal transmits the input meal details to the server. As input, meal data stored in the terminal is provided.

[0524] The server stores the received data and inputs it into an analysis algorithm, which outputs dietary data that can be used for analysis.

[0525] Step 11: Calculate your calorie intake and nutritional balance

[0526] The server calculates the balance of calories and nutrients (e.g., protein, fat, carbohydrates, vitamins, and minerals) based on the input dietary data. Dietary data is provided as input.

[0527] The calculated data is used to generate a personalized meal plan, with calorie intake and nutritional balance data as output.

[0528] Step 12: Generate a personalized meal plan

[0529] The server generates a personalized meal plan based on the calculated data, providing calorie intake and nutritional balance data as input.

[0530] The plan is optimized based on the user's health status and goals, and also takes emotional data into account. The output is a personalized meal plan.

[0531] Step 13: Set your fitness goals

[0532] A user sets a fitness goal and inputs it into the system through a terminal. The fitness goal (e.g., weight loss, muscle gain) is provided as input.

[0533] The terminal transmits the input fitness goal to the server, and the fitness goal data transmitted to the server is obtained as an output.

[0534] Step 14: Generate an exercise plan based on your goals and health data

[0535] The server generates an appropriate exercise plan based on the user's set goals and health data, and provides the fitness goal data and health data as input.

[0536] Emotional data is also taken into account: if the user feels tired, for example, a plan including relaxing yoga and gentle stretching will be suggested. The output is a personalized exercise plan.

[0537] Step 15: Provide an exercise plan

[0538] The server stores the generated exercise plan in the user's profile and transmits it to the terminal, which provides the generated exercise plan data as input.

[0539] The device displays the exercise plan to the user and provides the ability to track progress. As an output, the user can view the displayed exercise plan and input progress data.

[0540] Step 16: Entering Stress and Sleep Data

[0541] The user inputs their stress level and sleep state into a dedicated application, providing stress data and sleep data as input.

[0542] The terminal transmits the input data to the server, and as an output, the stress and sleep data transmitted to the server are obtained.

[0543] Step 17: Sending stress and sleep data to the server

[0544] The terminal transmits the input stress and sleep data to the server, where the stress and sleep data stored in the terminal is provided as input.

[0545] The server stores the received data and inputs it into an analysis algorithm, which outputs stress and sleep data that can be used for analysis.

[0546] Step 18: Generate mental health advice

[0547] The server generates mental health advice based on stress levels, sleep data, and emotional data. Stress data, sleep data, and emotional data are provided as input.

[0548] For example, a user experiencing high stress levels may be encouraged to meditate or listen to relaxing music. The output is mental health advice.

[0549] Step 19: Providing advice

[0550] The server stores the generated mental health advice in the user's profile and sends it to the terminal, which provides the generated mental health advice data as input.

[0551] The device displays these advices to the user and also provides a reminder function. As an output, the user can view the displayed mental health advice.

[0552] (Application example 2)

[0553] 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."

[0554] Traditionally, worker health management has relied on advice based on the results of regular health checkups, making it difficult to provide individual health guidance that responds to real-time conditions. Furthermore, the impact of workers' emotional states on their health has often been ignored, resulting in ineffective health management. This increases worker health risks, raising concerns about reduced productivity and the occurrence of work-related accidents.

[0555] 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.

[0556] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, means for recognizing the user's emotions in real time, and means for analyzing the recognized emotion data and adjusting the health advice generated by the generative AI model based on the user's emotional state. This enables effective and timely health management guidance tailored to the user's individual health and emotional state.

[0557] "Physical examination results" are the results of tests conducted to evaluate the user's health condition, and specifically include numerical data such as blood test data and physical measurement data.

[0558] A "generative AI model" is a machine learning algorithm that generates information for each user based on input data, automatically generating health advice and improvement plans.

[0559] "Personalized health advice" means guidance or suggestions for maintaining or improving health that are tailored to a specific individual and provided by a generative AI model based on the user's health checkup results and other relevant data.

[0560] "Emotion recognition" is a technology that analyzes data such as a user's facial expressions and tone of voice to infer their emotional state at that moment.

[0561] "Emotion data" is data that indicates the emotional state of the user and is obtained by emotion recognition.

[0562] "Calories intake" is a numerical value indicating the amount of energy the user takes in per day, and is calculated based on the record of dietary content.

[0563] "Nutritional balance" indicates the proportion and balance of each nutrient (protein, lipids, carbohydrates, vitamins, minerals, etc.) that the user ingests.

[0564] A "meal plan" is an optimized meal plan generated based on a user's health status and goals.

[0565] A "fitness goal" is an objective set by a user, such as improving health and physical strength or managing weight, and refers to a specific numerical value or state that the user aims to achieve.

[0566] An "exercise plan" is an exercise plan created based on a user's fitness goals and health data, and includes specific exercise content and frequency.

[0567] This invention is a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. It also integrates an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[0568] Specifically, the system includes functions for uploading and analyzing health checkup results, providing generated health advice, emotion recognition, emotion data analysis, and adjusting health advice based on emotional state.

[0569] System configuration

[0570] 1. Upload your health checkup results:

[0571] Users upload their own health checkup results to the system through a dedicated application, and the uploaded health checkup results are imported into the system in a compatible file format (e.g., PDF or CSV).

[0572] 2. Analysis of Health Examination Results:

[0573] The device sends the uploaded health checkup results to a server, which then uses an analysis algorithm to analyze the received health checkup results, including numerical data such as blood test results and physical measurement data.

[0574] 3. Use of generative AI models:

[0575] The server inputs the analyzed data into a generative AI model to generate personalized health advice. For example, if liver function is high, it will generate advice on specific dietary restrictions and lifestyle improvements.

[0576] 4. Providing health advice:

[0577] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[0578] 5. Emotion recognition:

[0579] The emotion engine captures the user's facial expressions and voice tone in real time through the camera and microphone, and recognizes their emotions. This data is periodically sent to the server.

[0580] 6. Emotional Data Analysis:

[0581] The server utilizes an emotion engine to analyze the acquired emotion data and stores the recognized emotional state in the user's profile.

[0582] 7. Adjusting advice based on emotional state:

[0583] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice including short-term actionable strategies and relaxation techniques.

[0584] Hardware and software used

[0585] Hardware:

[0586] Camera: Built-in webcam, IP camera

[0587] Microphone: Built-in microphone, external USB microphone

[0588] Devices: Smartphones, tablets, factory displays

[0589] software:

[0590] Image processing: OpenCV

[0591] Machine Learning: TENSORFLOW (registered trademark) (generative AI model)

[0592] Backend server: Flask (Python framework)

[0593] Specific examples

[0594] For example, if a user uploads the results of a health check and finds that their ALT (an indicator of liver function) is high, the server will use the generative AI model to generate dietary advice such as "increase intake of green and yellow vegetables and limit alcohol intake." On the other hand, if the emotion engine detects stress from the user's facial expression, the server will adjust the generated advice based on the emotion data and also provide stress management methods.

[0595] Prompt Sentence Examples

[0596] "Analyze workers' health checkup results and generate personalized health advice based on their emotional data. If they're under stress, suggest relaxation techniques."

[0597] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0598] Step 1:

[0599] Users upload their health checkup results through a dedicated application. The input is a file of the health checkup results (e.g., PDF, CSV), and the output is the data sent from the application to the server. This data is validated and saved on the server for analysis.

[0600] Step 2:

[0601] The terminal sends the uploaded health checkup results to the server. The input is the health checkup results uploaded by the user, and the output is the data correctly transferred to the server. The server performs error checks on the received data and converts it into an analyzable format.

[0602] Step 3:

[0603] The server analyzes the received health checkup results using an analysis algorithm. The input is the uploaded health checkup results, and the output is the analyzed health data. This analysis includes processing numerical data such as blood test results and physical measurement data.

[0604] Step 4:

[0605] The server inputs the analyzed data into a generative AI model to generate personalized health advice. The input is the analyzed health data, and the output is personalized health advice. The generative AI model automatically generates personalized advice based on the health data.

[0606] Step 5:

[0607] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is the generated health advice, and the output is the data saved in the user's profile and the data sent to the terminal. The terminal displays the received advice to the user.

[0608] Step 6:

[0609] The emotion engine recognizes emotions by capturing the user's facial expressions and voice tone in real time through a camera and microphone. The input is the user's facial expressions and voice data, and the output is the recognized emotional state. This emotional data is periodically sent to the server.

[0610] Step 7:

[0611] The server analyzes the acquired emotional data using the emotion engine and stores the recognized emotional state in the user's profile. The input is the acquired emotional data from the emotion engine, and the output is the analyzed emotional state data.

[0612] Step 8:

[0613] The server adjusts the health advice generated by the generative AI model based on the user's emotional state. The input is health advice and emotional data, and the output is tailored, personalized health advice. For example, a user experiencing high stress levels will be provided with advice on urgent countermeasures and relaxation techniques.

[0614] Step 9:

[0615] The server saves the adjusted health advice in the user's profile and sends it to the terminal. The input is the adjusted health advice, and the output is the data saved in the user's profile and sent to the terminal. The terminal displays the adjusted advice to the user.

[0616] Step 10:

[0617] The user inputs the details of their daily meals and sends them to the server via their device. The input is the data of the meals, and the output is the data sent to the server. The server receives and stores this data.

[0618] Step 11:

[0619] The server calculates the balance of calories ingested and each nutrient (protein, fat, carbohydrates, vitamins, and minerals) based on the input dietary data. The input is dietary content data, and the output is calculated calorie and nutritional balance data.

[0620] Step 12:

[0621] The server generates an individualized meal plan based on the calculated data and also reflects emotional data. The input is calorie and nutritional balance data and emotional data, and the output is an adjusted individualized meal plan. The adjusted meal plan is stored on the server and sent to the device.

[0622] 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.

[0623] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0624] 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.

[0625] [Second embodiment]

[0626] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0627] 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.

[0628] 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).

[0629] 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.

[0630] 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.

[0631] 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).

[0632] 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.

[0633] 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.

[0634] 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.

[0635] 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.

[0636] 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.

[0637] 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."

[0638] The present invention provides a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[0639] Program processing details

[0640] 1. User uploads health checkup results

[0641] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[0642] 2. Sending health check results to the server

[0643] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[0644] 3. Analysis of health examination results

[0645] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[0646] 4. Use of generative AI models

[0647] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[0648] 5. Providing health advice

[0649] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[0650] Nutritional management function

[0651] 6. User input of meal details

[0652] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[0653] 7. Sending meal details to the server

[0654] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[0655] 8. Calculating calorie intake and nutritional balance

[0656] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[0657] 9. Generate personalized meal plans

[0658] The server then generates a personalized meal plan based on the calculated data, which is optimized based on the user's health status and goals. For example, a user with a vitamin C deficiency may be recommended to increase their intake of certain fruits and vegetables.

[0659] Generate a training plan

[0660] 10. User-defined fitness goals

[0661] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[0662] 11. Generate exercise plans based on your goals and health data

[0663] The server generates an appropriate exercise plan based on the user's goals and health checkup data. The plan includes exercise content (e.g., aerobic exercise three times a week) that is appropriate for the user's abilities and goals.

[0664] 12. Providing exercise plans

[0665] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[0666] Mental health support function

[0667] 13. User input of stress and sleep data

[0668] Users input their stress levels and sleep status into a dedicated application.

[0669] 14. Sending stress and sleep data to a server

[0670] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[0671] 15. Generating mental health advice

[0672] The server generates mental health advice based on stress levels and sleep data, for example, recommending relaxation meditation or deep breathing techniques for users with high stress levels.

[0673] 16. Providing Advice

[0674] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[0675] Specific examples

[0676] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[0677] 1. User Actions

[0678] Upload the health check results to a dedicated application.

[0679] 2. Device Operation

[0680] The uploaded health check results are sent to the server.

[0681] 3. Server Processing

[0682] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[0683] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[0684] 4. Server Actions

[0685] The generated advice is saved in the user's profile and sent to the terminal.

[0686] 5. Terminal Operation

[0687] Display health advice to the user.

[0688] As described above, the system of the present invention provides personalized health advice based on the user's health data and supports a comprehensive health improvement plan.

[0689] The processing flow will be explained below.

[0690] Step 1:

[0691] The user uploads the health check results to a dedicated application on their mobile device.

[0692] Step 2:

[0693] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[0694] Step 3:

[0695] The terminal sends the adapted file to the server.

[0696] Step 4:

[0697] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[0698] Step 5:

[0699] The server inputs the extracted data into the generative AI model and begins analysis.

[0700] Step 6:

[0701] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[0702] Step 7:

[0703] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[0704] Step 8:

[0705] The terminal displays the health advice received from the server to the user.

[0706] Step 9:

[0707] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[0708] Step 10:

[0709] The terminal transmits the meal data entered by the user to the server.

[0710] Step 11:

[0711] The server stores the received dietary data and calculates the calorie intake and the balance of each nutrient.

[0712] Step 12:

[0713] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[0714] Step 13:

[0715] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[0716] Step 14:

[0717] The device displays the meal plan to the user and provides reminders for implementation.

[0718] Step 15:

[0719] Users set fitness goals and input them into the system through a terminal.

[0720] Step 16:

[0721] The server generates an appropriate exercise plan based on the user's set goals and health data.

[0722] Step 17:

[0723] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[0724] Step 18:

[0725] The device displays the exercise plan to the user and provides functionality for tracking progress.

[0726] Step 19:

[0727] Users input their stress levels and sleep status into a dedicated application.

[0728] Step 20:

[0729] The terminal transmits the stress and sleep data input by the user to the server.

[0730] Step 21:

[0731] The server generates advice on stress management and sleep improvement based on the received data.

[0732] Step 22:

[0733] The server stores the generated advice in the user's profile and transmits it to the terminal.

[0734] Step 23:

[0735] The device displays stress management and sleep improvement advice to the user and provides a reminder function for implementation.

[0736] Example 1

[0737] 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."

[0738] Conventional health management systems are limited in their ability to analyze biometric data and provide individualized advice, making it difficult for users to achieve comprehensive health management. Furthermore, there is a lack of systems that can provide integrated support for diet, exercise, and even mental health. As a result, personalized advice and plans based on individual health conditions have not been adequately generated.

[0739] 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.

[0740] In this invention, the server includes means for uploading health checkup results, means for transmitting the uploaded health checkup results to the server, means for analyzing the received health checkup results, means for generating personalized health advice based on the analyzed health checkup results using a generative AI model, means for providing the generated personalized health advice to the user, means for the user to input daily meal contents, means for calculating calorie intake and nutrient balance based on the input meal contents, means for generating a personalized meal plan based on the calculated data, means for transmitting the input meal contents to the server, means for the user to set fitness goals, means for generating an appropriate exercise plan based on the set goals and health data, means for displaying the generated exercise plan to the user, means for the user to input stress levels and sleep states, means for transmitting the input stress and sleep data to the server, means for analyzing the received stress and sleep data, means for generating mental health advice based on the analysis results, and means for providing the generated mental health advice to the user, thereby enabling comprehensive and personalized health management.

[0741] "Health checkup results" are records of health status measurements taken at medical institutions, etc., and include blood test results and physical measurement data.

[0742] "Server" means a computer system that receives, analyzes, and stores data sent by users, and generates and provides necessary information and advice to users.

[0743] "Uploading" refers to the act of a user importing data such as health checkup results and dietary details into the system from their own device.

[0744] "Analysis" is the process by which the server performs statistical and computational processing on the data it receives, identifying outliers and analyzing trends.

[0745] "Generative AI model" means an artificial intelligence model used by the server to generate health advice and plans based on data, including machine learning algorithms.

[0746] "Personalized health advice" is information that suggests specific recommended actions or improvements based on each user's health condition.

[0747] "Meal contents" refers to detailed information such as the names of ingredients that the user regularly consumes, the amount of intake, and cooking methods.

[0748] "Calories intake" refers to the total amount of calories taken into the body by the user through food.

[0749] "Nutritional balance" refers to the balance of nutrients such as protein, lipids, carbohydrates, vitamins, and minerals contained in the user's diet.

[0750] A "meal plan" is a meal plan that is optimized based on the user's health status and goals.

[0751] "Fitness goals" are specific examples of goals related to physical health and exercise that a user sets, including weight loss and muscle gain.

[0752] An "exercise plan" is an exercise program designed based on a user's health data and fitness goals.

[0753] "Stress level" refers to the degree of mental and physical tension or strain felt by the user.

[0754] "Sleep state" is information relating to the quality and quantity of the user's sleep.

[0755] "Mental health advice" is specific advice for improving mental health that is suggested based on the user's stress level and sleep state.

[0756] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[0757] Hardware and software used

[0758] 1. Server: Receives, analyzes, stores data, and generates advice.

[0759] 2. Terminal: Provides an interface for users to enter data and view advice.

[0760] 3. Generative AI model: A machine learning algorithm that generates personalized advice based on health checkup results and other user data.

[0761] Data processing and calculation

[0762] Uploading and analyzing health checkup results

[0763] Users upload their health checkup results using a dedicated application. The device then sends the file uploaded by the user to a server. This file includes blood test results and physical measurement data. The server performs error checks on the received data and analyzes it using an analytical algorithm. This analyzed data is then input into a generative AI model, which generates personalized health advice.

[0764] For example, if a user has a high ALT (liver function index) value, the generative AI model will generate health advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[0765] Nutritional management function

[0766] Users input their daily dietary information into a dedicated application. This information includes the names of ingredients, the amount of each ingredient, and cooking methods. The device then sends this data to a server, which then calculates the balance of calories and nutrients (protein, fat, carbohydrates, vitamins, and minerals) and generates a personalized meal plan based on the results.

[0767] For example, a user who is deficient in vitamin C will be provided with a meal plan that encourages consumption of orange fruits and green vegetables.

[0768] Training plan generation function

[0769] Users use a dedicated app to set fitness goals, such as weight loss or muscle gain. The device then sends these goals to a server, which then generates a personalized exercise plan based on the user's goals and health data.

[0770] For example, a user looking to lose weight may be offered an exercise plan that includes aerobic exercise.

[0771] Mental health support function

[0772] Users use the app to input their stress levels and sleep patterns, and the device sends this data to a server that analyzes it and generates mental health advice.

[0773] For example, users with high stress levels may be encouraged to meditate or take deep breaths to relax.

[0774] Examples of specific examples and prompts

[0775] For example, if you want to upload your health checkup results and generate the necessary advice from them, you could input the following prompts into the generative AI model:

[0776] "Create dietary and lifestyle advice for users whose ALT levels exceed normal levels."

[0777] Based on this prompt, the generative AI model will provide the user with appropriate health advice. In this way, the system provides personalized advice based on the user's health data, supporting comprehensive health management.

[0778] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0779] Step 1:

[0780] The user logs in to the dedicated application and clicks the "Upload health checkup results" button. Next, they select the health checkup results file (PDF or CSV format) they want to upload and import it into the system. The input is the health checkup results file, and the output is a notification that the file has been uploaded. This operation imports the file into the system.

[0781] Step 2:

[0782] The terminal sends the health check result file uploaded by the user to the server. At this time, the terminal checks the format and size of the file and checks for transmission errors. The input is the uploaded file, and the output is the file sent to the server. Once the terminal sends the file to the server, it proceeds to the next processing step.

[0783] Step 3:

[0784] The server inputs the received health check result file into the analysis algorithm. The algorithm analyzes blood test results (e.g., ALT, AST, blood glucose levels) and physical measurement data (e.g., weight, height, BMI, etc.). The input is the health check result file, and the output is the analyzed data. The server analyzes the data and extracts abnormal values ​​and data requiring attention.

[0785] Step 4:

[0786] The server inputs the analysis results into a generative AI model, which generates personalized health advice based on the given data. The input is the analyzed data, and the output is personalized health advice. For example, specific advice such as "Since your ALT is high, increase your intake of green and yellow vegetables and limit your alcohol intake" may be generated.

[0787] Step 5:

[0788] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is personalized health advice, and the output is saving it in the user's profile and sending it to the terminal. The server prepares the advice to provide to the user.

[0789] Step 6:

[0790] The terminal receives the generated health advice and notifies the user. When the user logs in to the application, they can view the latest health advice. The input is the health advice sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the advice.

[0791] Step 7:

[0792] Users input their daily dietary information into a dedicated application. The dietary information includes the names of ingredients, the amount of food consumed, and cooking methods. The input is the daily dietary information, and the output is a notification that the dietary data has been entered. This operation imports the dietary data into the system.

[0793] Step 8:

[0794] The terminal transmits the input meal details to the server. The input is meal data, and the output is transmission to the server. The terminal provides the meal details data to the server.

[0795] Step 9:

[0796] The server calculates the calorie intake and balance of each nutrient (protein, fat, carbohydrates, vitamins, minerals) based on the input dietary data. The input is dietary data, and the output is the calculated calorie intake and nutritional balance. The server calculates and analyzes the data.

[0797] Step 10:

[0798] The server generates an individualized meal plan based on the calculated data and sends it to the device. The input is the calculation result, and the output is an individualized meal plan. For example, if a user is deficient in vitamin C, a plan recommending fruits and vegetables rich in vitamin C will be generated.

[0799] Step 11:

[0800] The terminal receives the generated individual meal plan and notifies the user. When the user logs in to the application, they can view the latest meal plan. The input is the meal plan sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the meal plan.

[0801] Step 12:

[0802] The user sets fitness goals using a dedicated application. Fitness goals can include weight loss or muscle gain. The input is the fitness goal, and the output is a notification that the goal has been entered. This operation imports the fitness goal into the system.

[0803] Step 13:

[0804] The terminal transmits the set fitness goal to the server. The input is the fitness goal and the output is the transmission to the server. The terminal provides the goal data to the server.

[0805] Step 14:

[0806] The server generates an appropriate exercise plan based on the user's fitness goals and health data (e.g., weight, height, and past exercise habits). The input is the fitness goals and health data, and the output is the exercise plan. The server analyzes the data and designs the exercise plan.

[0807] Step 15:

[0808] The server sends the generated exercise plan to the device and saves it in the user's profile. The input is the exercise plan, and the output is sending it to the device and saving it in the profile. The server is ready to provide the plan.

[0809] Step 16:

[0810] The device receives the generated exercise plan and notifies the user. When the user logs in to the application, they can check the latest exercise plan. The input is the exercise plan sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the plan.

[0811] Step 17:

[0812] The user uses the application to input their own stress level and sleep state. The input is the stress level and sleep state, and the output is a notification that the data has been input. This operation inputs the stress and sleep data into the system.

[0813] Step 18:

[0814] The terminal transmits the input stress and sleep data to the server. The input is stress and sleep data, and the output is transmission to the server. The terminal provides data to the server.

[0815] Step 19:

[0816] The server analyzes the received stress and sleep data and generates mental health advice. The input is stress and sleep data, and the output is mental health advice. For example, a user with a high stress level may be recommended to meditate or take deep breaths to relax.

[0817] Step 20:

[0818] The server generates mental health advice, stores it in the user's profile, and sends it to the device. The input is the mental health advice, and the output is sending it to the device and saving it in the profile. The server is ready to provide the advice.

[0819] Step 21:

[0820] The device receives the generated mental health advice and notifies the user. When the user logs in to the application, they can view the latest mental health advice. The input is the mental health advice sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the advice.

[0821] Through the above processing steps, the system provides personalized advice based on the user's health data and supports comprehensive health management.

[0822] (Application example 1)

[0823] 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."

[0824] Effective individual health management is extremely important in modern society, but existing systems have difficulty providing sufficient personalized health advice and reminders. Furthermore, the generation of nutritional management and training plans based on health checkup results is not automated, leaving users to manage these themselves. Furthermore, mental health support functions based on stress and sleep data are often not integrated. To solve these issues, a more comprehensive and automated health management system is needed.

[0825] 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.

[0826] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, and means for notifying the user of the generated advice and reminders. This allows the user to receive detailed health advice based on the health checkup results and accompanying reminders.

[0827] The system further includes a means for a user to input daily meal contents, a means for calculating calorie intake and nutritional balance based on the input meal contents, a means for generating an individual meal plan based on the calculated data, and a means for providing a reminder function based on advice.

[0828] The device further includes a means for allowing a user to set fitness goals, a means for generating an appropriate exercise plan based on the set goals and health data, a means for displaying the generated exercise plan to the user, and a means for providing a reminder function based on the exercise plan, thereby enabling the user to efficiently manage their overall health.

[0829] "Health checkup results" refer to various health indicators and numerical data obtained as a result of health checkups conducted at medical institutions or testing facilities.

[0830] "Individualized health advice" refers to health guidance and instructions that are optimized for each individual based on individual data such as the user's health checkup results and lifestyle.

[0831] "Uploading means" refers to the process or technology by which a user submits medical examination results in the form of a digital file to the system.

[0832] "Means of analysis" refers to the technology or algorithms that process the uploaded health check result data and extract the necessary information.

[0833] A "generative AI model" is a model that uses artificial intelligence technology to find patterns and relationships from input data and generate appropriate output.

[0834] A "reminder" is a notification function that notifies the user of a specific time or action.

[0835] The "nutritional management function" is a function that records and analyzes the user's diet and adjusts the nutritional balance.

[0836] The "training plan generation function" is a function that creates an exercise plan based on the user's fitness goals and health data.

[0837] The "mental health support function" is a function for supporting the user's psychological health and provides advice that is useful for stress management and improving sleep.

[0838] The "smart notification function" is a function that notifies users of health advice and reminders in real time.

[0839] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. This system is implemented as a smartphone application and operates in conjunction with a backend running on a server.

[0840] Hardware and software used

[0841] Hardware: Smartphone

[0842] software:

[0843] Frontend: React Native (for cross-platform app development)

[0844] Backend: Node.js, Python (AI model)

[0845] Database: MongoDB

[0846] Cloud services: AWS (data processing and storage)

[0847] Processing Details

[0848] Uploading and analyzing health checkup results

[0849] Users upload their health checkup results in PDF or CSV format using their smartphones. The uploaded file is sent to a Node.js-based server through a front-end application using React Native. The server analyzes the received file and extracts the necessary health indicators.

[0850] Generative AI model generates advice

[0851] The analyzed data is input into a generative AI model, a Python-based AI model. This model generates personalized health advice based on the input data. For example, if the liver function score is high, specific advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption" is generated.

[0852] Providing health advice

[0853] The generated advice is stored in MongoDB and linked to the user's profile. A front-end application periodically retrieves this data and notifies the user. A smart notification feature also sets reminders and helps the user take the suggested actions.

[0854] Nutrition management and training plan generation functions

[0855] Users enter their daily dietary habits and fitness goals into the application. This data is then sent to the server and analyzed. Based on the analysis results, calorie intake and nutritional balance are calculated and an individualized meal plan is generated. An exercise plan based on the user's fitness goals is also generated and provided to the user. Reminders are also set for these plans to help the user continue to manage their health.

[0856] Specific example explanation

[0857] For example, if a user uploads their medical checkup results and finds that their liver function indicator, ALT, is high, the following specific steps will be taken:

[0858] 1. The user uploads the health check result file.

[0859] 2. The server receives the file and analyzes it.

[0860] 3. Based on the analysis results, the generated AI model generates advice such as "increase your intake of green and yellow vegetables and limit your alcohol intake."

[0861] 4. The server saves the generated advice in the user's profile and the application notifies the user.

[0862] Prompt Sentence Examples

[0863] An example of a text prompt is:

[0864] "Generate personalized health advice based on the user's health check results. The following data indicates high liver function values.

[0865] Liver function: High

[0866] Blood sugar: normal

[0867] Any advice generated should include specific dietary restrictions or lifestyle changes."

[0868] In this way, the system of the present invention utilizes data obtained from health checkup results in a multifaceted manner to support comprehensive health management.

[0869] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0870] Step 1:

[0871] Users upload their health checkup results using a smartphone application.

[0872] In this example, the user opens the app, selects a PDF or CSV format health checkup result file, and presses the send button. The input health checkup result file is sent to the server via the application.

[0873] Step 2:

[0874] The terminal sends the uploaded health check result file to the server.

[0875] The device receives the file and sends a POST request to the specified API endpoint. The input is a diagnostic result file in PDF or CSV format, which is then sent to the server.

[0876] Step 3:

[0877] The server receives the file and checks for errors.

[0878] The server checks the format and content of the received file and performs an error check. After the error check, it temporarily saves it for analysis. The input is the diagnostic result file, and the output is an error report or a confirmation message to proceed with the analysis.

[0879] Step 4:

[0880] The server analyzes the health check results and extracts the necessary health indicators.

[0881] The server uses an analysis algorithm to analyze the files and extract numerical data such as blood test results and physical measurement data. The input is the diagnostic result file, and the output is health index data.

[0882] Step 5:

[0883] The server inputs the analyzed data into a generative AI model.

[0884] The server passes the extracted health index data to a generative AI model to generate personalized health advice. The input is the health index data, and the output is the health advice.

[0885] Step 6:

[0886] The server stores the generated health advice in a database.

[0887] The server stores the generated advice in a database linked to the user's profile. The input is the health advice and the output is a message confirming the data storage.

[0888] Step 7:

[0889] The server notifies the device of advice and reminders.

[0890] The server sends the saved advice to the device and notifies the user via instant messaging or notification. The input is health advice, and the output is notification to the user device.

[0891] Step 8:

[0892] Users enter their daily diet and fitness goals into the app.

[0893] Users input and submit their dietary information and fitness goals through the app. The input is their daily dietary information and fitness goals, and the output is data sent to the server via the application.

[0894] Step 9:

[0895] The server analyzes the entered data and generates personalized meal and exercise plans.

[0896] The server analyzes data on daily dietary habits and fitness goals, calculates calorie intake and nutritional balance, and generates appropriate meal and exercise plans. The input is daily dietary habits and fitness goals, and the output is an individual plan.

[0897] Step 10:

[0898] The device displays the generated plan to the user and sets reminders.

[0899] The terminal displays the individual plan received from the server to the user and sets reminders. The input is the generated plan, and the output is the plan displayed to the user and the set reminders.

[0900] 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.

[0901] This invention integrates a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans, as well as an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[0902] Program processing details

[0903] 1. User uploads health checkup results

[0904] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[0905] 2. Sending health check results to the server

[0906] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[0907] 3. Analysis of health examination results

[0908] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[0909] 4. Use of generative AI models

[0910] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[0911] 5. Providing health advice

[0912] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[0913] Emotion engine integration

[0914] 6. User Emotion Recognition

[0915] The emotion engine has the ability to recognize emotions in real time from the user's facial expressions, tone of voice, etc. When the user uses the dedicated application, emotional data is collected through the built-in camera and microphone.

[0916] 7. Transmission and analysis of emotional data

[0917] The device transmits the captured emotion data to a server, which uses an emotion engine to analyze the data and store the recognized emotional state in the user's profile.

[0918] 8. Adjusting advice based on emotions

[0919] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice on taking immediate action.

[0920] Nutritional management function

[0921] 9. User input of meal details

[0922] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[0923] 10. Sending meal details to the server

[0924] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[0925] 11. Calculating calorie intake and nutritional balance

[0926] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[0927] 12. Generate personalized meal plans

[0928] The server then generates a personalized meal plan based on the calculated data. This plan is optimized based on the user's health status and goals. It also incorporates emotional data, recommending foods with a relaxing effect if the user is under high stress.

[0929] Generate a training plan

[0930] 13. User-defined fitness goals

[0931] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[0932] 14. Generate exercise plans based on your goals and health data

[0933] The server generates an appropriate exercise plan based on the user's goals and health data. The plan is also tailored to take emotional data into account. For example, if the user feels tired, a plan including relaxing yoga and light stretching will be suggested.

[0934] 15. Providing exercise plans

[0935] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[0936] Mental health support function

[0937] 16. User input of stress and sleep data

[0938] Users input their stress levels and sleep status into a dedicated application.

[0939] 17. Sending stress and sleep data to a server

[0940] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[0941] 18. Generating mental health advice

[0942] The server generates mental health advice based on stress levels, sleep data, and emotional data. For example, a user experiencing high stress might be recommended meditation, deep breathing techniques, or listening to relaxing music.

[0943] 19. Providing Advice

[0944] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[0945] Specific examples

[0946] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[0947] 1. User Actions

[0948] Upload the health check results to a dedicated application.

[0949] 2. Device Operation

[0950] The uploaded health check results are sent to the server.

[0951] 3. Server Processing

[0952] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[0953] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[0954] 4. User Emotion Recognition

[0955] The emotion engine detects stress from the user's facial expression.

[0956] 5. Server Actions

[0957] The generated advice reflects emotional data and also provides stress management techniques.

[0958] The advice is saved in the user's profile and sent to the device.

[0959] 6. Terminal Operation

[0960] Displaying health and stress management advice to the user.

[0961] As described above, the system of the present invention integrates a user's health data and emotional data to provide more personalized health advice and support a comprehensive health improvement plan.

[0962] The processing flow will be explained below.

[0963] Step 1:

[0964] The user uploads the health check results to a dedicated application on their mobile device.

[0965] Step 2:

[0966] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[0967] Step 3:

[0968] The terminal sends the adapted file to the server.

[0969] Step 4:

[0970] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[0971] Step 5:

[0972] The server inputs the extracted data into the generative AI model and begins analysis.

[0973] Step 6:

[0974] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[0975] Step 7:

[0976] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[0977] Step 8:

[0978] The terminal displays the health advice received from the server to the user.

[0979] Step 9:

[0980] The emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data in real time.

[0981] Step 10:

[0982] The terminal transmits the acquired emotion data to the server.

[0983] Step 11:

[0984] The server receives the analysis results of the emotion engine and identifies the user's emotional state, for example, if the user is feeling stressed, that state is saved in the profile.

[0985] Step 12:

[0986] The server takes into account the user's emotional state and adjusts the health advice provided by the generative AI model: for example, if stress levels are high, advice encouraging relaxation will be added.

[0987] Step 13:

[0988] The server stores the adjusted health advice again in the user's profile and transmits it to the terminal.

[0989] Step 14:

[0990] The terminal displays the tailored health advice to the user.

[0991] Step 15:

[0992] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[0993] Step 16:

[0994] The terminal transmits the input meal details to the server.

[0995] Step 17:

[0996] The server stores the received dietary data and calculates the balance of ingested calories and each nutrient (e.g., protein, fat, carbohydrates, vitamins, and minerals).

[0997] Step 18:

[0998] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[0999] Step 19:

[1000] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[1001] Step 20:

[1002] The device displays the meal plan to the user and provides reminders for implementation.

[1003] Step 21:

[1004] Users set fitness goals and input them into the system through a terminal.

[1005] Step 22:

[1006] The server generates an appropriate exercise plan based on the user's set goals and health data, and the plan is adjusted to take emotional data into account.

[1007] Step 23:

[1008] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[1009] Step 24:

[1010] The device displays the exercise plan to the user and provides functionality for tracking progress.

[1011] Step 25:

[1012] Users input their stress levels and sleep status into a dedicated application.

[1013] Step 26:

[1014] The terminal transmits the input data to the server.

[1015] Step 27:

[1016] The server analyzes the received stress and sleep data and generates mental health advice taking into account emotional data.

[1017] Step 28:

[1018] The server stores the generated mental health advice in the user's profile and sends it to the terminal.

[1019] Step 29:

[1020] The device displays mental health advice to the user and provides reminders for action.

[1021] These are the specific processing steps of this system that integrates an emotion engine, allowing users to receive more personalized health care.

[1022] Example 2

[1023] 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."

[1024] Conventional health management systems analyze users' health checkup results and provide health advice based on them, but because they do not take the user's emotional state into consideration, the advice is often ineffective. Furthermore, because a user's emotional state has a significant impact on health behavior, advice that ignores this has the problem of being difficult to implement.

[1025] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for recognizing the user's emotions and acquiring emotional data, means for transmitting the acquired emotional data to the server for analysis, and means for adjusting the generated health advice based on the user's emotional data. This makes it possible to consider the user's health state and emotional state in an integrated manner, thereby enabling the provision of more effective and easy-to-follow health advice.

[1026] The "health checkup result uploading means" is a means for a user to send health checkup results to the system.

[1027] The "medical examination result transmission means" is a means for the terminal to transmit the medical examination results uploaded by the user to the server.

[1028] The "health checkup result analysis means" is a means for analyzing the health checkup results received by the server.

[1029] A "generative AI model" is an AI model that generates individual health advice based on analyzed health checkup results.

[1030] A "means for generating personalized health advice using a generative AI model" is a means for generating personalized health advice from data analyzed using a generative AI model.

[1031] The "health advice providing means" is a means for providing the generated individual health advice to the user.

[1032] The "emotion recognition means" is a means for recognizing the user's emotions based on their facial expressions and voice tones.

[1033] The "emotion data acquisition means" is a means for acquiring the user's emotion data.

[1034] The "emotion data transmission means" is a means for transmitting the acquired emotion data to the server.

[1035] "Emotion data analysis means" is a means by which the server analyzes emotion data.

[1036] The "means for adjusting advice based on emotion data" is a means for adjusting the generated health advice based on the emotion data of the user.

[1037] The "meal content input means" is a means for a user to input daily meal content into the system.

[1038] The "calorie intake calculation means" is a means for calculating calorie intake based on the input meal contents.

[1039] The "nutritional balance calculation means" is a means for calculating the balance of nutrients based on the input meal contents.

[1040] "Meal plan generator" means a means for generating an individualized meal plan based on the calculated data.

[1041] The "fitness goal setting means" is a means for a user to set a fitness goal in the system.

[1042] The "exercise plan generation means" is a means for generating an appropriate exercise plan based on the set goals and health data.

[1043] The "exercise plan providing means" is a means for providing the generated exercise plan to the user.

[1044] The "exercise plan adjustment means" is a means for adjusting the generated exercise plan based on the user's emotional data.

[1045] The "stress data input means" is a means for a user to input a stress level into the system.

[1046] The "sleep data input means" is a means for the user to input sleep status into the system.

[1047] The "stress and sleep data transmission means" is a means for transmitting input stress and sleep data to a server.

[1048] The "mental health advice generation means" is a means for generating mental health advice based on stress levels, sleep data, and emotional data.

[1049] The "mental health advice providing means" is a means for providing the generated mental health advice to the user.

[1050] This invention integrates an emotion engine that recognizes the user's emotions into a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system includes a generative AI model, a nutrition management function, a training plan generation function, and a mental health support function.

[1051] Hardware and software used

[1052] Dedicated applications (e.g., HealthApp): Tools that allow users to upload and enter health checkup results and dietary information.

[1053] Server (e.g., central data server): Analyzes and stores data, runs generative AI models, and analyzes emotion data.

[1054] Generative AI models (e.g., GPT-4): AI models for generating personalized health advice.

[1055] Emotion engine (e.g., EmotionDetector): Recognizes emotions by analyzing the user's facial expressions and tone of voice.

[1056] Analysis algorithms (e.g., HealthAnalyzer, CalorieCounter): Analyze health checkup results, dietary data, and exercise data.

[1057] Specific operation of the system

[1058] 1. Upload your health checkup results

[1059] Users open the dedicated application, select and upload their health check results (in PDF or CSV format).

[1060] The device sends the uploaded health check results to the server, which performs error checks to verify the integrity of the received data.

[1061] 2. Analysis of health examination results

[1062] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[1063] The analysis results are input into a generative AI model, which generates personalized health advice. For example, a user with high liver function scores might be advised to increase their intake of green and yellow vegetables and limit alcohol consumption.

[1064] 3. Providing health advice

[1065] The server saves the generated health advice in the user's profile and sends it to the device, which displays the advice to the user.

[1066] 4. Functions of the Emotion Engine

[1067] When a user uses a dedicated application, emotional data such as facial expressions and voice tone is acquired through the built-in camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state.

[1068] The device sends the acquired emotion data to the server, which uses an emotion engine to analyze the emotion data and saves it in the user's profile.

[1069] 5. Adjusting advice based on emotions

[1070] The server then adjusts the health advice generated by the generative AI model based on the user's emotional data. For example, if a user is experiencing high stress, it will also provide them with stress management techniques.

[1071] 6. Nutritional management function

[1072] Users input their daily dietary information into a dedicated application, which records the names of ingredients, the amount consumed, cooking methods, and other information.

[1073] The terminal transmits the entered meal details to the server.

[1074] The server calculates calorie intake and nutritional balance based on the received dietary data. Based on the calculation results, a personalized meal plan is generated. The plan is optimized based on the user's health status and goals, and also takes emotional data into account.

[1075] 7. Generate a training plan

[1076] Users set fitness goals and input them into the system through a terminal, such as "weight loss" or "muscle gain."

[1077] The server generates an appropriate exercise plan based on the user's goals and health data, taking emotional data into account and suggesting light exercise if the user feels tired, for example.

[1078] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the plan to the user and provides the ability to track progress.

[1079] 8. Mental health support function

[1080] Users input their stress levels and sleep status into a dedicated application.

[1081] The terminal transmits the input data to the server.

[1082] The server generates mental health advice based on stress, sleep, and emotional data. For example, users with high stress levels may be recommended meditation or deep breathing techniques.

[1083] Specific examples

[1084] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[1085] Users upload their health checkup results to a dedicated application.

[1086] The terminal transmits the diagnosis results to the server.

[1087] The server analyzes the data and generates personalized health advice using a generative AI model, such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[1088] The emotion engine detects stress from the user's facial expression.

[1089] The server reflects emotional data in its advice and also provides stress management techniques.

[1090] The device displays health and stress management advice to the user.

[1091] Example prompts to input to the generative AI model

[1092] "Based on the user's health checkup results, generate dietary advice for those with high liver function. Also, take stress management methods into consideration when generating advice."

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Step 1: Upload your health check results

[1095] The user opens a dedicated application (e.g., HealthApp) and selects and uploads their own health checkup results. The user's health checkup result file (PDF or CSV format) is provided as input.

[1096] The terminal receives the uploaded health checkup results, checks their consistency, and then transmits them to the server. The output is the health checkup result data transmitted to the server.

[1097] Step 2: Submit your health check results

[1098] The terminal transmits the uploaded health checkup results to the server, and the health checkup result data stored in the terminal is provided as input.

[1099] The server stores the received medical examination results for analysis and performs error checking. As an output, medical examination result data that can be used for analysis is obtained.

[1100] Step 3: Analysis of health check results

[1101] The server analyzes the received health checkup results using an analysis algorithm (e.g., HealthAnalyzer). Health checkup result data is provided as input.

[1102] The analysis includes numerical data such as blood test results and anthropometric data, and health status is assessed from these data. The output is the analyzed health status data.

[1103] Step 4: Use the generative AI model

[1104] The server inputs the analyzed data into a generative AI model (e.g., GPT-4), which provides the analyzed health status data as input.

[1105] The generative AI model generates personalized health advice based on the data. For example, if the liver function score is high, the generated advice would be "increase your intake of green and yellow vegetables and limit alcohol consumption." The output is personalized health advice.

[1106] Step 5: Providing health advice

[1107] The server stores the generated health advice in the user's profile and sends it to the terminal, which provides the generated health advice data as input.

[1108] The terminal displays the received health advice to the user, and as an output, the user can view the displayed health advice.

[1109] Step 6: Emotion Recognition

[1110] The emotion engine recognizes emotions in real time from the user's facial expressions and voice tone. Inputs include facial expression data and voice data captured through the built-in camera and microphone.

[1111] The terminal transmits the acquired emotion data to the server, and the emotion data transmitted to the server is obtained as an output.

[1112] Step 7: Send and analyze emotion data

[1113] The terminal transmits the acquired emotion data to the server, which provides the emotion data stored in the terminal as input.

[1114] The server analyzes these data using an emotion engine and stores the recognized emotional state in the user's profile. The output is the analyzed emotion data.

[1115] Step 8: Adjust your advice based on emotions

[1116] The server adjusts the health advice generated by the generative AI model based on the user's emotional state, and receives as input the generated health advice data and the analyzed emotional data.

[1117] For example, a user experiencing high stress may also be offered stress management techniques. The output is tailored health advice.

[1118] Step 9: Enter your meal details

[1119] Users input their daily dietary information into a dedicated application, providing detailed dietary data such as ingredient names, intake amounts, and cooking methods.

[1120] The terminal transmits the input meal details to the server, and the meal data transmitted to the server is obtained as an output.

[1121] Step 10: Sending meal details to the server

[1122] The terminal transmits the input meal details to the server. As input, meal data stored in the terminal is provided.

[1123] The server stores the received data and inputs it into an analysis algorithm, which outputs dietary data that can be used for analysis.

[1124] Step 11: Calculate your calorie intake and nutritional balance

[1125] The server calculates the balance of calories and nutrients (e.g., protein, fat, carbohydrates, vitamins, and minerals) based on the input dietary data. Dietary data is provided as input.

[1126] The calculated data is used to generate a personalized meal plan, with calorie intake and nutritional balance data as output.

[1127] Step 12: Generate a personalized meal plan

[1128] The server generates a personalized meal plan based on the calculated data, providing calorie intake and nutritional balance data as input.

[1129] The plan is optimized based on the user's health status and goals, and also takes emotional data into account. The output is a personalized meal plan.

[1130] Step 13: Set your fitness goals

[1131] A user sets a fitness goal and inputs it into the system through a terminal. The fitness goal (e.g., weight loss, muscle gain) is provided as input.

[1132] The terminal transmits the input fitness goal to the server, and the fitness goal data transmitted to the server is obtained as an output.

[1133] Step 14: Generate an exercise plan based on your goals and health data

[1134] The server generates an appropriate exercise plan based on the user's set goals and health data, and provides the fitness goal data and health data as input.

[1135] Emotional data is also taken into account: if the user feels tired, for example, a plan including relaxing yoga and gentle stretching will be suggested. The output is a personalized exercise plan.

[1136] Step 15: Provide an exercise plan

[1137] The server stores the generated exercise plan in the user's profile and transmits it to the terminal, which provides the generated exercise plan data as input.

[1138] The device displays the exercise plan to the user and provides the ability to track progress. As an output, the user can view the displayed exercise plan and input progress data.

[1139] Step 16: Entering Stress and Sleep Data

[1140] The user inputs their stress level and sleep state into a dedicated application, providing stress data and sleep data as input.

[1141] The terminal transmits the input data to the server, and as an output, the stress and sleep data transmitted to the server are obtained.

[1142] Step 17: Sending stress and sleep data to the server

[1143] The terminal transmits the input stress and sleep data to the server, where the stress and sleep data stored in the terminal is provided as input.

[1144] The server stores the received data and inputs it into an analysis algorithm, which outputs stress and sleep data that can be used for analysis.

[1145] Step 18: Generate mental health advice

[1146] The server generates mental health advice based on stress levels, sleep data, and emotional data. Stress data, sleep data, and emotional data are provided as input.

[1147] For example, a user experiencing high stress levels may be encouraged to meditate or listen to relaxing music. The output is mental health advice.

[1148] Step 19: Providing advice

[1149] The server stores the generated mental health advice in the user's profile and sends it to the terminal, which provides the generated mental health advice data as input.

[1150] The device displays these advices to the user and also provides a reminder function. As an output, the user can view the displayed mental health advice.

[1151] (Application example 2)

[1152] 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."

[1153] Traditionally, worker health management has relied on advice based on the results of regular health checkups, making it difficult to provide individual health guidance that responds to real-time conditions. Furthermore, the impact of workers' emotional states on their health has often been ignored, resulting in ineffective health management. This increases worker health risks, raising concerns about reduced productivity and the occurrence of work-related accidents.

[1154] 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.

[1155] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, means for recognizing the user's emotions in real time, and means for analyzing the recognized emotion data and adjusting the health advice generated by the generative AI model based on the user's emotional state. This enables effective and timely health management guidance tailored to the user's individual health and emotional state.

[1156] "Physical examination results" are the results of tests conducted to evaluate the user's health condition, and specifically include numerical data such as blood test data and physical measurement data.

[1157] A "generative AI model" is a machine learning algorithm that generates information for each user based on input data, automatically generating health advice and improvement plans.

[1158] "Personalized health advice" means guidance or suggestions for maintaining or improving health that are tailored to a specific individual and provided by a generative AI model based on the user's health checkup results and other relevant data.

[1159] "Emotion recognition" is a technology that analyzes data such as a user's facial expressions and tone of voice to infer their emotional state at that moment.

[1160] "Emotion data" is data that indicates the emotional state of the user and is obtained by emotion recognition.

[1161] "Calories intake" is a numerical value indicating the amount of energy the user takes in per day, and is calculated based on the record of dietary content.

[1162] "Nutritional balance" indicates the proportion and balance of each nutrient (protein, lipids, carbohydrates, vitamins, minerals, etc.) that the user ingests.

[1163] A "meal plan" is an optimized meal plan generated based on a user's health status and goals.

[1164] A "fitness goal" is an objective set by a user, such as improving health and physical strength or managing weight, and refers to a specific numerical value or state that the user aims to achieve.

[1165] An "exercise plan" is an exercise plan created based on a user's fitness goals and health data, and includes specific exercise content and frequency.

[1166] This invention is a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. It also integrates an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[1167] Specifically, the system includes functions for uploading and analyzing health checkup results, providing generated health advice, emotion recognition, emotion data analysis, and adjusting health advice based on emotional state.

[1168] System configuration

[1169] 1. Upload your health checkup results:

[1170] Users upload their own health checkup results to the system through a dedicated application, and the uploaded health checkup results are imported into the system in a compatible file format (e.g., PDF or CSV).

[1171] 2. Analysis of Health Examination Results:

[1172] The device sends the uploaded health checkup results to a server, which then uses an analysis algorithm to analyze the received health checkup results, including numerical data such as blood test results and physical measurement data.

[1173] 3. Use of generative AI models:

[1174] The server inputs the analyzed data into a generative AI model to generate personalized health advice. For example, if liver function is high, it will generate advice on specific dietary restrictions and lifestyle improvements.

[1175] 4. Providing health advice:

[1176] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[1177] 5. Emotion recognition:

[1178] The emotion engine captures the user's facial expressions and voice tone in real time through the camera and microphone, and recognizes their emotions. This data is periodically sent to the server.

[1179] 6. Emotional Data Analysis:

[1180] The server utilizes an emotion engine to analyze the acquired emotion data and stores the recognized emotional state in the user's profile.

[1181] 7. Adjusting advice based on emotional state:

[1182] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice including short-term actionable strategies and relaxation techniques.

[1183] Hardware and software used

[1184] Hardware:

[1185] Camera: Built-in webcam, IP camera

[1186] Microphone: Built-in microphone, external USB microphone

[1187] Devices: Smartphones, tablets, factory displays

[1188] software:

[1189] Image processing: OpenCV

[1190] Machine Learning: TensorFlow (generative AI model)

[1191] Backend server: Flask (Python framework)

[1192] Specific examples

[1193] For example, if a user uploads the results of a health check and finds that their ALT (an indicator of liver function) is high, the server will use the generative AI model to generate dietary advice such as "increase intake of green and yellow vegetables and limit alcohol intake." On the other hand, if the emotion engine detects stress from the user's facial expression, the server will adjust the generated advice based on the emotion data and also provide stress management methods.

[1194] Prompt Sentence Examples

[1195] "Analyze workers' health checkup results and generate personalized health advice based on their emotional data. If they're under stress, suggest relaxation techniques."

[1196] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1197] Step 1:

[1198] Users upload their health checkup results through a dedicated application. The input is a file of the health checkup results (e.g., PDF, CSV), and the output is the data sent from the application to the server. This data is validated and saved on the server for analysis.

[1199] Step 2:

[1200] The terminal sends the uploaded health checkup results to the server. The input is the health checkup results uploaded by the user, and the output is the data correctly transferred to the server. The server performs error checks on the received data and converts it into an analyzable format.

[1201] Step 3:

[1202] The server analyzes the received health checkup results using an analysis algorithm. The input is the uploaded health checkup results, and the output is the analyzed health data. This analysis includes processing numerical data such as blood test results and physical measurement data.

[1203] Step 4:

[1204] The server inputs the analyzed data into a generative AI model to generate personalized health advice. The input is the analyzed health data, and the output is personalized health advice. The generative AI model automatically generates personalized advice based on the health data.

[1205] Step 5:

[1206] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is the generated health advice, and the output is the data saved in the user's profile and the data sent to the terminal. The terminal displays the received advice to the user.

[1207] Step 6:

[1208] The emotion engine recognizes emotions by capturing the user's facial expressions and voice tone in real time through a camera and microphone. The input is the user's facial expressions and voice data, and the output is the recognized emotional state. This emotional data is periodically sent to the server.

[1209] Step 7:

[1210] The server analyzes the acquired emotional data using the emotion engine and stores the recognized emotional state in the user's profile. The input is the acquired emotional data from the emotion engine, and the output is the analyzed emotional state data.

[1211] Step 8:

[1212] The server adjusts the health advice generated by the generative AI model based on the user's emotional state. The input is health advice and emotional data, and the output is tailored, personalized health advice. For example, a user experiencing high stress levels will be provided with advice on urgent countermeasures and relaxation techniques.

[1213] Step 9:

[1214] The server saves the adjusted health advice in the user's profile and sends it to the terminal. The input is the adjusted health advice, and the output is the data saved in the user's profile and sent to the terminal. The terminal displays the adjusted advice to the user.

[1215] Step 10:

[1216] The user inputs the details of their daily meals and sends them to the server via their device. The input is the data of the meals, and the output is the data sent to the server. The server receives and stores this data.

[1217] Step 11:

[1218] The server calculates the balance of calories ingested and each nutrient (protein, fat, carbohydrates, vitamins, and minerals) based on the input dietary data. The input is dietary content data, and the output is calculated calorie and nutritional balance data.

[1219] Step 12:

[1220] The server generates an individualized meal plan based on the calculated data and also reflects emotional data. The input is calorie and nutritional balance data and emotional data, and the output is an adjusted individualized meal plan. The adjusted meal plan is stored on the server and sent to the device.

[1221] 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.

[1222] 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.

[1223] 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.

[1224] [Third embodiment]

[1225] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1226] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1227] 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).

[1228] 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.

[1229] 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.

[1230] 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).

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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.

[1235] 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.

[1236] 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."

[1237] The present invention provides a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[1238] Program processing details

[1239] 1. User uploads health checkup results

[1240] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[1241] 2. Sending health check results to the server

[1242] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[1243] 3. Analysis of health examination results

[1244] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[1245] 4. Use of generative AI models

[1246] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[1247] 5. Providing health advice

[1248] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[1249] Nutritional management function

[1250] 6. User input of meal details

[1251] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[1252] 7. Sending meal details to the server

[1253] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[1254] 8. Calculating calorie intake and nutritional balance

[1255] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[1256] 9. Generate personalized meal plans

[1257] The server then generates a personalized meal plan based on the calculated data, which is optimized based on the user's health status and goals. For example, a user with a vitamin C deficiency may be recommended to increase their intake of certain fruits and vegetables.

[1258] Generate a training plan

[1259] 10. User-defined fitness goals

[1260] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[1261] 11. Generate exercise plans based on your goals and health data

[1262] The server generates an appropriate exercise plan based on the user's goals and health checkup data. The plan includes exercise content (e.g., aerobic exercise three times a week) that is appropriate for the user's abilities and goals.

[1263] 12. Providing exercise plans

[1264] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[1265] Mental health support function

[1266] 13. User input of stress and sleep data

[1267] Users input their stress levels and sleep status into a dedicated application.

[1268] 14. Sending stress and sleep data to a server

[1269] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[1270] 15. Generating mental health advice

[1271] The server generates mental health advice based on stress levels and sleep data, for example, recommending relaxation meditation or deep breathing techniques for users with high stress levels.

[1272] 16. Providing Advice

[1273] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[1274] Specific examples

[1275] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[1276] 1. User Actions

[1277] Upload the health check results to a dedicated application.

[1278] 2. Device Operation

[1279] The uploaded health check results are sent to the server.

[1280] 3. Server Processing

[1281] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[1282] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[1283] 4. Server Actions

[1284] The generated advice is saved in the user's profile and sent to the terminal.

[1285] 5. Terminal Operation

[1286] Display health advice to the user.

[1287] As described above, the system of the present invention provides personalized health advice based on the user's health data and supports a comprehensive health improvement plan.

[1288] The processing flow will be explained below.

[1289] Step 1:

[1290] The user uploads the health check results to a dedicated application on their mobile device.

[1291] Step 2:

[1292] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[1293] Step 3:

[1294] The terminal sends the adapted file to the server.

[1295] Step 4:

[1296] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[1297] Step 5:

[1298] The server inputs the extracted data into the generative AI model and begins analysis.

[1299] Step 6:

[1300] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[1301] Step 7:

[1302] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[1303] Step 8:

[1304] The terminal displays the health advice received from the server to the user.

[1305] Step 9:

[1306] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[1307] Step 10:

[1308] The terminal transmits the meal data entered by the user to the server.

[1309] Step 11:

[1310] The server stores the received dietary data and calculates the calorie intake and the balance of each nutrient.

[1311] Step 12:

[1312] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[1313] Step 13:

[1314] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[1315] Step 14:

[1316] The device displays the meal plan to the user and provides reminders for implementation.

[1317] Step 15:

[1318] Users set fitness goals and input them into the system through a terminal.

[1319] Step 16:

[1320] The server generates an appropriate exercise plan based on the user's set goals and health data.

[1321] Step 17:

[1322] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[1323] Step 18:

[1324] The device displays the exercise plan to the user and provides functionality for tracking progress.

[1325] Step 19:

[1326] Users input their stress levels and sleep status into a dedicated application.

[1327] Step 20:

[1328] The terminal transmits the stress and sleep data input by the user to the server.

[1329] Step 21:

[1330] The server generates advice on stress management and sleep improvement based on the received data.

[1331] Step 22:

[1332] The server stores the generated advice in the user's profile and transmits it to the terminal.

[1333] Step 23:

[1334] The device displays stress management and sleep improvement advice to the user and provides a reminder function for implementation.

[1335] Example 1

[1336] 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."

[1337] Conventional health management systems are limited in their ability to analyze biometric data and provide individualized advice, making it difficult for users to achieve comprehensive health management. Furthermore, there is a lack of systems that can provide integrated support for diet, exercise, and even mental health. As a result, personalized advice and plans based on individual health conditions have not been adequately generated.

[1338] 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.

[1339] In this invention, the server includes means for uploading health checkup results, means for transmitting the uploaded health checkup results to the server, means for analyzing the received health checkup results, means for generating personalized health advice based on the analyzed health checkup results using a generative AI model, means for providing the generated personalized health advice to the user, means for the user to input daily meal contents, means for calculating calorie intake and nutrient balance based on the input meal contents, means for generating a personalized meal plan based on the calculated data, means for transmitting the input meal contents to the server, means for the user to set fitness goals, means for generating an appropriate exercise plan based on the set goals and health data, means for displaying the generated exercise plan to the user, means for the user to input stress levels and sleep states, means for transmitting the input stress and sleep data to the server, means for analyzing the received stress and sleep data, means for generating mental health advice based on the analysis results, and means for providing the generated mental health advice to the user, thereby enabling comprehensive and personalized health management.

[1340] "Health checkup results" are records of health status measurements taken at medical institutions, etc., and include blood test results and physical measurement data.

[1341] "Server" means a computer system that receives, analyzes, and stores data sent by users, and generates and provides necessary information and advice to users.

[1342] "Uploading" refers to the act of a user importing data such as health checkup results and dietary details into the system from their own device.

[1343] "Analysis" is the process by which the server performs statistical and computational processing on the data it receives, identifying outliers and analyzing trends.

[1344] "Generative AI model" means an artificial intelligence model used by the server to generate health advice and plans based on data, including machine learning algorithms.

[1345] "Personalized health advice" is information that suggests specific recommended actions or improvements based on each user's health condition.

[1346] "Meal contents" refers to detailed information such as the names of ingredients that the user regularly consumes, the amount of intake, and cooking methods.

[1347] "Calories intake" refers to the total amount of calories taken into the body by the user through food.

[1348] "Nutritional balance" refers to the balance of nutrients such as protein, lipids, carbohydrates, vitamins, and minerals contained in the user's diet.

[1349] A "meal plan" is a meal plan that is optimized based on the user's health status and goals.

[1350] "Fitness goals" are specific examples of goals related to physical health and exercise that a user sets, including weight loss and muscle gain.

[1351] An "exercise plan" is an exercise program designed based on a user's health data and fitness goals.

[1352] "Stress level" refers to the degree of mental and physical tension or strain felt by the user.

[1353] "Sleep state" is information relating to the quality and quantity of the user's sleep.

[1354] "Mental health advice" is specific advice for improving mental health that is suggested based on the user's stress level and sleep state.

[1355] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[1356] Hardware and software used

[1357] 1. Server: Receives, analyzes, stores data, and generates advice.

[1358] 2. Terminal: Provides an interface for users to enter data and view advice.

[1359] 3. Generative AI model: A machine learning algorithm that generates personalized advice based on health checkup results and other user data.

[1360] Data processing and calculation

[1361] Uploading and analyzing health checkup results

[1362] Users upload their health checkup results using a dedicated application. The device then sends the file uploaded by the user to a server. This file includes blood test results and physical measurement data. The server performs error checks on the received data and analyzes it using an analytical algorithm. This analyzed data is then input into a generative AI model, which generates personalized health advice.

[1363] For example, if a user has a high ALT (liver function index) value, the generative AI model will generate health advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[1364] Nutritional management function

[1365] Users input their daily dietary information into a dedicated application. This information includes the names of ingredients, the amount of each ingredient, and cooking methods. The device then sends this data to a server, which then calculates the balance of calories and nutrients (protein, fat, carbohydrates, vitamins, and minerals) and generates a personalized meal plan based on the results.

[1366] For example, a user who is deficient in vitamin C will be provided with a meal plan that encourages consumption of orange fruits and green vegetables.

[1367] Training plan generation function

[1368] Users use a dedicated app to set fitness goals, such as weight loss or muscle gain. The device then sends these goals to a server, which then generates a personalized exercise plan based on the user's goals and health data.

[1369] For example, a user looking to lose weight may be offered an exercise plan that includes aerobic exercise.

[1370] Mental health support function

[1371] Users use the app to input their stress levels and sleep patterns, and the device sends this data to a server that analyzes it and generates mental health advice.

[1372] For example, users with high stress levels may be encouraged to meditate or take deep breaths to relax.

[1373] Examples of specific examples and prompts

[1374] For example, if you want to upload your health checkup results and generate the necessary advice from them, you could input the following prompts into the generative AI model:

[1375] "Create dietary and lifestyle advice for users whose ALT levels exceed normal levels."

[1376] Based on this prompt, the generative AI model will provide the user with appropriate health advice. In this way, the system provides personalized advice based on the user's health data, supporting comprehensive health management.

[1377] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1378] Step 1:

[1379] The user logs in to the dedicated application and clicks the "Upload health checkup results" button. Next, they select the health checkup results file (PDF or CSV format) they want to upload and import it into the system. The input is the health checkup results file, and the output is a notification that the file has been uploaded. This operation imports the file into the system.

[1380] Step 2:

[1381] The terminal sends the health check result file uploaded by the user to the server. At this time, the terminal checks the format and size of the file and checks for transmission errors. The input is the uploaded file, and the output is the file sent to the server. Once the terminal sends the file to the server, it proceeds to the next processing step.

[1382] Step 3:

[1383] The server inputs the received health check result file into the analysis algorithm. The algorithm analyzes blood test results (e.g., ALT, AST, blood glucose levels) and physical measurement data (e.g., weight, height, BMI, etc.). The input is the health check result file, and the output is the analyzed data. The server analyzes the data and extracts abnormal values ​​and data requiring attention.

[1384] Step 4:

[1385] The server inputs the analysis results into a generative AI model, which generates personalized health advice based on the given data. The input is the analyzed data, and the output is personalized health advice. For example, specific advice such as "Since your ALT is high, increase your intake of green and yellow vegetables and limit your alcohol intake" may be generated.

[1386] Step 5:

[1387] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is personalized health advice, and the output is saving it in the user's profile and sending it to the terminal. The server prepares the advice to provide to the user.

[1388] Step 6:

[1389] The terminal receives the generated health advice and notifies the user. When the user logs in to the application, they can view the latest health advice. The input is the health advice sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the advice.

[1390] Step 7:

[1391] Users input their daily dietary information into a dedicated application. The dietary information includes the names of ingredients, the amount of food consumed, and cooking methods. The input is the daily dietary information, and the output is a notification that the dietary data has been entered. This operation imports the dietary data into the system.

[1392] Step 8:

[1393] The terminal transmits the input meal details to the server. The input is meal data, and the output is transmission to the server. The terminal provides the meal details data to the server.

[1394] Step 9:

[1395] The server calculates the calorie intake and balance of each nutrient (protein, fat, carbohydrates, vitamins, minerals) based on the input dietary data. The input is dietary data, and the output is the calculated calorie intake and nutritional balance. The server calculates and analyzes the data.

[1396] Step 10:

[1397] The server generates an individualized meal plan based on the calculated data and sends it to the device. The input is the calculation result, and the output is an individualized meal plan. For example, if a user is deficient in vitamin C, a plan recommending fruits and vegetables rich in vitamin C will be generated.

[1398] Step 11:

[1399] The terminal receives the generated individual meal plan and notifies the user. When the user logs in to the application, they can view the latest meal plan. The input is the meal plan sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the meal plan.

[1400] Step 12:

[1401] The user sets fitness goals using a dedicated application. Fitness goals can include weight loss or muscle gain. The input is the fitness goal, and the output is a notification that the goal has been entered. This operation imports the fitness goal into the system.

[1402] Step 13:

[1403] The terminal transmits the set fitness goal to the server. The input is the fitness goal and the output is the transmission to the server. The terminal provides the goal data to the server.

[1404] Step 14:

[1405] The server generates an appropriate exercise plan based on the user's fitness goals and health data (e.g., weight, height, and past exercise habits). The input is the fitness goals and health data, and the output is the exercise plan. The server analyzes the data and designs the exercise plan.

[1406] Step 15:

[1407] The server sends the generated exercise plan to the device and saves it in the user's profile. The input is the exercise plan, and the output is sending it to the device and saving it in the profile. The server is ready to provide the plan.

[1408] Step 16:

[1409] The device receives the generated exercise plan and notifies the user. When the user logs in to the application, they can check the latest exercise plan. The input is the exercise plan sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the plan.

[1410] Step 17:

[1411] The user uses the application to input their own stress level and sleep state. The input is the stress level and sleep state, and the output is a notification that the data has been input. This operation inputs the stress and sleep data into the system.

[1412] Step 18:

[1413] The terminal transmits the input stress and sleep data to the server. The input is stress and sleep data, and the output is transmission to the server. The terminal provides data to the server.

[1414] Step 19:

[1415] The server analyzes the received stress and sleep data and generates mental health advice. The input is stress and sleep data, and the output is mental health advice. For example, a user with a high stress level may be recommended to meditate or take deep breaths to relax.

[1416] Step 20:

[1417] The server generates mental health advice, stores it in the user's profile, and sends it to the device. The input is the mental health advice, and the output is sending it to the device and saving it in the profile. The server is ready to provide the advice.

[1418] Step 21:

[1419] The device receives the generated mental health advice and notifies the user. When the user logs in to the application, they can view the latest mental health advice. The input is the mental health advice sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the advice.

[1420] Through the above processing steps, the system provides personalized advice based on the user's health data and supports comprehensive health management.

[1421] (Application example 1)

[1422] 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."

[1423] Effective individual health management is extremely important in modern society, but existing systems have difficulty providing sufficient personalized health advice and reminders. Furthermore, the generation of nutritional management and training plans based on health checkup results is not automated, leaving users to manage these themselves. Furthermore, mental health support functions based on stress and sleep data are often not integrated. To solve these issues, a more comprehensive and automated health management system is needed.

[1424] 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.

[1425] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, and means for notifying the user of the generated advice and reminders. This allows the user to receive detailed health advice based on the health checkup results and accompanying reminders.

[1426] The system further includes a means for a user to input daily meal contents, a means for calculating calorie intake and nutritional balance based on the input meal contents, a means for generating an individual meal plan based on the calculated data, and a means for providing a reminder function based on advice.

[1427] The device further includes a means for allowing a user to set fitness goals, a means for generating an appropriate exercise plan based on the set goals and health data, a means for displaying the generated exercise plan to the user, and a means for providing a reminder function based on the exercise plan, thereby enabling the user to efficiently manage their overall health.

[1428] "Health checkup results" refer to various health indicators and numerical data obtained as a result of health checkups conducted at medical institutions or testing facilities.

[1429] "Individualized health advice" refers to health guidance and instructions that are optimized for each individual based on individual data such as the user's health checkup results and lifestyle.

[1430] "Uploading means" refers to the process or technology by which a user submits medical examination results in the form of a digital file to the system.

[1431] "Means of analysis" refers to the technology or algorithms that process the uploaded health check result data and extract the necessary information.

[1432] A "generative AI model" is a model that uses artificial intelligence technology to find patterns and relationships from input data and generate appropriate output.

[1433] A "reminder" is a notification function that notifies the user of a specific time or action.

[1434] The "nutritional management function" is a function that records and analyzes the user's diet and adjusts the nutritional balance.

[1435] The "training plan generation function" is a function that creates an exercise plan based on the user's fitness goals and health data.

[1436] The "mental health support function" is a function for supporting the user's psychological health and provides advice that is useful for stress management and improving sleep.

[1437] The "smart notification function" is a function that notifies users of health advice and reminders in real time.

[1438] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. This system is implemented as a smartphone application and operates in conjunction with a backend running on a server.

[1439] Hardware and software used

[1440] Hardware: Smartphone

[1441] software:

[1442] Frontend: React Native (for cross-platform app development)

[1443] Backend: Node.js, Python (AI model)

[1444] Database: MongoDB

[1445] Cloud services: AWS (data processing and storage)

[1446] Processing Details

[1447] Uploading and analyzing health checkup results

[1448] Users upload their health checkup results in PDF or CSV format using their smartphones. The uploaded file is sent to a Node.js-based server through a front-end application using React Native. The server analyzes the received file and extracts the necessary health indicators.

[1449] Generative AI model generates advice

[1450] The analyzed data is input into a generative AI model, a Python-based AI model. This model generates personalized health advice based on the input data. For example, if the liver function score is high, specific advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption" is generated.

[1451] Providing health advice

[1452] The generated advice is stored in MongoDB and linked to the user's profile. A front-end application periodically retrieves this data and notifies the user. A smart notification feature also sets reminders and helps the user take the suggested actions.

[1453] Nutrition management and training plan generation functions

[1454] Users enter their daily dietary habits and fitness goals into the application. This data is then sent to the server and analyzed. Based on the analysis results, calorie intake and nutritional balance are calculated and an individualized meal plan is generated. An exercise plan based on the user's fitness goals is also generated and provided to the user. Reminders are also set for these plans to help the user continue to manage their health.

[1455] Specific example explanation

[1456] For example, if a user uploads their medical checkup results and finds that their liver function indicator, ALT, is high, the following specific steps will be taken:

[1457] 1. The user uploads the health check result file.

[1458] 2. The server receives the file and analyzes it.

[1459] 3. Based on the analysis results, the generated AI model generates advice such as "increase your intake of green and yellow vegetables and limit your alcohol intake."

[1460] 4. The server saves the generated advice in the user's profile and the application notifies the user.

[1461] Prompt Sentence Examples

[1462] An example of a text prompt is:

[1463] "Generate personalized health advice based on the user's health check results. The following data indicates high liver function values.

[1464] Liver function: High

[1465] Blood sugar: normal

[1466] Any advice generated should include specific dietary restrictions or lifestyle changes."

[1467] In this way, the system of the present invention utilizes data obtained from health checkup results in a multifaceted manner to support comprehensive health management.

[1468] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1469] Step 1:

[1470] Users upload their health checkup results using a smartphone application.

[1471] In this example, the user opens the app, selects a PDF or CSV format health checkup result file, and presses the send button. The input health checkup result file is sent to the server via the application.

[1472] Step 2:

[1473] The terminal sends the uploaded health check result file to the server.

[1474] The device receives the file and sends a POST request to the specified API endpoint. The input is a diagnostic result file in PDF or CSV format, which is then sent to the server.

[1475] Step 3:

[1476] The server receives the file and checks for errors.

[1477] The server checks the format and content of the received file and performs an error check. After the error check, it temporarily saves it for analysis. The input is the diagnostic result file, and the output is an error report or a confirmation message to proceed with the analysis.

[1478] Step 4:

[1479] The server analyzes the health check results and extracts the necessary health indicators.

[1480] The server uses an analysis algorithm to analyze the files and extract numerical data such as blood test results and physical measurement data. The input is the diagnostic result file, and the output is health index data.

[1481] Step 5:

[1482] The server inputs the analyzed data into a generative AI model.

[1483] The server passes the extracted health index data to a generative AI model to generate personalized health advice. The input is the health index data, and the output is the health advice.

[1484] Step 6:

[1485] The server stores the generated health advice in a database.

[1486] The server stores the generated advice in a database linked to the user's profile. The input is the health advice and the output is a message confirming the data storage.

[1487] Step 7:

[1488] The server notifies the device of advice and reminders.

[1489] The server sends the saved advice to the device and notifies the user via instant messaging or notification. The input is health advice, and the output is notification to the user device.

[1490] Step 8:

[1491] Users enter their daily diet and fitness goals into the app.

[1492] Users input and submit their dietary information and fitness goals through the app. The input is their daily dietary information and fitness goals, and the output is data sent to the server via the application.

[1493] Step 9:

[1494] The server analyzes the entered data and generates personalized meal and exercise plans.

[1495] The server analyzes data on daily dietary habits and fitness goals, calculates calorie intake and nutritional balance, and generates appropriate meal and exercise plans. The input is daily dietary habits and fitness goals, and the output is an individual plan.

[1496] Step 10:

[1497] The device displays the generated plan to the user and sets reminders.

[1498] The terminal displays the individual plan received from the server to the user and sets reminders. The input is the generated plan, and the output is the plan displayed to the user and the set reminders.

[1499] 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.

[1500] This invention integrates a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans, as well as an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[1501] Program processing details

[1502] 1. User uploads health checkup results

[1503] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[1504] 2. Sending health check results to the server

[1505] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[1506] 3. Analysis of health examination results

[1507] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[1508] 4. Use of generative AI models

[1509] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[1510] 5. Providing health advice

[1511] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[1512] Emotion engine integration

[1513] 6. User Emotion Recognition

[1514] The emotion engine has the ability to recognize emotions in real time from the user's facial expressions, tone of voice, etc. When the user uses the dedicated application, emotional data is collected through the built-in camera and microphone.

[1515] 7. Transmission and analysis of emotional data

[1516] The device transmits the captured emotion data to a server, which uses an emotion engine to analyze the data and store the recognized emotional state in the user's profile.

[1517] 8. Adjusting advice based on emotions

[1518] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice on taking immediate action.

[1519] Nutritional management function

[1520] 9. User input of meal details

[1521] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[1522] 10. Sending meal details to the server

[1523] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[1524] 11. Calculating calorie intake and nutritional balance

[1525] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[1526] 12. Generate personalized meal plans

[1527] The server then generates a personalized meal plan based on the calculated data. This plan is optimized based on the user's health status and goals. It also incorporates emotional data, recommending foods with a relaxing effect if the user is under high stress.

[1528] Generate a training plan

[1529] 13. User-defined fitness goals

[1530] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[1531] 14. Generate exercise plans based on your goals and health data

[1532] The server generates an appropriate exercise plan based on the user's goals and health data. The plan is also tailored to take emotional data into account. For example, if the user feels tired, a plan including relaxing yoga and light stretching will be suggested.

[1533] 15. Providing exercise plans

[1534] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[1535] Mental health support function

[1536] 16. User input of stress and sleep data

[1537] Users input their stress levels and sleep status into a dedicated application.

[1538] 17. Sending stress and sleep data to a server

[1539] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[1540] 18. Generating mental health advice

[1541] The server generates mental health advice based on stress levels, sleep data, and emotional data. For example, a user experiencing high stress might be recommended meditation, deep breathing techniques, or listening to relaxing music.

[1542] 19. Providing Advice

[1543] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[1544] Specific examples

[1545] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[1546] 1. User Actions

[1547] Upload the health check results to a dedicated application.

[1548] 2. Device Operation

[1549] The uploaded health check results are sent to the server.

[1550] 3. Server Processing

[1551] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[1552] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[1553] 4. User Emotion Recognition

[1554] The emotion engine detects stress from the user's facial expression.

[1555] 5. Server Actions

[1556] The generated advice reflects emotional data and also provides stress management techniques.

[1557] The advice is saved in the user's profile and sent to the device.

[1558] 6. Terminal Operation

[1559] Displaying health and stress management advice to the user.

[1560] As described above, the system of the present invention integrates a user's health data and emotional data to provide more personalized health advice and support a comprehensive health improvement plan.

[1561] The processing flow will be explained below.

[1562] Step 1:

[1563] The user uploads the health check results to a dedicated application on their mobile device.

[1564] Step 2:

[1565] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[1566] Step 3:

[1567] The terminal sends the adapted file to the server.

[1568] Step 4:

[1569] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[1570] Step 5:

[1571] The server inputs the extracted data into the generative AI model and begins analysis.

[1572] Step 6:

[1573] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[1574] Step 7:

[1575] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[1576] Step 8:

[1577] The terminal displays the health advice received from the server to the user.

[1578] Step 9:

[1579] The emotion engine analyzes the user's facial expressions and tone of voice to obtain emotional data in real time.

[1580] Step 10:

[1581] The terminal transmits the acquired emotion data to the server.

[1582] Step 11:

[1583] The server receives the analysis results of the emotion engine and identifies the user's emotional state, for example, if the user is feeling stressed, that state is saved in the profile.

[1584] Step 12:

[1585] The server takes into account the user's emotional state and adjusts the health advice provided by the generative AI model: for example, if stress levels are high, advice encouraging relaxation will be added.

[1586] Step 13:

[1587] The server stores the adjusted health advice again in the user's profile and transmits it to the terminal.

[1588] Step 14:

[1589] The terminal displays the tailored health advice to the user.

[1590] Step 15:

[1591] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[1592] Step 16:

[1593] The terminal transmits the input meal details to the server.

[1594] Step 17:

[1595] The server stores the received dietary data and calculates the balance of ingested calories and each nutrient (e.g., protein, fat, carbohydrates, vitamins, and minerals).

[1596] Step 18:

[1597] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[1598] Step 19:

[1599] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[1600] Step 20:

[1601] The device displays the meal plan to the user and provides reminders for implementation.

[1602] Step 21:

[1603] Users set fitness goals and input them into the system through a terminal.

[1604] Step 22:

[1605] The server generates an appropriate exercise plan based on the user's set goals and health data, and the plan is adjusted to take emotional data into account.

[1606] Step 23:

[1607] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[1608] Step 24:

[1609] The device displays the exercise plan to the user and provides functionality for tracking progress.

[1610] Step 25:

[1611] Users input their stress levels and sleep status into a dedicated application.

[1612] Step 26:

[1613] The terminal transmits the input data to the server.

[1614] Step 27:

[1615] The server analyzes the received stress and sleep data and generates mental health advice taking into account emotional data.

[1616] Step 28:

[1617] The server stores the generated mental health advice in the user's profile and sends it to the terminal.

[1618] Step 29:

[1619] The device displays mental health advice to the user and provides reminders for action.

[1620] These are the specific processing steps of this system that integrates an emotion engine, allowing users to receive more personalized health care.

[1621] Example 2

[1622] 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."

[1623] Conventional health management systems analyze users' health checkup results and provide health advice based on them, but because they do not take the user's emotional state into consideration, the advice is often ineffective. Furthermore, because a user's emotional state has a significant impact on health behavior, advice that ignores this has the problem of being difficult to implement.

[1624] The specification process by the specification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for analyzing health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for recognizing the user's emotions and acquiring emotional data, means for transmitting the acquired emotional data to the server for analysis, and means for adjusting the generated health advice based on the user's emotional data. This makes it possible to consider the user's health state and emotional state in an integrated manner, thereby enabling the provision of more effective and easy-to-follow health advice.

[1625] The "health checkup result uploading means" is a means for a user to send health checkup results to the system.

[1626] The "medical examination result transmission means" is a means for the terminal to transmit the medical examination results uploaded by the user to the server.

[1627] The "health checkup result analysis means" is a means for analyzing the health checkup results received by the server.

[1628] A "generative AI model" is an AI model that generates individual health advice based on analyzed health checkup results.

[1629] A "means for generating personalized health advice using a generative AI model" is a means for generating personalized health advice from data analyzed using a generative AI model.

[1630] The "health advice providing means" is a means for providing the generated individual health advice to the user.

[1631] The "emotion recognition means" is a means for recognizing the user's emotions based on their facial expressions and voice tones.

[1632] The "emotion data acquisition means" is a means for acquiring the user's emotion data.

[1633] The "emotion data transmission means" is a means for transmitting the acquired emotion data to the server.

[1634] "Emotion data analysis means" is a means by which the server analyzes emotion data.

[1635] The "means for adjusting advice based on emotion data" is a means for adjusting the generated health advice based on the emotion data of the user.

[1636] The "meal content input means" is a means for a user to input daily meal content into the system.

[1637] The "calorie intake calculation means" is a means for calculating calorie intake based on the input meal contents.

[1638] The "nutritional balance calculation means" is a means for calculating the balance of nutrients based on the input meal contents.

[1639] "Meal plan generator" means a means for generating an individualized meal plan based on the calculated data.

[1640] The "fitness goal setting means" is a means for a user to set a fitness goal in the system.

[1641] The "exercise plan generation means" is a means for generating an appropriate exercise plan based on the set goals and health data.

[1642] The "exercise plan providing means" is a means for providing the generated exercise plan to the user.

[1643] The "exercise plan adjustment means" is a means for adjusting the generated exercise plan based on the user's emotional data.

[1644] The "stress data input means" is a means for a user to input a stress level into the system.

[1645] The "sleep data input means" is a means for the user to input sleep status into the system.

[1646] The "stress and sleep data transmission means" is a means for transmitting input stress and sleep data to a server.

[1647] The "mental health advice generation means" is a means for generating mental health advice based on stress levels, sleep data, and emotional data.

[1648] The "mental health advice providing means" is a means for providing the generated mental health advice to the user.

[1649] This invention integrates an emotion engine that recognizes the user's emotions into a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system includes a generative AI model, a nutrition management function, a training plan generation function, and a mental health support function.

[1650] Hardware and software used

[1651] Dedicated applications (e.g., HealthApp): Tools that allow users to upload and enter health checkup results and dietary information.

[1652] Server (e.g., central data server): Analyzes and stores data, runs generative AI models, and analyzes emotion data.

[1653] Generative AI models (e.g., GPT-4): AI models for generating personalized health advice.

[1654] Emotion engine (e.g., EmotionDetector): Recognizes emotions by analyzing the user's facial expressions and tone of voice.

[1655] Analysis algorithms (e.g., HealthAnalyzer, CalorieCounter): Analyze health checkup results, dietary data, and exercise data.

[1656] Specific operation of the system

[1657] 1. Upload your health checkup results

[1658] Users open the dedicated application, select and upload their health check results (in PDF or CSV format).

[1659] The device sends the uploaded health check results to the server, which performs error checks to verify the integrity of the received data.

[1660] 2. Analysis of health examination results

[1661] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[1662] The analysis results are input into a generative AI model, which generates personalized health advice. For example, a user with high liver function scores might be advised to increase their intake of green and yellow vegetables and limit alcohol consumption.

[1663] 3. Providing health advice

[1664] The server saves the generated health advice in the user's profile and sends it to the device, which displays the advice to the user.

[1665] 4. Functions of the Emotion Engine

[1666] When a user uses a dedicated application, emotional data such as facial expressions and voice tone is acquired through the built-in camera and microphone. The emotion engine analyzes this data and recognizes the user's emotional state.

[1667] The device sends the acquired emotion data to the server, which uses an emotion engine to analyze the emotion data and saves it in the user's profile.

[1668] 5. Adjusting advice based on emotions

[1669] The server then adjusts the health advice generated by the generative AI model based on the user's emotional data. For example, if a user is experiencing high stress, it will also provide them with stress management techniques.

[1670] 6. Nutritional management function

[1671] Users input their daily dietary information into a dedicated application, which records the names of ingredients, the amount consumed, cooking methods, and other information.

[1672] The terminal transmits the entered meal details to the server.

[1673] The server calculates calorie intake and nutritional balance based on the received dietary data. Based on the calculation results, a personalized meal plan is generated. The plan is optimized based on the user's health status and goals, and also takes emotional data into account.

[1674] 7. Generate a training plan

[1675] Users set fitness goals and input them into the system through a terminal, such as "weight loss" or "muscle gain."

[1676] The server generates an appropriate exercise plan based on the user's goals and health data, taking emotional data into account and suggesting light exercise if the user feels tired, for example.

[1677] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the plan to the user and provides the ability to track progress.

[1678] 8. Mental health support function

[1679] Users input their stress levels and sleep status into a dedicated application.

[1680] The terminal transmits the input data to the server.

[1681] The server generates mental health advice based on stress, sleep, and emotional data. For example, users with high stress levels may be recommended meditation or deep breathing techniques.

[1682] Specific examples

[1683] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[1684] Users upload their health checkup results to a dedicated application.

[1685] The terminal transmits the diagnosis results to the server.

[1686] The server analyzes the data and generates personalized health advice using a generative AI model, such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[1687] The emotion engine detects stress from the user's facial expression.

[1688] The server reflects emotional data in its advice and also provides stress management techniques.

[1689] The device displays health and stress management advice to the user.

[1690] Example prompts to input to the generative AI model

[1691] "Based on the user's health checkup results, generate dietary advice for those with high liver function. Also, take stress management methods into consideration when generating advice."

[1692] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1693] Step 1: Upload your health check results

[1694] The user opens a dedicated application (e.g., HealthApp) and selects and uploads their own health checkup results. The user's health checkup result file (PDF or CSV format) is provided as input.

[1695] The terminal receives the uploaded health checkup results, checks their consistency, and then transmits them to the server. The output is the health checkup result data transmitted to the server.

[1696] Step 2: Submit your health check results

[1697] The terminal transmits the uploaded health checkup results to the server, and the health checkup result data stored in the terminal is provided as input.

[1698] The server stores the received medical examination results for analysis and performs error checking. As an output, medical examination result data that can be used for analysis is obtained.

[1699] Step 3: Analysis of health check results

[1700] The server analyzes the received health checkup results using an analysis algorithm (e.g., HealthAnalyzer). Health checkup result data is provided as input.

[1701] The analysis includes numerical data such as blood test results and anthropometric data, and health status is assessed from these data. The output is the analyzed health status data.

[1702] Step 4: Use the generative AI model

[1703] The server inputs the analyzed data into a generative AI model (e.g., GPT-4), which provides the analyzed health status data as input.

[1704] The generative AI model generates personalized health advice based on the data. For example, if the liver function score is high, the generated advice would be "increase your intake of green and yellow vegetables and limit alcohol consumption." The output is personalized health advice.

[1705] Step 5: Providing health advice

[1706] The server stores the generated health advice in the user's profile and sends it to the terminal, which provides the generated health advice data as input.

[1707] The terminal displays the received health advice to the user, and as an output, the user can view the displayed health advice.

[1708] Step 6: Emotion Recognition

[1709] The emotion engine recognizes emotions in real time from the user's facial expressions and voice tone. Inputs include facial expression data and voice data captured through the built-in camera and microphone.

[1710] The terminal transmits the acquired emotion data to the server, and the emotion data transmitted to the server is obtained as an output.

[1711] Step 7: Send and analyze emotion data

[1712] The terminal transmits the acquired emotion data to the server, which provides the emotion data stored in the terminal as input.

[1713] The server analyzes these data using an emotion engine and stores the recognized emotional state in the user's profile. The output is the analyzed emotion data.

[1714] Step 8: Adjust your advice based on emotions

[1715] The server adjusts the health advice generated by the generative AI model based on the user's emotional state, and receives as input the generated health advice data and the analyzed emotional data.

[1716] For example, a user experiencing high stress may also be offered stress management techniques. The output is tailored health advice.

[1717] Step 9: Enter your meal details

[1718] Users input their daily dietary information into a dedicated application, providing detailed dietary data such as ingredient names, intake amounts, and cooking methods.

[1719] The terminal transmits the input meal details to the server, and the meal data transmitted to the server is obtained as an output.

[1720] Step 10: Sending meal details to the server

[1721] The terminal transmits the input meal details to the server. As input, meal data stored in the terminal is provided.

[1722] The server stores the received data and inputs it into an analysis algorithm, which outputs dietary data that can be used for analysis.

[1723] Step 11: Calculate your calorie intake and nutritional balance

[1724] The server calculates the balance of calories and nutrients (e.g., protein, fat, carbohydrates, vitamins, and minerals) based on the input dietary data. Dietary data is provided as input.

[1725] The calculated data is used to generate a personalized meal plan, with calorie intake and nutritional balance data as output.

[1726] Step 12: Generate a personalized meal plan

[1727] The server generates a personalized meal plan based on the calculated data, providing calorie intake and nutritional balance data as input.

[1728] The plan is optimized based on the user's health status and goals, and also takes emotional data into account. The output is a personalized meal plan.

[1729] Step 13: Set your fitness goals

[1730] A user sets a fitness goal and inputs it into the system through a terminal. The fitness goal (e.g., weight loss, muscle gain) is provided as input.

[1731] The terminal transmits the input fitness goal to the server, and the fitness goal data transmitted to the server is obtained as an output.

[1732] Step 14: Generate an exercise plan based on your goals and health data

[1733] The server generates an appropriate exercise plan based on the user's set goals and health data, and provides the fitness goal data and health data as input.

[1734] Emotional data is also taken into account: if the user feels tired, for example, a plan including relaxing yoga and gentle stretching will be suggested. The output is a personalized exercise plan.

[1735] Step 15: Provide an exercise plan

[1736] The server stores the generated exercise plan in the user's profile and transmits it to the terminal, which provides the generated exercise plan data as input.

[1737] The device displays the exercise plan to the user and provides the ability to track progress. As an output, the user can view the displayed exercise plan and input progress data.

[1738] Step 16: Entering Stress and Sleep Data

[1739] The user inputs their stress level and sleep state into a dedicated application, providing stress data and sleep data as input.

[1740] The terminal transmits the input data to the server, and as an output, the stress and sleep data transmitted to the server are obtained.

[1741] Step 17: Sending stress and sleep data to the server

[1742] The terminal transmits the input stress and sleep data to the server, where the stress and sleep data stored in the terminal is provided as input.

[1743] The server stores the received data and inputs it into an analysis algorithm, which outputs stress and sleep data that can be used for analysis.

[1744] Step 18: Generate mental health advice

[1745] The server generates mental health advice based on stress levels, sleep data, and emotional data. Stress data, sleep data, and emotional data are provided as input.

[1746] For example, a user experiencing high stress levels may be encouraged to meditate or listen to relaxing music. The output is mental health advice.

[1747] Step 19: Providing advice

[1748] The server stores the generated mental health advice in the user's profile and sends it to the terminal, which provides the generated mental health advice data as input.

[1749] The device displays these advices to the user and also provides a reminder function. As an output, the user can view the displayed mental health advice.

[1750] (Application example 2)

[1751] 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."

[1752] Traditionally, worker health management has relied on advice based on the results of regular health checkups, making it difficult to provide individual health guidance that responds to real-time conditions. Furthermore, the impact of workers' emotional states on their health has often been ignored, resulting in ineffective health management. This increases worker health risks, raising concerns about reduced productivity and the occurrence of work-related accidents.

[1753] 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.

[1754] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, means for recognizing the user's emotions in real time, and means for analyzing the recognized emotion data and adjusting the health advice generated by the generative AI model based on the user's emotional state. This enables effective and timely health management guidance tailored to the user's individual health and emotional state.

[1755] "Physical examination results" are the results of tests conducted to evaluate the user's health condition, and specifically include numerical data such as blood test data and physical measurement data.

[1756] A "generative AI model" is a machine learning algorithm that generates information for each user based on input data, automatically generating health advice and improvement plans.

[1757] "Personalized health advice" means guidance or suggestions for maintaining or improving health that are tailored to a specific individual and provided by a generative AI model based on the user's health checkup results and other relevant data.

[1758] "Emotion recognition" is a technology that analyzes data such as a user's facial expressions and tone of voice to infer their emotional state at that moment.

[1759] "Emotion data" is data that indicates the emotional state of the user and is obtained by emotion recognition.

[1760] "Calories intake" is a numerical value indicating the amount of energy the user takes in per day, and is calculated based on the record of dietary content.

[1761] "Nutritional balance" indicates the proportion and balance of each nutrient (protein, lipids, carbohydrates, vitamins, minerals, etc.) that the user ingests.

[1762] A "meal plan" is an optimized meal plan generated based on a user's health status and goals.

[1763] A "fitness goal" is an objective set by a user, such as improving health and physical strength or managing weight, and refers to a specific numerical value or state that the user aims to achieve.

[1764] An "exercise plan" is an exercise plan created based on a user's fitness goals and health data, and includes specific exercise content and frequency.

[1765] This invention is a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. It also integrates an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[1766] Specifically, the system includes functions for uploading and analyzing health checkup results, providing generated health advice, emotion recognition, emotion data analysis, and adjusting health advice based on emotional state.

[1767] System configuration

[1768] 1. Upload your health checkup results:

[1769] Users upload their own health checkup results to the system through a dedicated application, and the uploaded health checkup results are imported into the system in a compatible file format (e.g., PDF or CSV).

[1770] 2. Analysis of Health Examination Results:

[1771] The device sends the uploaded health checkup results to a server, which then uses an analysis algorithm to analyze the received health checkup results, including numerical data such as blood test results and physical measurement data.

[1772] 3. Use of generative AI models:

[1773] The server inputs the analyzed data into a generative AI model to generate personalized health advice. For example, if liver function is high, it will generate advice on specific dietary restrictions and lifestyle improvements.

[1774] 4. Providing health advice:

[1775] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[1776] 5. Emotion recognition:

[1777] The emotion engine captures the user's facial expressions and voice tone in real time through the camera and microphone, and recognizes their emotions. This data is periodically sent to the server.

[1778] 6. Emotional Data Analysis:

[1779] The server utilizes an emotion engine to analyze the acquired emotion data and stores the recognized emotional state in the user's profile.

[1780] 7. Adjusting advice based on emotional state:

[1781] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice including short-term actionable strategies and relaxation techniques.

[1782] Hardware and software used

[1783] Hardware:

[1784] Camera: Built-in webcam, IP camera

[1785] Microphone: Built-in microphone, external USB microphone

[1786] Devices: Smartphones, tablets, factory displays

[1787] software:

[1788] Image processing: OpenCV

[1789] Machine Learning: TensorFlow (generative AI model)

[1790] Backend server: Flask (Python framework)

[1791] Specific examples

[1792] For example, if a user uploads the results of a health check and finds that their ALT (an indicator of liver function) is high, the server will use the generative AI model to generate dietary advice such as "increase intake of green and yellow vegetables and limit alcohol intake." On the other hand, if the emotion engine detects stress from the user's facial expression, the server will adjust the generated advice based on the emotion data and also provide stress management methods.

[1793] Prompt Sentence Examples

[1794] "Analyze workers' health checkup results and generate personalized health advice based on their emotional data. If they're under stress, suggest relaxation techniques."

[1795] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1796] Step 1:

[1797] Users upload their health checkup results through a dedicated application. The input is a file of the health checkup results (e.g., PDF, CSV), and the output is the data sent from the application to the server. This data is validated and saved on the server for analysis.

[1798] Step 2:

[1799] The terminal sends the uploaded health checkup results to the server. The input is the health checkup results uploaded by the user, and the output is the data correctly transferred to the server. The server performs error checks on the received data and converts it into an analyzable format.

[1800] Step 3:

[1801] The server analyzes the received health checkup results using an analysis algorithm. The input is the uploaded health checkup results, and the output is the analyzed health data. This analysis includes processing numerical data such as blood test results and physical measurement data.

[1802] Step 4:

[1803] The server inputs the analyzed data into a generative AI model to generate personalized health advice. The input is the analyzed health data, and the output is personalized health advice. The generative AI model automatically generates personalized advice based on the health data.

[1804] Step 5:

[1805] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is the generated health advice, and the output is the data saved in the user's profile and the data sent to the terminal. The terminal displays the received advice to the user.

[1806] Step 6:

[1807] The emotion engine recognizes emotions by capturing the user's facial expressions and voice tone in real time through a camera and microphone. The input is the user's facial expressions and voice data, and the output is the recognized emotional state. This emotional data is periodically sent to the server.

[1808] Step 7:

[1809] The server analyzes the acquired emotional data using the emotion engine and stores the recognized emotional state in the user's profile. The input is the acquired emotional data from the emotion engine, and the output is the analyzed emotional state data.

[1810] Step 8:

[1811] The server adjusts the health advice generated by the generative AI model based on the user's emotional state. The input is health advice and emotional data, and the output is tailored, personalized health advice. For example, a user experiencing high stress levels will be provided with advice on urgent countermeasures and relaxation techniques.

[1812] Step 9:

[1813] The server saves the adjusted health advice in the user's profile and sends it to the terminal. The input is the adjusted health advice, and the output is the data saved in the user's profile and sent to the terminal. The terminal displays the adjusted advice to the user.

[1814] Step 10:

[1815] The user inputs the details of their daily meals and sends them to the server via their device. The input is the data of the meals, and the output is the data sent to the server. The server receives and stores this data.

[1816] Step 11:

[1817] The server calculates the balance of calories ingested and each nutrient (protein, fat, carbohydrates, vitamins, and minerals) based on the input dietary data. The input is dietary content data, and the output is calculated calorie and nutritional balance data.

[1818] Step 12:

[1819] The server generates an individualized meal plan based on the calculated data and also reflects emotional data. The input is calorie and nutritional balance data and emotional data, and the output is an adjusted individualized meal plan. The adjusted meal plan is stored on the server and sent to the device.

[1820] 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.

[1821] 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.

[1822] 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.

[1823] [Fourth embodiment]

[1824] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1825] 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.

[1826] 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).

[1827] 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.

[1828] 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.

[1829] 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).

[1830] 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.

[1831] 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.

[1832] 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.

[1833] 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.

[1834] 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.

[1835] 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.

[1836] 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."

[1837] The present invention provides a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[1838] Program processing details

[1839] 1. User uploads health checkup results

[1840] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[1841] 2. Sending health check results to the server

[1842] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[1843] 3. Analysis of health examination results

[1844] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[1845] 4. Use of generative AI models

[1846] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[1847] 5. Providing health advice

[1848] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[1849] Nutritional management function

[1850] 6. User input of meal details

[1851] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[1852] 7. Sending meal details to the server

[1853] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[1854] 8. Calculating calorie intake and nutritional balance

[1855] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[1856] 9. Generate personalized meal plans

[1857] The server then generates a personalized meal plan based on the calculated data, which is optimized based on the user's health status and goals. For example, a user with a vitamin C deficiency may be recommended to increase their intake of certain fruits and vegetables.

[1858] Generate a training plan

[1859] 10. User-defined fitness goals

[1860] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[1861] 11. Generate exercise plans based on your goals and health data

[1862] The server generates an appropriate exercise plan based on the user's goals and health checkup data. The plan includes exercise content (e.g., aerobic exercise three times a week) that is appropriate for the user's abilities and goals.

[1863] 12. Providing exercise plans

[1864] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[1865] Mental health support function

[1866] 13. User input of stress and sleep data

[1867] Users input their stress levels and sleep status into a dedicated application.

[1868] 14. Sending stress and sleep data to a server

[1869] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[1870] 15. Generating mental health advice

[1871] The server generates mental health advice based on stress levels and sleep data, for example, recommending relaxation meditation or deep breathing techniques for users with high stress levels.

[1872] 16. Providing Advice

[1873] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[1874] Specific examples

[1875] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[1876] 1. User Actions

[1877] Upload the health check results to a dedicated application.

[1878] 2. Device Operation

[1879] The uploaded health check results are sent to the server.

[1880] 3. Server Processing

[1881] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[1882] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[1883] 4. Server Actions

[1884] The generated advice is saved in the user's profile and sent to the terminal.

[1885] 5. Terminal Operation

[1886] Display health advice to the user.

[1887] As described above, the system of the present invention provides personalized health advice based on the user's health data and supports a comprehensive health improvement plan.

[1888] The processing flow will be explained below.

[1889] Step 1:

[1890] The user uploads the health check results to a dedicated application on their mobile device.

[1891] Step 2:

[1892] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[1893] Step 3:

[1894] The terminal sends the adapted file to the server.

[1895] Step 4:

[1896] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[1897] Step 5:

[1898] The server inputs the extracted data into the generative AI model and begins analysis.

[1899] Step 6:

[1900] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[1901] Step 7:

[1902] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[1903] Step 8:

[1904] The terminal displays the health advice received from the server to the user.

[1905] Step 9:

[1906] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, cooking methods).

[1907] Step 10:

[1908] The terminal transmits the meal data entered by the user to the server.

[1909] Step 11:

[1910] The server stores the received dietary data and calculates the calorie intake and the balance of each nutrient.

[1911] Step 12:

[1912] The server uses the calculated data to generate a personalized meal plan that is optimized based on the user's health status and goals.

[1913] Step 13:

[1914] The server stores the generated meal plan in the user's profile and transmits it to the terminal.

[1915] Step 14:

[1916] The device displays the meal plan to the user and provides reminders for implementation.

[1917] Step 15:

[1918] Users set fitness goals and input them into the system through a terminal.

[1919] Step 16:

[1920] The server generates an appropriate exercise plan based on the user's set goals and health data.

[1921] Step 17:

[1922] The server saves the generated exercise plan in the user's profile and transmits it to the terminal.

[1923] Step 18:

[1924] The device displays the exercise plan to the user and provides functionality for tracking progress.

[1925] Step 19:

[1926] Users input their stress levels and sleep status into a dedicated application.

[1927] Step 20:

[1928] The terminal transmits the stress and sleep data input by the user to the server.

[1929] Step 21:

[1930] The server generates advice on stress management and sleep improvement based on the received data.

[1931] Step 22:

[1932] The server stores the generated advice in the user's profile and transmits it to the terminal.

[1933] Step 23:

[1934] The device displays stress management and sleep improvement advice to the user and provides a reminder function for implementation.

[1935] Example 1

[1936] 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."

[1937] Conventional health management systems are limited in their ability to analyze biometric data and provide individualized advice, making it difficult for users to achieve comprehensive health management. Furthermore, there is a lack of systems that can provide integrated support for diet, exercise, and even mental health. As a result, personalized advice and plans based on individual health conditions have not been adequately generated.

[1938] 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.

[1939] In this invention, the server includes means for uploading health checkup results, means for transmitting the uploaded health checkup results to the server, means for analyzing the received health checkup results, means for generating personalized health advice based on the analyzed health checkup results using a generative AI model, means for providing the generated personalized health advice to the user, means for the user to input daily meal contents, means for calculating calorie intake and nutrient balance based on the input meal contents, means for generating a personalized meal plan based on the calculated data, means for transmitting the input meal contents to the server, means for the user to set fitness goals, means for generating an appropriate exercise plan based on the set goals and health data, means for displaying the generated exercise plan to the user, means for the user to input stress levels and sleep states, means for transmitting the input stress and sleep data to the server, means for analyzing the received stress and sleep data, means for generating mental health advice based on the analysis results, and means for providing the generated mental health advice to the user, thereby enabling comprehensive and personalized health management.

[1940] "Health checkup results" are records of health status measurements taken at medical institutions, etc., and include blood test results and physical measurement data.

[1941] "Server" means a computer system that receives, analyzes, and stores data sent by users, and generates and provides necessary information and advice to users.

[1942] "Uploading" refers to the act of a user importing data such as health checkup results and dietary details into the system from their own device.

[1943] "Analysis" is the process by which the server performs statistical and computational processing on the data it receives, identifying outliers and analyzing trends.

[1944] "Generative AI model" means an artificial intelligence model used by the server to generate health advice and plans based on data, including machine learning algorithms.

[1945] "Personalized health advice" is information that suggests specific recommended actions or improvements based on each user's health condition.

[1946] "Meal contents" refers to detailed information such as the names of ingredients that the user regularly consumes, the amount of intake, and cooking methods.

[1947] "Calories intake" refers to the total amount of calories taken into the body by the user through food.

[1948] "Nutritional balance" refers to the balance of nutrients such as protein, lipids, carbohydrates, vitamins, and minerals contained in the user's diet.

[1949] A "meal plan" is a meal plan that is optimized based on the user's health status and goals.

[1950] "Fitness goals" are specific examples of goals related to physical health and exercise that a user sets, including weight loss and muscle gain.

[1951] An "exercise plan" is an exercise program designed based on a user's health data and fitness goals.

[1952] "Stress level" refers to the degree of mental and physical tension or strain felt by the user.

[1953] "Sleep state" is information relating to the quality and quantity of the user's sleep.

[1954] "Mental health advice" is specific advice for improving mental health that is suggested based on the user's stress level and sleep state.

[1955] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. The system integrates generative AI models, nutrition management functions, training plan generation functions, and mental health support functions.

[1956] Hardware and software used

[1957] 1. Server: Receives, analyzes, stores data, and generates advice.

[1958] 2. Terminal: Provides an interface for users to enter data and view advice.

[1959] 3. Generative AI model: A machine learning algorithm that generates personalized advice based on health checkup results and other user data.

[1960] Data processing and calculation

[1961] Uploading and analyzing health checkup results

[1962] Users upload their health checkup results using a dedicated application. The device then sends the file uploaded by the user to a server. This file includes blood test results and physical measurement data. The server performs error checks on the received data and analyzes it using an analytical algorithm. This analyzed data is then input into a generative AI model, which generates personalized health advice.

[1963] For example, if a user has a high ALT (liver function index) value, the generative AI model will generate health advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption."

[1964] Nutritional management function

[1965] Users input their daily dietary information into a dedicated application. This information includes the names of ingredients, the amount of each ingredient, and cooking methods. The device then sends this data to a server, which then calculates the balance of calories and nutrients (protein, fat, carbohydrates, vitamins, and minerals) and generates a personalized meal plan based on the results.

[1966] For example, a user who is deficient in vitamin C will be provided with a meal plan that encourages consumption of orange fruits and green vegetables.

[1967] Training plan generation function

[1968] Users use a dedicated app to set fitness goals, such as weight loss or muscle gain. The device then sends these goals to a server, which then generates a personalized exercise plan based on the user's goals and health data.

[1969] For example, a user looking to lose weight may be offered an exercise plan that includes aerobic exercise.

[1970] Mental health support function

[1971] Users use the app to input their stress levels and sleep patterns, and the device sends this data to a server that analyzes it and generates mental health advice.

[1972] For example, users with high stress levels may be encouraged to meditate or take deep breaths to relax.

[1973] Examples of specific examples and prompts

[1974] For example, if you want to upload your health checkup results and generate the necessary advice from them, you could input the following prompts into the generative AI model:

[1975] "Create dietary and lifestyle advice for users whose ALT levels exceed normal levels."

[1976] Based on this prompt, the generative AI model will provide the user with appropriate health advice. In this way, the system provides personalized advice based on the user's health data, supporting comprehensive health management.

[1977] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1978] Step 1:

[1979] The user logs in to the dedicated application and clicks the "Upload health checkup results" button. Next, they select the health checkup results file (PDF or CSV format) they want to upload and import it into the system. The input is the health checkup results file, and the output is a notification that the file has been uploaded. This operation imports the file into the system.

[1980] Step 2:

[1981] The terminal sends the health check result file uploaded by the user to the server. At this time, the terminal checks the format and size of the file and checks for transmission errors. The input is the uploaded file, and the output is the file sent to the server. Once the terminal sends the file to the server, it proceeds to the next processing step.

[1982] Step 3:

[1983] The server inputs the received health check result file into the analysis algorithm. The algorithm analyzes blood test results (e.g., ALT, AST, blood glucose levels) and physical measurement data (e.g., weight, height, BMI, etc.). The input is the health check result file, and the output is the analyzed data. The server analyzes the data and extracts abnormal values ​​and data requiring attention.

[1984] Step 4:

[1985] The server inputs the analysis results into a generative AI model, which generates personalized health advice based on the given data. The input is the analyzed data, and the output is personalized health advice. For example, specific advice such as "Since your ALT is high, increase your intake of green and yellow vegetables and limit your alcohol intake" may be generated.

[1986] Step 5:

[1987] The server saves the generated personalized health advice in the user's profile and sends it to the terminal. The input is personalized health advice, and the output is saving it in the user's profile and sending it to the terminal. The server prepares the advice to provide to the user.

[1988] Step 6:

[1989] The terminal receives the generated health advice and notifies the user. When the user logs in to the application, they can view the latest health advice. The input is the health advice sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the advice.

[1990] Step 7:

[1991] Users input their daily dietary information into a dedicated application. The dietary information includes the names of ingredients, the amount of food consumed, and cooking methods. The input is the daily dietary information, and the output is a notification that the dietary data has been entered. This operation imports the dietary data into the system.

[1992] Step 8:

[1993] The terminal transmits the input meal details to the server. The input is meal data, and the output is transmission to the server. The terminal provides the meal details data to the server.

[1994] Step 9:

[1995] The server calculates the calorie intake and balance of each nutrient (protein, fat, carbohydrates, vitamins, minerals) based on the input dietary data. The input is dietary data, and the output is the calculated calorie intake and nutritional balance. The server calculates and analyzes the data.

[1996] Step 10:

[1997] The server generates an individualized meal plan based on the calculated data and sends it to the device. The input is the calculation result, and the output is an individualized meal plan. For example, if a user is deficient in vitamin C, a plan recommending fruits and vegetables rich in vitamin C will be generated.

[1998] Step 11:

[1999] The terminal receives the generated individual meal plan and notifies the user. When the user logs in to the application, they can view the latest meal plan. The input is the meal plan sent from the server, and the output is the notification and viewing function for the user. The terminal is responsible for displaying the meal plan.

[2000] Step 12:

[2001] The user sets fitness goals using a dedicated application. Fitness goals can include weight loss or muscle gain. The input is the fitness goal, and the output is a notification that the goal has been entered. This operation imports the fitness goal into the system.

[2002] Step 13:

[2003] The terminal transmits the set fitness goal to the server. The input is the fitness goal and the output is the transmission to the server. The terminal provides the goal data to the server.

[2004] Step 14:

[2005] The server generates an appropriate exercise plan based on the user's fitness goals and health data (e.g., weight, height, and past exercise habits). The input is the fitness goals and health data, and the output is the exercise plan. The server analyzes the data and designs the exercise plan.

[2006] Step 15:

[2007] The server sends the generated exercise plan to the device and saves it in the user's profile. The input is the exercise plan, and the output is sending it to the device and saving it in the profile. The server is ready to provide the plan.

[2008] Step 16:

[2009] The device receives the generated exercise plan and notifies the user. When the user logs in to the application, they can check the latest exercise plan. The input is the exercise plan sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the plan.

[2010] Step 17:

[2011] The user uses the application to input their own stress level and sleep state. The input is the stress level and sleep state, and the output is a notification that the data has been input. This operation inputs the stress and sleep data into the system.

[2012] Step 18:

[2013] The terminal transmits the input stress and sleep data to the server. The input is stress and sleep data, and the output is transmission to the server. The terminal provides data to the server.

[2014] Step 19:

[2015] The server analyzes the received stress and sleep data and generates mental health advice. The input is stress and sleep data, and the output is mental health advice. For example, a user with a high stress level may be recommended to meditate or take deep breaths to relax.

[2016] Step 20:

[2017] The server generates mental health advice, stores it in the user's profile, and sends it to the device. The input is the mental health advice, and the output is sending it to the device and saving it in the profile. The server is ready to provide the advice.

[2018] Step 21:

[2019] The device receives the generated mental health advice and notifies the user. When the user logs in to the application, they can view the latest mental health advice. The input is the mental health advice sent from the server, and the output is the notification and viewing function for the user. The device is responsible for displaying the advice.

[2020] Through the above processing steps, the system provides personalized advice based on the user's health data and supports comprehensive health management.

[2021] (Application example 1)

[2022] 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."

[2023] Effective individual health management is extremely important in modern society, but existing systems have difficulty providing sufficient personalized health advice and reminders. Furthermore, the generation of nutritional management and training plans based on health checkup results is not automated, leaving users to manage these themselves. Furthermore, mental health support functions based on stress and sleep data are often not integrated. To solve these issues, a more comprehensive and automated health management system is needed.

[2024] 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.

[2025] In this invention, the server includes means for uploading health checkup results, means for analyzing the uploaded health checkup results, means for generating personalized health advice using a generative AI model based on the analyzed health checkup results, means for providing the generated personalized health advice to the user, and means for notifying the user of the generated advice and reminders. This allows the user to receive detailed health advice based on the health checkup results and accompanying reminders.

[2026] The system further includes a means for a user to input daily meal contents, a means for calculating calorie intake and nutritional balance based on the input meal contents, a means for generating an individual meal plan based on the calculated data, and a means for providing a reminder function based on advice.

[2027] The device further includes a means for allowing a user to set fitness goals, a means for generating an appropriate exercise plan based on the set goals and health data, a means for displaying the generated exercise plan to the user, and a means for providing a reminder function based on the exercise plan, thereby enabling the user to efficiently manage their overall health.

[2028] "Health checkup results" refer to various health indicators and numerical data obtained as a result of health checkups conducted at medical institutions or testing facilities.

[2029] "Individualized health advice" refers to health guidance and instructions that are optimized for each individual based on individual data such as the user's health checkup results and lifestyle.

[2030] "Uploading means" refers to the process or technology by which a user submits medical examination results in the form of a digital file to the system.

[2031] "Means of analysis" refers to the technology or algorithms that process the uploaded health check result data and extract the necessary information.

[2032] A "generative AI model" is a model that uses artificial intelligence technology to find patterns and relationships from input data and generate appropriate output.

[2033] A "reminder" is a notification function that notifies the user of a specific time or action.

[2034] The "nutritional management function" is a function that records and analyzes the user's diet and adjusts the nutritional balance.

[2035] The "training plan generation function" is a function that creates an exercise plan based on the user's fitness goals and health data.

[2036] The "mental health support function" is a function for supporting the user's psychological health and provides advice that is useful for stress management and improving sleep.

[2037] The "smart notification function" is a function that notifies users of health advice and reminders in real time.

[2038] This is a health management system that allows users to upload their health checkup results, analyzes the data, and provides personalized health advice and improvement plans. This system is implemented as a smartphone application and operates in conjunction with a backend running on a server.

[2039] Hardware and software used

[2040] Hardware: Smartphone

[2041] software:

[2042] Frontend: React Native (for cross-platform app development)

[2043] Backend: Node.js, Python (AI model)

[2044] Database: MongoDB

[2045] Cloud services: AWS (data processing and storage)

[2046] Processing Details

[2047] Uploading and analyzing health checkup results

[2048] Users upload their health checkup results in PDF or CSV format using their smartphones. The uploaded file is sent to a Node.js-based server through a front-end application using React Native. The server analyzes the received file and extracts the necessary health indicators.

[2049] Generative AI model generates advice

[2050] The analyzed data is input into a generative AI model, a Python-based AI model. This model generates personalized health advice based on the input data. For example, if the liver function score is high, specific advice such as "increase your intake of green and yellow vegetables and limit alcohol consumption" is generated.

[2051] Providing health advice

[2052] The generated advice is stored in MongoDB and linked to the user's profile. A front-end application periodically retrieves this data and notifies the user. A smart notification feature also sets reminders and helps the user take the suggested actions.

[2053] Nutrition management and training plan generation functions

[2054] Users enter their daily dietary habits and fitness goals into the application. This data is then sent to the server and analyzed. Based on the analysis results, calorie intake and nutritional balance are calculated and an individualized meal plan is generated. An exercise plan based on the user's fitness goals is also generated and provided to the user. Reminders are also set for these plans to help the user continue to manage their health.

[2055] Specific example explanation

[2056] For example, if a user uploads their medical checkup results and finds that their liver function indicator, ALT, is high, the following specific steps will be taken:

[2057] 1. The user uploads the health check result file.

[2058] 2. The server receives the file and analyzes it.

[2059] 3. Based on the analysis results, the generated AI model generates advice such as "increase your intake of green and yellow vegetables and limit your alcohol intake."

[2060] 4. The server saves the generated advice in the user's profile and the application notifies the user.

[2061] Prompt Sentence Examples

[2062] An example of a text prompt is:

[2063] "Generate personalized health advice based on the user's health check results. The following data indicates high liver function values.

[2064] Liver function: High

[2065] Blood sugar: normal

[2066] Any advice generated should include specific dietary restrictions or lifestyle changes."

[2067] In this way, the system of the present invention utilizes data obtained from health checkup results in a multifaceted manner to support comprehensive health management.

[2068] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2069] Step 1:

[2070] Users upload their health checkup results using a smartphone application.

[2071] In this example, the user opens the app, selects a PDF or CSV format health checkup result file, and presses the send button. The input health checkup result file is sent to the server via the application.

[2072] Step 2:

[2073] The terminal sends the uploaded health check result file to the server.

[2074] The device receives the file and sends a POST request to the specified API endpoint. The input is a diagnostic result file in PDF or CSV format, which is then sent to the server.

[2075] Step 3:

[2076] The server receives the file and checks for errors.

[2077] The server checks the format and content of the received file and performs an error check. After the error check, it temporarily saves it for analysis. The input is the diagnostic result file, and the output is an error report or a confirmation message to proceed with the analysis.

[2078] Step 4:

[2079] The server analyzes the health check results and extracts the necessary health indicators.

[2080] The server uses an analysis algorithm to analyze the files and extract numerical data such as blood test results and physical measurement data. The input is the diagnostic result file, and the output is health index data.

[2081] Step 5:

[2082] The server inputs the analyzed data into a generative AI model.

[2083] The server passes the extracted health index data to a generative AI model to generate personalized health advice. The input is the health index data, and the output is the health advice.

[2084] Step 6:

[2085] The server stores the generated health advice in a database.

[2086] The server stores the generated advice in a database linked to the user's profile. The input is the health advice and the output is a message confirming the data storage.

[2087] Step 7:

[2088] The server notifies the device of advice and reminders.

[2089] The server sends the saved advice to the device and notifies the user via instant messaging or notification. The input is health advice, and the output is notification to the user device.

[2090] Step 8:

[2091] Users enter their daily diet and fitness goals into the app.

[2092] Users input and submit their dietary information and fitness goals through the app. The input is their daily dietary information and fitness goals, and the output is data sent to the server via the application.

[2093] Step 9:

[2094] The server analyzes the entered data and generates personalized meal and exercise plans.

[2095] The server analyzes data on daily dietary habits and fitness goals, calculates calorie intake and nutritional balance, and generates appropriate meal and exercise plans. The input is daily dietary habits and fitness goals, and the output is an individual plan.

[2096] Step 10:

[2097] The device displays the generated plan to the user and sets reminders.

[2098] The terminal displays the individual plan received from the server to the user and sets reminders. The input is the generated plan, and the output is the plan displayed to the user and the set reminders.

[2099] 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.

[2100] This invention integrates a health management system that allows users to upload their health checkup results, analyzes the results, and provides personalized health advice and improvement plans, as well as an emotion engine that recognizes the user's emotions. The system includes a generative AI model, nutrition management functions, training plan generation functions, and mental health support functions.

[2101] Program processing details

[2102] 1. User uploads health checkup results

[2103] Users upload their health checkup results to the system through a dedicated application, which then imports the results into the system in a compatible file format (e.g., PDF or CSV).

[2104] 2. Sending health check results to the server

[2105] The device sends the uploaded health check results to the server, which then checks the received data and performs error checks.

[2106] 3. Analysis of health examination results

[2107] The server uses an analysis algorithm to analyze the received health checkup results, which include numerical data such as blood test results and physical measurements.

[2108] 4. Use of generative AI models

[2109] The server inputs the analyzed data into a generative AI model, which then generates personalized health advice based on this data. For example, if liver function scores are high, the model will recommend specific dietary restrictions and lifestyle improvements.

[2110] 5. Providing health advice

[2111] The server stores the generated personalized health advice in the user's profile and sends it to the device, which displays the received advice to the user.

[2112] Emotion engine integration

[2113] 6. User Emotion Recognition

[2114] The emotion engine has the ability to recognize emotions in real time from the user's facial expressions, tone of voice, etc. When the user uses the dedicated application, emotional data is collected through the built-in camera and microphone.

[2115] 7. Transmission and analysis of emotional data

[2116] The device transmits the captured emotion data to a server, which uses an emotion engine to analyze the data and store the recognized emotional state in the user's profile.

[2117] 8. Adjusting advice based on emotions

[2118] The server then adjusts the health advice generated by the generative AI model based on the user's emotional state. For example, a user experiencing high stress levels will be provided with advice on taking immediate action.

[2119] Nutritional management function

[2120] 9. User input of meal details

[2121] Users input their daily dietary information into a dedicated application, recording details of each meal (e.g., ingredient names, intake amounts, and cooking methods).

[2122] 10. Sending meal details to the server

[2123] The device sends the entered meal details to a server, which stores the received data and inputs it into an analysis algorithm.

[2124] 11. Calculating calorie intake and nutritional balance

[2125] The server calculates the balance of calories ingested and each nutrient (e.g., protein, fat, carbohydrates, vitamins, minerals) based on the entered dietary data.

[2126] 12. Generate personalized meal plans

[2127] The server then generates a personalized meal plan based on the calculated data. This plan is optimized based on the user's health status and goals. It also incorporates emotional data, recommending foods with a relaxing effect if the user is under high stress.

[2128] Generate a training plan

[2129] 13. User-defined fitness goals

[2130] Users set fitness goals and input them into the system through a terminal, such as weight loss or muscle gain.

[2131] 14. Generate exercise plans based on your goals and health data

[2132] The server generates an appropriate exercise plan based on the user's goals and health data. The plan is also tailored to take emotional data into account. For example, if the user feels tired, a plan including relaxing yoga and light stretching will be suggested.

[2133] 15. Providing exercise plans

[2134] The server stores the generated exercise plan in the user's profile and sends it to the device, which displays the exercise plan to the user and provides the ability to track progress.

[2135] Mental health support function

[2136] 16. User input of stress and sleep data

[2137] Users input their stress levels and sleep status into a dedicated application.

[2138] 17. Sending stress and sleep data to a server

[2139] The device sends the input data to the server, which stores the data and inputs it into an analysis algorithm.

[2140] 18. Generating mental health advice

[2141] The server generates mental health advice based on stress levels, sleep data, and emotional data. For example, a user experiencing high stress might be recommended meditation, deep breathing techniques, or listening to relaxing music.

[2142] 19. Providing Advice

[2143] The server stores the generated mental health advice in the user's profile and sends it to the device, which displays the advice to the user and also provides a reminder function.

[2144] Specific examples

[2145] For example, if a user uploads a medical checkup result and their ALT (a measure of liver function) is high:

[2146] 1. User Actions

[2147] Upload the health check results to a dedicated application.

[2148] 2. Device Operation

[2149] The uploaded health check results are sent to the server.

[2150] 3. Server Processing

[2151] Health checkup results are analyzed and personalized health advice is generated using a generative AI model.

[2152] Generate dietary advice: "Increase your intake of green and yellow vegetables and limit alcohol."

[2153] 4. User Emotion Recognition

[2154] The emotion engine detects stress from the user's facial expression.

[2155] 5. Server Actions

[2156] The generated advice reflects emotional data and also provides stress management techniques.

[2157] The advice is saved in the user's profile and sent to the device.

[2158] 6. Terminal Operation

[2159] Displaying health and stress management advice to the user.

[2160] As described above, the system of the present invention integrates a user's health data and emotional data to provide more personalized health advice and support a comprehensive health improvement plan.

[2161] The processing flow will be explained below.

[2162] Step 1:

[2163] The user uploads the health check results to a dedicated application on their mobile device.

[2164] Step 2:

[2165] The terminal receives the uploaded health check results and checks the compatibility of the file format (PDF or CSV).

[2166] Step 3:

[2167] The terminal sends the adapted file to the server.

[2168] Step 4:

[2169] The server parses the received medical examination results and extracts the necessary numerical data (e.g., ALT, blood pressure, etc.).

[2170] Step 5:

[2171] The server inputs the extracted data into the generative AI model and begins analysis.

[2172] Step 6:

[2173] The generative AI model generates personalized health advice based on the input data, for example, if the ALT level is high, it will recommend specific dietary restrictions and lifestyle changes.

[2174] Step 7:

[2175] The server stores the generated personalized health advice in the user's profile and transmits it to the terminal.

[2176] Step 8:

[2177] The terminal displays the health advice received from the server to the user.

[2178] Step 9:

[2179] The emotion engine analyzes ...

Claims

1. A means for uploading health checkup results; A means for analyzing the uploaded medical examination results; A means for generating personalized health advice using a generative AI model based on the analyzed health checkup results; means for providing the generated personalized health advice to the user; A system including:

2. A means for a user to input daily meal contents; A method for calculating calorie intake and nutritional balance based on the entered meal contents, a means for generating a personalized meal plan based on the calculated data; The system of claim 1 further comprising:

3. a means for a user to set fitness goals; A means for generating an appropriate exercise plan based on set goals and health data; means for displaying the generated exercise plan to the user; The system of claim 1 further comprising:

Images