System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting lifestyle information, diet information, and health care information of a user; means for analyzing and storing the input lifestyle information, diet information, and health care information in a database; means for generating an individually optimal diet plan and exercise plan using a generation model based on the stored information; means for presenting the generated plan to the user; means for collecting performance data of the user and generating a daily report; and means for performing relearning of the generation model based on the collected performance data and adjusting the plan.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] While health management is becoming increasingly important in modern times, existing health management methods rely on generalized methods and are often unable to adapt to individual physiques, constitutions, and lifestyles. As a result, self-directed diets and health management methods often fail to produce results, leading users to lose motivation. Furthermore, conventional tools have difficulty in consistently collecting and analyzing data, making it difficult to provide individually optimized recommendations. Given this background, the objective of this invention is to provide a system that efficiently manages health optimally for each individual, enabling users to sustainably maintain and improve their health. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: A means for inputting a user's lifestyle information, dietary information, and healthcare information is provided. Next, a means for analyzing the input lifestyle information, dietary information, and healthcare information and saving it in a database is provided. A means for generating an individually optimized meal plan and exercise plan using a generative model based on the saved information is provided. A means for presenting the generated plan to the user and collecting the results of the user's implementation is provided. A means for generating a daily report based on the collected implementation data is provided, and further a means for re-training the generative model using the implementation data and adjusting the plan as appropriate is provided. This enables health management that is optimized for each individual and supports sustainable health maintenance and improvement.

[0006] "User's lifestyle information" refers to data on the user's behavioral patterns and habits in daily life, particularly on how they work on weekdays, how they spend their days off, and how often they exercise.

[0007] "Dietary information" refers to information about a user's food preferences and eating habits, specifically, their favorite and least favorite foods.

[0008] "Healthcare information" refers to information about a user's health status and physiological data, particularly heart rate, sleep data, and daily calorie intake.

[0009] A "generative model" is an artificial intelligence algorithm or machine learning model that generates an optimal individualized meal plan and exercise plan based on input lifestyle, dietary, and healthcare information.

[0010] An "optimal meal plan" is a combination of foods and nutrients that should be consumed at each meal each day, based on the user's health status and goals.

[0011] An "exercise plan" is a plan that indicates the type of daily exercise, frequency, time, etc., suggested based on the user's lifestyle and health data.

[0012] The "daily report" is a report that records the user's daily activities, calorie intake, amount of exercise, etc., and includes the user's level of achievement, any nutrient deficiencies, and recommended next steps.

[0013] "Retraining" is a machine learning process that updates the generative model based on collected implementation data to make more accurate suggestions. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is configured as follows, and its specific operation is shown below.

[0036] System Configuration

[0037] 1. Server

[0038] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[0039] A generative AI model is used to analyze this information and generate personalized meal and exercise plans.

[0040] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[0041] 2. Terminal

[0042] The terminal provides an interface for users to input lifestyle, dietary, and health care information.

[0043] Displays the generated plans and daily reports received from the server.

[0044] The user's implementation data is sent to the server.

[0045] 3. Users

[0046] The user inputs his / her lifestyle information, dietary information, and health care information into the terminal.

[0047] Follow the suggested diet and exercise plan and enter the results into the device.

[0048] Check your own health management achievements and suggestions for improvement through daily reports.

[0049] Program processing

[0050] Entering information

[0051] The user launches the health management app and inputs information about their lifestyle, diet, and health care. For example, they input data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours.

[0052] The device collects this information and sends it to the server in JSON format.

[0053] Data analysis and storage

[0054] The server parses the data it receives and stores the information for each field in a database, adding new data and checking it against existing data for missing information or inconsistencies.

[0055] Plan generation using generative AI models

[0056] The server runs a generative AI model based on the stored data. The generative AI model takes the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[0057] Plan presentation

[0058] The server sends the generated plan to the device, which then visualizes the plan and presents it to the user. For example, the screen displays "Today's Meal Plan" and "Today's Exercise Plan."

[0059] Daily report creation

[0060] The user practices diet and exercise and inputs the results into the application. For example, they input data such as "I had yogurt for breakfast today" or "I walked for 30 minutes in the evening."

[0061] The device collects this performance data and sends it to a server. The server analyzes the performance data and generates a daily report. The daily report includes achievement levels, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[0062] Relearn

[0063] If the user is unable to complete the proposed plan, that data is also collected, for example, "I had difficulty completing 30 minutes of walking."

[0064] The server retrains the generative AI model based on difficult-to-achieve data. The generative AI model generates an optimal plan under the new conditions and sends it back to the device. For example, it suggests "instead of walking at night, we suggest light indoor exercise."

[0065] Specific examples

[0066] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on his days off, but doesn't exercise much every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night.

[0067] The server uses an AI model to generate a plan like the one below and displays it on the device.

[0068] Meal Plan:

[0069] Breakfast: Yogurt and fruit

[0070] Lunch: Chicken breast salad

[0071] Dinner: Vegetable soup and whole wheat bread

[0072] Exercise plan:

[0073] Every morning: 15 minutes of stretching

[0074] Evening: 30-minute walk

[0075] The next morning, the terminal presents the user with the following daily health management report:

[0076] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[0077] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] The user launches the health management app and inputs lifestyle, diet, and health information, such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep."

[0081] Step 2:

[0082] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[0083] Step 3:

[0084] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[0085] Step 4:

[0086] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[0087] Step 5:

[0088] The server runs a generative AI model based on the stored information. Specifically, it inputs lifestyle, dietary, and health information into the model to generate optimal meal and exercise plans.

[0089] Step 6:

[0090] The server sends the generated plan to the terminal in JSON format.

[0091] Step 7:

[0092] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," and "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking."

[0093] Step 8:

[0094] The user follows the plan and enters the results into the app every day, for example, "I ate yogurt for breakfast" or "I walked for 30 minutes in the evening."

[0095] Step 9:

[0096] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[0097] Step 10:

[0098] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[0099] Step 11:

[0100] The server transmits the generated daily report to the terminal.

[0101] Step 12:

[0102] The terminal displays the daily report on the user interface, allowing the user to check their own health management achievements and suggestions for next actions.

[0103] Step 13:

[0104] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[0105] Step 14:

[0106] The server retrains the generative AI model based on difficult-to-achieve data, and after retraining, generates an optimal plan under new conditions.

[0107] Step 15:

[0108] The server sends the regenerated plan to the terminal.

[0109] Step 16:

[0110] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[0111] Example 1

[0112] 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."

[0113] In modern society, many people lead busy lives and often find it difficult to find enough time for health management. As a result, the risk of lifestyle-related diseases increases, making it difficult to maintain good health. Existing health management systems have issues such as difficulty in providing optimal diet and exercise plans tailored to each user's individual needs and inability to flexibly adapt to changes in the user's lifestyle. Furthermore, the mechanisms for evaluating the effectiveness of the generated plans and relearning them are inadequate, making it difficult to expect long-term health management effects.

[0114] 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.

[0115] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing the information in a database, means for generating an individually optimized meal plan and exercise plan using a generative AI model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for retraining the generative AI model based on the collected performance data and adjusting the plan, means for communicating the user's input information and performance data in JSON format, means for visually displaying the generated plan and daily report, means for the server to receive and parse the JSON format data and store it in a database, means for the generative model to be trained using TensorFlow or PyTorch, and means for the retrained generative model to generate and retransmit an optimal plan under new conditions. This not only enables the provision of an optimal health management plan tailored to the user's individual needs, but also enables the user to maintain and improve their health over the long term by evaluating and relearning the plan's effectiveness.

[0116] "Lifestyle information" refers to behavioral patterns and habits related to the user's daily life, specifically information such as how they work on weekdays, how they spend their holidays, and how often they exercise.

[0117] "Dietary information" refers to information including the user's daily food and drink preferences, disliked foods, allergy information, etc.

[0118] "Healthcare information" refers to specific data that indicates the user's health status, including health indicators such as heart rate, sleep time, and weight.

[0119] A "generative AI model" is an algorithm trained using machine learning that generates an optimal plan for each individual user based on their input information.

[0120] "JSON format" refers to JavaScript Object Notation (JSON), a format that represents data in a lightweight, structured way and is used for text-based data exchange.

[0121] A "daily report" is a document that reports on a day's health management activities and includes achievement levels, nutrient deficiencies, and recommended actions.

[0122] "Database" refers to a system for efficiently storing, managing, and accessing information, and refers to a place where a user's lifestyle information, dietary information, and healthcare information are stored.

[0123] "Parsing" refers to the process of interpreting and structurally analyzing received data.

[0124] "TensorFlow" is an open-source machine learning framework and software tool used to train neural networks.

[0125] "PyTorch" is an open-source library that makes it easy to train and run machine learning models, and refers to a software tool used to train neural networks, similar to TensorFlow.

[0126] "Server" refers to the computer system that receives data sent by users, processes and stores it, and runs the generative AI model.

[0127] "Terminal" refers to a device that allows users to input information and view generated plans and daily reports, such as a smartphone or tablet.

[0128] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is mainly composed of a server, a terminal, and a user, and its specific operation is as follows.

[0129] System Configuration

[0130] 1. Server

[0131] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[0132] A generative AI model is used to analyze the information received and generate a personalized meal and exercise plan.

[0133] User performance data is collected, a daily report is created based on this data, and the generative AI model is then retrained.

[0134] The servers are installed with machine learning frameworks such as TensorFlow and PyTorch, which are used to train and retrain generative AI models.

[0135] 2. Terminal

[0136] The terminal provides an interface for users to input lifestyle information, dietary information, and health care information through the application.

[0137] Visually display the generated plans and daily reports received from the server.

[0138] The data performed by the user is sent to the server.

[0139] 3. Users

[0140] Users use a dedicated health management app to input their lifestyle, dietary, and health care information into the device.

[0141] Follow the suggested meal and exercise plan and re-enter your results into the app.

[0142] Check your own health management achievements and suggestions for improvement through daily reports.

[0143] Input and analysis of information

[0144] The user launches the health management app and enters information about their individual lifestyle habits (e.g., weekday working habits and exercise frequency), dietary information (e.g., favorite foods, disliked foods), and health information (e.g., heart rate, sleep duration). After input, the device converts this information into JSON format and sends it to the server.

[0145] The server parses the received JSON data and stores it in a database. The newly added information is checked against existing data to check for consistency and gaps, providing reliable data to feed into the generative AI model.

[0146] Plan generation using generative AI models

[0147] The data stored on the server is input into a generative AI model and analyzed using specific algorithms (using TensorFlow or PyTorch). This model generates optimal meal and exercise plans based on each user's data. For example, "For a user who works at a desk, we recommend yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner."

[0148] Presenting a plan and collecting implementation data

[0149] The generated plan is sent from the server to the device, which then visually displays the plan. The user follows the plan, practices diet and exercise, and re-enters the results into the app. The device then sends this data back to the server in JSON format.

[0150] Daily report creation and generation AI model retraining

[0151] Based on the user's activity data, the server generates a daily report that includes the user's achievements, nutrient deficiencies, and recommended actions for the next day. For example, specific feedback is provided, such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet."

[0152] In addition, data on plans that could not be completed is collected, and the generative AI model is retrained based on this data. This retraining process generates a new, more realistic and feasible plan and sends it back to the device. For example, adjustments may be made, such as suggesting light indoor exercise instead of an evening walk.

[0153] Prompt Sentence Examples

[0154] "What's the best meal plan for someone who works a desk job during the week?"

[0155] "Please suggest a recommended exercise plan for someone with a heart rate of 70."

[0156] This allows users to continuously manage their health and obtain the health plan that is best suited to them through the system.

[0157] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0158] Step 1:

[0159] Entering information

[0160] The user launches the health management app and inputs lifestyle, diet, and health information. Specifically, the user enters "weekday work habits" (e.g., desk work), "weekend habits" (e.g., jogging), and "exercise frequency" (e.g., three times a week) into the interface. The input information is converted to JSON format, and the input amount is sent to the server in JSON format for subsequent processing.

[0161] Step 2:

[0162] Data transmission and storage

[0163] The device sends the lifestyle, diet, and health information entered to the server in JSON format. The server receives this information, parses the JSON data, analyzes the details of each item, and stores it in a database. Specifically, information such as how you work on weekdays, how you spend your days off, and how often you exercise is stored in the database.

[0164] Step 3:

[0165] Data analysis

[0166] The server performs an analysis based on the information stored in the database. This analysis includes checking the user's lifestyle information, consistency, and missing data. Each data item is collated to identify missing information or inconsistencies. The analysis results are used as input data for the generative AI model.

[0167] Step 4:

[0168] Plan generation using generative AI models

[0169] The server runs a generative AI model (trained using TensorFlow or PyTorch) based on the analyzed data. For example, if a user works at a desk, their favorite food is salad, and their heart rate is 70, the generative AI model will take these data as input and generate an optimal meal plan and exercise plan (e.g., yogurt and fruit for breakfast, vegetable soup for dinner). The output is the generated plan.

[0170] Step 5:

[0171] Presenting the plan

[0172] The server converts the generated plan back into JSON format and sends it to the device. The device visually displays the received generated plan. Specifically, the app screen displays "Today's meal plan" and "Today's exercise plan." For example, items such as "Yogurt and fruit for breakfast," "Chicken breast salad for lunch," and "Vegetable soup for dinner" are displayed.

[0173] Step 6:

[0174] Entering implementation data

[0175] The user puts the presented plan into practice and enters the results into the app. Specifically, they enter implementation data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects the implementation data entered by the user and sends it back to the server in JSON format.

[0176] Step 7:

[0177] Creating daily reports

[0178] The server receives and analyzes the user's exercise data. Based on this analysis, it generates a daily report on the user's exercise results for the day. The daily report includes the user's achievement level, any nutrient deficiencies, and recommended health behaviors for the next day. For example, the report may include specific feedback such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat foods rich in iron."

[0179] Step 8:

[0180] Retraining generative AI models

[0181] The server also collects data if the user is unable to complete the plan. For example, data such as "it was difficult to walk for 30 minutes" is input. This data is used to retrain the generative AI model. The generative AI model is retrained under new conditions and generates the optimal plan again. Specifically, a new suggestion such as "instead of walking in the evening, we suggest light indoor exercise" is generated and sent to the device.

[0182] (Application example 1)

[0183] 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."

[0184] While existing health management systems provide individually optimized meal and exercise plans, few of them offer integrated health content (e.g., blog posts, videos, recipes, etc.). Furthermore, they lacked systems that provide feedback on the effectiveness of the plans based on user data and enable continuous improvement by retraining generative models. This limited the sustainability and effectiveness of users' health management.

[0185] 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.

[0186] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan and exercise plan using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's implementation data and generating a daily report, means for relearning the generative model based on the collected implementation data and adjusting the plan, means for delivering the generated plan and related health-related content to the user, and means for collecting implementation data based on the generated plan and providing feedback. This allows the user to receive not only an individually optimized health management plan but also useful health information related to it, enabling sustainable and effective health management.

[0187] "Lifestyle information" refers to information about the user's behavioral patterns and habits in their daily lives, such as how they work, when they wake up and go to bed, and how often they exercise.

[0188] "Dietary information" refers to information about the user's eating habits, such as favorite foods, disliked foods, and the contents of daily meals.

[0189] "Healthcare information" refers to information about the user's health condition, such as data about heart rate, weight, height, and sleep duration.

[0190] A "database" is a storage device that stores collected lifestyle, dietary, and healthcare information and makes it accessible as needed.

[0191] A "generative model" is a model that uses AI technology to generate optimal meal and exercise plans based on a user's lifestyle, dietary, and healthcare information.

[0192] A "meal plan" is a plan that suggests meal plans suitable for the user based on a generative model.

[0193] An "exercise plan" is a plan that suggests exercise content suitable for the user based on a generative model.

[0194] A "daily report" is a report that includes an evaluation of the activities carried out that day and suggestions for improvement based on the user's implementation data.

[0195] "Retraining" refers to updating a generative model to improve its accuracy based on newly collected data.

[0196] "Related health content" is additional information to help users manage their health, such as health blog posts, videos, recipes, etc.

[0197] "Feedback" refers to the process of providing evaluations and advice based on the data the user has put into practice.

[0198] This invention relates to a system that utilizes a generative AI model based on a user's lifestyle, diet, and health information to propose optimal health management. The system has the function of allowing users to input information about their lifestyle and health status, and based on that information, provides personalized optimal meal and exercise plans. It also delivers related health content and receives feedback on implementation data, allowing the generative model to retrain and improve the quality of the plans.

[0199] System Configuration

[0200] The server receives lifestyle, dietary, and health information sent by the user and stores it in a database. It analyzes the stored information and uses a generative AI model to generate an optimal meal plan and exercise plan for each individual. It also collects the user's exercise data and creates a daily report. It then retrains the generative model based on the exercise data.

[0201] The terminal provides an interface for users to input lifestyle, diet, and health information, displays the generated plan and daily report received from the server, and transmits the user's implementation data to the server.

[0202] Users enter their lifestyle, dietary, and health information into the device, follow the suggested meal and exercise plans, and then enter the results into the device to check their health management progress and improvement suggestions through daily reports.

[0203] Detailed explanation of operation

[0204] The server is built using Python and provides a REST API using frameworks such as Django or Flask, data is processed in JSON format, databases are AWS DynamoDB or Firebase Firestore, and generative AI models are built using AI frameworks such as TensorFlow and PyTorch.

[0205] As a specific example, the following scenario can be considered.

[0206] The user opens the smartphone app "My Health Guide" and enters information about their lifestyle, diet, and health care. For example, they might enter data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They might also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. This information is sent to the server in JSON format.

[0207] The server analyzes the received data and stores it in a database. It then runs a generative AI model to generate optimal meal and exercise plans for each user. The generated plan is again sent to the smartphone in JSON format and displayed on the app's UI. For example, "Today's meal plan" might show "yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner." Additionally, "Today's exercise plan" might suggest "15 minutes of stretching every morning and 30 minutes of walking in the evening."

[0208] When a user practices diet and exercise and enters the results into the application, the device collects this data and sends it to the server. The server analyzes the data and generates a daily report. The daily report includes the level of achievement, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[0209] Furthermore, if the user is unable to complete the proposed plan, that data is also collected, and the server retrains the generative AI model based on the difficult-to-achieve data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device. For example, it may suggest something like, "Instead of walking in the evening, we suggest light indoor exercise."

[0210] Example prompt sentence:

[0211] You're a busy desk worker with a lifestyle where you only exercise three times a week. Your favorite food is salad and you hate fried food. Your heart rate is 70 and you get seven hours of sleep each night. Use this information to generate a meal and exercise plan that's perfect for you.

[0212] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0213] Step 1:

[0214] The user launches the smartphone app and inputs lifestyle, diet, and health information. Specifically, the user enters information such as their weekday work style (desk work), weekend habits (jogging), how often they exercise three times a week, their favorite food (salad), their least favorite food (fried food), their heart rate (70), and the amount of sleep they get (7 hours). This information is collected through the device's interface. Input formats include text fields and selection lists.

[0215] input:

[0216] Lifestyle information

[0217] Meal Information

[0218] Healthcare Information

[0219] output:

[0220] User information data in JSON format

[0221] Step 2:

[0222] The device converts the collected lifestyle, dietary, and health information into JSON format and sends it to the server. The HTTPS protocol is used for communication, ensuring secure data transfer. The server receives the request, analyzes the data, and stores it in a database. Specifically, a web framework such as Django or Flask is used.

[0223] input:

[0224] User information data in JSON format

[0225] output:

[0226] User information stored in a server-side database

[0227] Step 3:

[0228] The server runs a generative AI model based on user information stored in a database. The generative AI model receives the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. It also generates an exercise plan that includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[0229] input:

[0230] User information stored in a database

[0231] output:

[0232] Personalized meal and exercise plans

[0233] Step 4:

[0234] The generated meal and exercise plans are sent to the device in JSON format. The device visualizes the received plans and presents them to the user. Specifically, the app's UI displays "Today's meal plan" as "Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread." Additionally, "Today's exercise plan" displays "Every morning: 15 minutes of stretching, Evening: 30 minutes of walking."

[0235] input:

[0236] Meal and exercise plans in JSON format

[0237] output:

[0238] Plans displayed in the app UI

[0239] Step 5:

[0240] The user puts the suggested diet and exercise into practice and enters the results into the application. For example, they enter data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects this data and sends it to the server in JSON format.

[0241] input:

[0242] Dietary and exercise data

[0243] output:

[0244] JSON format implementation data

[0245] Step 6:

[0246] The server analyzes the received data and generates a daily report. The daily report includes the user's achievement level, nutrient deficiencies, and recommended actions. For example, it may include, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet." The generated report is sent to the device in JSON format, and the device displays it on the app's UI.

[0247] input:

[0248] JSON format implementation data

[0249] output:

[0250] JSON format health management daily report

[0251] Step 7:

[0252] If the user is unable to complete the proposed plan, that data is also collected in JSON format and sent to the server. The server then retrains the generative AI model based on the difficult-to-complete data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device in JSON format. For example, the system may suggest something like, "Instead of walking at night, we suggest light indoor exercise."

[0253] input:

[0254] Hard to achieve data in JSON format

[0255] output:

[0256] New plans from retrained generative AI models

[0257] 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.

[0258] The present invention relates to a system that proposes optimal health management based on a user's emotions by combining an emotion engine with the user's lifestyle, dietary information, and healthcare information. The system is configured as follows, and its specific operation is shown below.

[0259] System Configuration

[0260] 1. Server

[0261] The server receives lifestyle information, dietary information, health care information, and emotion data sent by the user and stores them in a database.

[0262] Generative AI models are used to analyze this information and emotional data to generate personalized meal plans, exercise plans, and activities to improve mental health.

[0263] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[0264] 2. Terminal

[0265] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data.

[0266] Display generated plans and daily reports received from the server, as well as mental health improvement activities.

[0267] The user's implementation data is sent to the server.

[0268] 3. Users

[0269] Users input their lifestyle, diet, and health information, as well as emotional data, into the device, which is collected from facial expressions, voice, and text input.

[0270] Follow the suggested meal plans, exercise plans, and mental health activities and enter the results into your device.

[0271] Check your own health management achievements and suggestions for improvement through daily reports.

[0272] Program processing

[0273] Entering information

[0274] A user launches a health management app and inputs lifestyle, diet, health, and emotional data. For example, the user enters data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. The user also provides information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. Emotional data is collected based on the user's facial expression analysis, tone of voice, and text input.

[0275] The device collects this information and converts it into JSON format, preparing the data for later transmission.

[0276] Data analysis and storage

[0277] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[0278] Plan generation using generative AI models

[0279] The server runs a generative AI model based on the stored data and emotional data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotional data as input, and generates individually optimized meal plans, exercise plans, and activities to improve mental health. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening. Furthermore, based on the emotional data, it also suggests meditation for relaxation and exercises to relieve stress.

[0280] Plan presentation

[0281] The server sends the generated plan to the terminal in JSON format.

[0282] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," while "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." Furthermore, "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[0283] Daily report creation

[0284] The user performs dietary, exercise, and relaxation activities and enters the results into the application. For example, they can enter "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[0285] The device collects these implementation data and sends them to the server in JSON format.

[0286] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[0287] Relearn

[0288] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[0289] The server retrains the generative AI model based on difficult-to-achieve data and emotional data. After retraining, it generates an optimal plan under the new conditions.

[0290] The server sends the regenerated plan to the terminal.

[0291] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[0292] Specific examples

[0293] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[0294] The server uses an AI model to generate a plan like the one below and displays it on the device.

[0295] Meal Plan:

[0296] Breakfast: Yogurt and fruit

[0297] Lunch: Chicken breast salad

[0298] Dinner: Vegetable soup and whole wheat bread

[0299] Exercise plan:

[0300] Every morning: 15 minutes of stretching

[0301] Evening: 30-minute walk

[0302] Mental Health Improvement Plan:

[0303] Meditation: 10 minutes

[0304] The next morning, the terminal presents the user with the following daily health management report:

[0305] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[0306] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[0307] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[0308] The processing flow will be explained below.

[0309] Step 1:

[0310] The user launches the health management app and inputs lifestyle information, dietary information, health information, and emotional data. Specifically, the user inputs data such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep." Emotional data is collected based on facial expression analysis, tone of voice, and text input.

[0311] Step 2:

[0312] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[0313] Step 3:

[0314] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[0315] Step 4:

[0316] The server analyzes the received data, extracts and validates the necessary fields, and stores them in the database. At the same time, emotion data is also stored in the database.

[0317] Step 5:

[0318] The server runs a generative AI model based on the stored information and emotional data. The generative AI model receives lifestyle, diet, health, and emotional data as inputs and generates an individually optimized meal plan, exercise plan, and activities to improve mental health.

[0319] Step 6:

[0320] The server sends the generated plan to the terminal in JSON format.

[0321] Step 7:

[0322] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread." "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[0323] Step 8:

[0324] Users follow the plan and enter their results into the app every day, for example, "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[0325] Step 9:

[0326] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[0327] Step 10:

[0328] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[0329] Step 11:

[0330] The server transmits the generated daily report to the terminal.

[0331] Step 12:

[0332] The terminal displays the daily report on the user interface, and the user can check the progress of their health management and suggestions for improvement.

[0333] Step 13:

[0334] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[0335] Step 14:

[0336] The server retrains the generative AI model based on difficult-to-achieve data and emotional data, and then generates an optimal plan under the new conditions.

[0337] Step 15:

[0338] The server sends the regenerated plan to the terminal.

[0339] Step 16:

[0340] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[0341] Specific examples

[0342] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[0343] The server uses an AI model to generate a plan like the one below and displays it on the device.

[0344] Meal Plan:

[0345] Breakfast: Yogurt and fruit

[0346] Lunch: Chicken breast salad

[0347] Dinner: Vegetable soup and whole wheat bread

[0348] Exercise plan:

[0349] Every morning: 15 minutes of stretching

[0350] Evening: 30-minute walk

[0351] Mental Health Improvement Plan:

[0352] Meditation: 10 minutes

[0353] The next morning, the terminal presents the user with the following daily health management report:

[0354] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[0355] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[0356] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[0357] Example 2

[0358] 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."

[0359] Conventional health management systems generally propose plans based on a user's lifestyle, diet, and healthcare information, but do not take into account factors such as emotional fluctuations and mental stress. Furthermore, these systems do not adequately analyze individual data or retrain models, making it difficult to provide users with optimal health management plans.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0361] In this invention, the server includes means for inputting lifestyle information, dietary information, and health care information of a user, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for relearning the generative model based on the collected performance data and adjusting the plan, means for collecting and analyzing emotional data, and means for adjusting the generated plan based on the emotional data, thereby enabling comprehensive health management including the user's emotional fluctuations.

[0362] "Lifestyle information" refers to information about the user's daily life, including how they work on weekdays, how they spend their holidays, how often they exercise, and so on.

[0363] "Dietary information" refers to information about the user's daily diet, including favorite foods, disliked foods, and frequency of intake.

[0364] "Healthcare information" refers to information about the user's health condition, including biometric data such as heart rate, sleep time, and blood pressure, as well as self-assessment of health condition.

[0365] "Emotional data" refers to information about a user's emotional state, including data obtained from facial expression analysis, tone of voice, text input, and the like.

[0366] A "generative model" refers to an algorithm or AI model that analyzes input data and generates the optimal plan.

[0367] "Meal Plan" means the specific dietary recommendations made to maintain and improve the User's health.

[0368] An "exercise plan" refers to specific exercise content proposed to maintain and improve the user's health.

[0369] "Mental health activities" refers to relaxation and stress relief activities suggested to improve the user's mental health.

[0370] "Implementation data" includes data showing the results of the diet, exercise, and activities that the user actually undertook.

[0371] A "daily report" is a report that compiles the results of actions taken by a user and shows the level of achievement and areas for improvement.

[0372] "Relearning" refers to the process of retraining the generative model based on collected implementation and emotion data to generate more accurate plans.

[0373] This invention is a system that collects lifestyle information, dietary information, health care information, and emotional data from users, and provides individually optimized health management plans based on the collected data. The main components of this system include a server, a terminal, and a user.

[0374] server

[0375] The server receives lifestyle, diet, health, and emotional data sent by users and stores it in a database. The server analyzes this information using a generative model (e.g., OpenAI's GPT-3) to generate optimal meal plans, exercise plans, and activities for improving mental health. It also creates daily reports based on the user's implementation data and retrains the generative model to continuously improve the plans.

[0376] Terminal

[0377] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data. The terminal displays the generated plan and daily report received from the server, collects the user's implementation data, and sends it to the server.

[0378] User

[0379] Users input their lifestyle, dietary, and health information, as well as emotional data, into the device. Emotional data is collected from facial expression analysis, tone of voice, and text input. Users also execute the proposed meal plan, exercise plan, and mental health improvement activities and input the results into the device, contributing to the system's plan generation and re-learning.

[0380] Specific examples

[0381] For example, suppose a user works at a desk on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but do not exercise often on a daily basis. Their favorite food is salad, and they dislike fried food. Their heart rate is 70, and they get 7 hours of sleep every night. Emotional data collected recently indicates that they tend to feel stressed.

[0382] The server runs a generative AI model based on this information and generates a plan like the one below.

[0383] Meal Plan:

[0384] Breakfast: Yogurt and fruit

[0385] Lunch: Chicken breast salad

[0386] Dinner: Vegetable soup and whole wheat bread

[0387] Exercise plan:

[0388] Every morning: 15 minutes of stretching

[0389] Evening: 30-minute walk

[0390] Mental Health Improvement Plan:

[0391] Meditation: 10 minutes

[0392] The next morning, the terminal presents the user with the following daily health management report:

[0393] "You exercised as planned today, but your iron intake is low. Eat more iron-rich foods tomorrow."

[0394] "I only meditated for five minutes, but I think it will be effective if I continue. Next time, I'll aim for 10 minutes."

[0395] Prompt Sentence Examples

[0396] "I currently have a desk job during the weekdays, waking up at 7am every day and working from 8am until 5pm. I go jogging on my days off. I've been feeling stressed a lot lately. Could you please suggest the best meal plan, exercise plan, and activities to improve my mental health?"

[0397] This system enables users to manage their health in an individually optimized way, enabling them to maintain and improve their health continuously. It also analyzes users' emotional data in real time and provides appropriate healthcare suggestions based on their emotional fluctuations, enabling them to live a balanced life both physically and mentally.

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1:

[0400] The user starts the health management app and inputs lifestyle information, dietary information, health information, and emotional data. The personal information is input in the following format. For example,

[0401] Lifestyle information: "Desk work on weekdays, jog on weekends, exercise three times a week"

[0402] Dietary information: "My favorite food is salad, and my least favorite food is fried food."

[0403] Health information: "Heart rate is 70, sleep time is 7 hours"

[0404] Emotional data: "I feel stressed easily these days"

[0405] The input information is sent to the terminal. The terminal converts this information into JSON format and prepares it for sending to the server. The input to the server includes the user data in JSON format.

[0406] Step 2:

[0407] The device converts the lifestyle, diet, health, and emotion data entered by the user into JSON format. The converted data is sent to the server. Specifically, the device organizes the data collected from the user interface and packages it as a JSON string. The output includes the user data in JSON format.

[0408] Step 3:

[0409] The server parses the JSON formatted user data received from the device and extracts the required fields. This parsing includes checking the data for consistency, eliminating duplicate data, etc. The input contains the JSON formatted user data, and the output is the extracted user data that is stored in the database.

[0410] Step 4:

[0411] The server runs a generative AI model (e.g., OpenAI GPT-3) based on the stored user data and emotion data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotion data as input, and generates optimal meal plans, exercise plans, and activities to improve mental health. Specifically, the model provides input data, performs calculations, and obtains plan data as output. The input includes the user's integrated data, and the output is plan data in JSON format.

[0412] Step 5:

[0413] The server sends the generated plan data to the terminal in JSON format. Specifically, it converts the plan data obtained by the generative AI model into JSON format and performs communication processing to send it to the terminal. The output includes the plan data in JSON format.

[0414] Step 6:

[0415] The device displays the received plan on the user interface. Specifically, it parses the plan data in JSON format and renders the UI to display it in a user-friendly format. The displayed information includes "Today's meal plan: Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread" and "Today's exercise plan: 15 minutes of stretching every morning, 30 minutes of walking in the evening." The output is displayed on the user interface.

[0416] Step 7:

[0417] The user puts the proposed meal plan, exercise plan, and activities to improve mental health into practice and enters the results into the application. For example, they might enter "I ate yogurt for breakfast," "I walked for 30 minutes in the evening," or "I meditated for 10 minutes." The entered information is sent to the device, which then converts it back into JSON format and sends it to the server. The input contains the user's activity data, and the output is JSON-formatted activity data.

[0418] Step 8:

[0419] The server analyzes the received behavior data and generates a daily report. This analysis includes validity checks on the behavior data and extraction of missing elements (e.g., nutrients, exercise). The daily report includes achievement, missing nutrients, and recommended actions. The input includes the behavior data in JSON format, and the output is the generated daily report.

[0420] Step 9:

[0421] The device displays the generated daily report on the user interface. Specifically, it analyzes the JSON format daily report data and processes it to display it on the user interface. For example, it displays a message such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Eat an iron-rich diet tomorrow." The output is the daily report displayed on the user interface.

[0422] Step 10:

[0423] The server retrains the generative AI model based on the collected performance data and emotion data. Specifically, it adds the newly collected data to the model's training set and executes a process to readjust the model's parameters. After retraining, it generates an optimal plan under the new conditions and sends it to the device. Specifically, it includes evaluating the model's performance and adding training data as needed. The input includes performance data and emotion data, and the output is regenerated plan data.

[0424] (Application example 2)

[0425] 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."

[0426] Current food delivery services have the problem of being unable to suggest and deliver optimal meals based on a user's individual health and emotional state. Furthermore, to effectively support users' health maintenance and emotional stability, it is desirable to integrate and analyze lifestyle habits, dietary content, healthcare information, and emotional data, and provide optimal plans using a generative AI model. However, no system exists that can effectively achieve this.

[0427] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting the user's lifestyle information, dietary information, health care information, and emotional data; means for analyzing the input lifestyle information, dietary information, health care information, and emotional data and storing them in a database; means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative AI model based on the stored information and emotional data; means for presenting the generated plan and activity to the user; means for collecting the user's implementation data and generating a daily report; and means for retraining the generative AI model based on the collected implementation data and adjusting the plan and activity. This makes it possible to propose a meal plan optimized for the user's health and emotional state and to deliver the plan directly via food delivery, thereby supporting the user's health maintenance and emotional stability.

[0428] "Lifestyle information" is information about the user's daily activities and habits, including, for example, how they work, how they spend their holidays, and how often they exercise.

[0429] "Dietary information" refers to information about a user's eating preferences and habits, including, for example, favorite foods, disliked foods, meal frequency and timing, and the like.

[0430] "Healthcare information" refers to information about the user's health condition, including, for example, heart rate, blood pressure, sleep time, and amount of exercise.

[0431] "Emotion data" refers to information relating to the user's emotional state, including, for example, stress levels and mood changes.

[0432] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate optimal plans based on received data.

[0433] A "meal plan" is a personalized meal plan created based on the user's health and lifestyle, including specific food and cooking recommendations.

[0434] An "exercise plan" is an optimal exercise suggestion generated based on the user's health condition and lifestyle, and includes specific exercise types, times, and frequency.

[0435] "Mental health activities" are suggested activities to improve the mental health of users, including meditation, stretching, and relaxation techniques.

[0436] "Generated Plan" means a personalized meal plan, exercise plan, and mental health activities created by a generative AI model based on lifestyle information, dietary information, healthcare information, and emotional data.

[0437] "Implementation Data" means data about the results of diet, exercise, and mental health improvement activities that you actually undertake, including the specific results you enter into the Application.

[0438] A "Daily Report" is a report summarizing the results of a user's diet, exercise, and mental health improvement activities, including achievements, nutrient deficiencies, and recommended actions.

[0439] "Relearning" refers to the retraining of the generative AI model based on collected implementation data, a technology that enables more accurate plan generation.

[0440] This system collects, integrates, and analyzes a user's lifestyle, diet, health, and emotional data to provide optimal meal plans, exercise plans, and activities to improve mental health. This system is composed of three elements: a server, a terminal, and the user.

[0441] server

[0442] The server first receives the user's lifestyle, dietary, health, and emotional data sent from the device and stores it in a database. The data is received in JSON format. The server then analyzes the stored data, extracts and verifies the necessary fields, and runs a generative AI model based on the analyzed data to generate individually optimized meal plans, exercise plans, and activities to improve mental health.

[0443] The generated plan is then sent back to the device in JSON format. The server then collects the user's implementation data and generates a daily report, which includes information such as progress, nutrient deficiencies, and recommended actions. The server also retrains the generation AI model based on the collected implementation and emotional data, adjusting the plan.

[0444] Terminal

[0445] The device provides an interface for users to input lifestyle, diet, health, and emotional data. This data is converted into JSON format by the device and sent to the server. The device also displays the generated plan, daily report, and activities for improving mental health received from the server to the user. The displayed content is optimal health management suggestions based on lifestyle and emotional state. The device also collects the user's implementation data and sends it to the server.

[0446] User

[0447] Users input their lifestyle, diet, health, and emotional data through the device. Emotional data may also be collected through facial expression analysis, tone of voice, and text input. They then implement the suggested meal plan, exercise plan, and mental health improvement activities and enter the results into the device. Users can view daily reports to check their health management progress and receive suggestions for improvement.

[0448] Specific examples

[0449] For example, suppose a user works at a desk, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but don't exercise much every day. Their favorite food is salad and they dislike fried food. Their heart rate is 70 and they get 7 hours of sleep every night. Furthermore, the emotion engine detects that the user has recently been prone to stress. Based on this information, the server uses a generative AI model to generate the following plan and displays it on the device.

[0450] Meal Plan

[0451] Breakfast: Yogurt and fruit

[0452] Lunch: Chicken breast salad

[0453] Dinner: Vegetable soup and whole wheat bread

[0454] Exercise plan

[0455] Every morning: 15 minutes of stretching

[0456] Evening: 30-minute walk

[0457] Mental Health Improvement Plan

[0458] Meditation: 10 minutes

[0459] When the user carries out these plans and enters the results into the terminal, the following health management daily report will be presented the next day.

[0460] "Today's exercise was completed as planned, but your iron intake is low. Tomorrow, eat an iron-rich diet. You only meditated for five minutes, but continued meditation can help. Next time, aim for 10 minutes."

[0461] Prompt Sentence Examples

[0462] "I have a desk job and have been experiencing a lot of stress lately. My favorite food is salad and I avoid fried foods. My heart rate is 70 and I get 7 hours of sleep each night. Based on these parameters, please suggest a meal plan for today."

[0463] As such, the present invention enables users to perform individually optimized health management and continuously maintain and improve their health.

[0464] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0465] Step 1:

[0466] The user inputs lifestyle information, dietary information, health information, and emotional data using the device, which then converts the input data into JSON format and sends it to the server.

[0467] Input information includes how you work during the week, how you spend your days off, your likes and dislikes, your heart rate, sleep time, stress level, and more.

[0468] The output is the customer data in JSON format.

[0469] Step 2:

[0470] The server receives the JSON format data sent from the terminal and stores it in a database.

[0471] After receiving the data, the server parses and validates each field and prepares to run a generative AI model based on the stored data.

[0472] The input information is the user data in JSON format sent from the terminal, and the output is the saved data and parsed field information.

[0473] Step 3:

[0474] The server uses stored user data and emotional data to run a generative AI model to generate optimal meal plans, exercise plans, and activities to improve mental health.

[0475] The generative AI model takes into account the user's lifestyle habits, dietary preferences, healthcare information, and emotional data, and performs data calculations to suggest the optimal plan.

[0476] The input information is the user information stored in the database, and the output is the generated plan.

[0477] Step 4:

[0478] The server converts the generated plan into JSON format and sends it to the terminal.

[0479] The device receives the plan and displays it on the user's screen, including meal plans, exercise plans, and activities to improve mental health.

[0480] The input information is the generated plan, and the output is the plan information displayed on the terminal.

[0481] Step 5:

[0482] The user carries out a meal plan, an exercise plan, and mental health improvement activities and inputs the results into the device.

[0483] Specifically, users enter details about the meals they ate, the exercise they did, and the mental health activities they engaged in. The device converts this data into JSON format and sends it to the server.

[0484] The input information is the implementation data entered by the user, and the output is the implementation data in JSON format.

[0485] Step 6:

[0486] The server receives and analyzes the implementation data sent by the user.

[0487] The implementation data is verified and compiled into a daily report, which includes achievements, nutrient deficiencies, and recommended actions.

[0488] The input information is the performance data sent by the user, and the output is a daily report.

[0489] Step 7:

[0490] The server generates a daily report and sends it back to the terminal.

[0491] The device displays the received daily report to the user, who can then check their progress and areas for improvement and consider their next action plan.

[0492] The input information is the generated daily report, and the output is the daily report displayed on the terminal.

[0493] Step 8:

[0494] The server retrains the generative AI model based on the implementation data and emotion data.

[0495] Re-learning improves the accuracy of plan generation from the next time onwards.

[0496] The input information is analyzed performance and emotion data, and the output is a retrained generative AI model.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] [Second embodiment]

[0501] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0502] 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.

[0503] 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).

[0504] 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.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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."

[0513] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is configured as follows, and its specific operation is shown below.

[0514] System Configuration

[0515] 1. Server

[0516] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[0517] A generative AI model is used to analyze this information and generate personalized meal and exercise plans.

[0518] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[0519] 2. Terminal

[0520] The terminal provides an interface for users to input lifestyle, dietary, and health care information.

[0521] Displays the generated plans and daily reports received from the server.

[0522] The user's implementation data is sent to the server.

[0523] 3. Users

[0524] The user inputs his / her lifestyle information, dietary information, and health care information into the terminal.

[0525] Follow the suggested diet and exercise plan and enter the results into the device.

[0526] Check your own health management achievements and suggestions for improvement through daily reports.

[0527] Program processing

[0528] Entering information

[0529] The user launches the health management app and inputs information about their lifestyle, diet, and health care. For example, they input data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours.

[0530] The device collects this information and sends it to the server in JSON format.

[0531] Data analysis and storage

[0532] The server parses the data it receives and stores the information for each field in a database, adding new data and checking it against existing data for missing information or inconsistencies.

[0533] Plan generation using generative AI models

[0534] The server runs a generative AI model based on the stored data. The generative AI model takes the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[0535] Plan presentation

[0536] The server sends the generated plan to the device, which then visualizes the plan and presents it to the user. For example, the screen displays "Today's Meal Plan" and "Today's Exercise Plan."

[0537] Daily report creation

[0538] The user practices diet and exercise and inputs the results into the application. For example, they input data such as "I had yogurt for breakfast today" or "I walked for 30 minutes in the evening."

[0539] The device collects this performance data and sends it to a server. The server analyzes the performance data and generates a daily report. The daily report includes achievement levels, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[0540] Relearn

[0541] If the user is unable to complete the proposed plan, that data is also collected, for example, "I had difficulty completing 30 minutes of walking."

[0542] The server retrains the generative AI model based on difficult-to-achieve data. The generative AI model generates an optimal plan under the new conditions and sends it back to the device. For example, it suggests "instead of walking at night, we suggest light indoor exercise."

[0543] Specific examples

[0544] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on his days off, but doesn't exercise much every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night.

[0545] The server uses an AI model to generate a plan like the one below and displays it on the device.

[0546] Meal Plan:

[0547] Breakfast: Yogurt and fruit

[0548] Lunch: Chicken breast salad

[0549] Dinner: Vegetable soup and whole wheat bread

[0550] Exercise plan:

[0551] Every morning: 15 minutes of stretching

[0552] Evening: 30-minute walk

[0553] The next morning, the terminal presents the user with the following daily health management report:

[0554] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[0555] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[0556] The processing flow will be explained below.

[0557] Step 1:

[0558] The user launches the health management app and inputs lifestyle, diet, and health information, such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep."

[0559] Step 2:

[0560] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[0561] Step 3:

[0562] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[0563] Step 4:

[0564] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[0565] Step 5:

[0566] The server runs a generative AI model based on the stored information. Specifically, it inputs lifestyle, dietary, and health information into the model to generate optimal meal and exercise plans.

[0567] Step 6:

[0568] The server sends the generated plan to the terminal in JSON format.

[0569] Step 7:

[0570] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," and "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking."

[0571] Step 8:

[0572] The user follows the plan and enters the results into the app every day, for example, "I ate yogurt for breakfast" or "I walked for 30 minutes in the evening."

[0573] Step 9:

[0574] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[0575] Step 10:

[0576] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[0577] Step 11:

[0578] The server transmits the generated daily report to the terminal.

[0579] Step 12:

[0580] The terminal displays the daily report on the user interface, allowing the user to check their own health management achievements and suggestions for next actions.

[0581] Step 13:

[0582] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[0583] Step 14:

[0584] The server retrains the generative AI model based on difficult-to-achieve data, and after retraining, generates an optimal plan under new conditions.

[0585] Step 15:

[0586] The server sends the regenerated plan to the terminal.

[0587] Step 16:

[0588] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[0589] Example 1

[0590] 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."

[0591] In modern society, many people lead busy lives and often find it difficult to find enough time for health management. As a result, the risk of lifestyle-related diseases increases, making it difficult to maintain good health. Existing health management systems have issues such as difficulty in providing optimal diet and exercise plans tailored to each user's individual needs and inability to flexibly adapt to changes in the user's lifestyle. Furthermore, the mechanisms for evaluating the effectiveness of the generated plans and relearning them are inadequate, making it difficult to expect long-term health management effects.

[0592] 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.

[0593] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing the information in a database, means for generating an individually optimized meal plan and exercise plan using a generative AI model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for retraining the generative AI model based on the collected performance data and adjusting the plan, means for communicating the user's input information and performance data in JSON format, means for visually displaying the generated plan and daily report, means for the server to receive and parse the JSON format data and store it in a database, means for the generative model to be trained using TensorFlow or PyTorch, and means for the retrained generative model to generate and retransmit an optimal plan under new conditions. This not only enables the provision of an optimal health management plan tailored to the user's individual needs, but also enables the user to maintain and improve their health over the long term by evaluating and relearning the plan's effectiveness.

[0594] "Lifestyle information" refers to behavioral patterns and habits related to the user's daily life, specifically information such as how they work on weekdays, how they spend their holidays, and how often they exercise.

[0595] "Dietary information" refers to information including the user's daily food and drink preferences, disliked foods, allergy information, etc.

[0596] "Healthcare information" refers to specific data that indicates the user's health status, including health indicators such as heart rate, sleep time, and weight.

[0597] A "generative AI model" is an algorithm trained using machine learning that generates an optimal plan for each individual user based on their input information.

[0598] "JSON format" refers to JavaScript Object Notation (JSON), a format that represents data in a lightweight, structured way and is used for text-based data exchange.

[0599] A "daily report" is a document that reports on a day's health management activities and includes achievement levels, nutrient deficiencies, and recommended actions.

[0600] "Database" refers to a system for efficiently storing, managing, and accessing information, and refers to a place where a user's lifestyle information, dietary information, and healthcare information are stored.

[0601] "Parsing" refers to the process of interpreting and structurally analyzing received data.

[0602] "TensorFlow" is an open-source machine learning framework and software tool used to train neural networks.

[0603] "PyTorch" is an open-source library that makes it easy to train and run machine learning models, and refers to a software tool used to train neural networks, similar to TensorFlow.

[0604] "Server" refers to the computer system that receives data sent by users, processes and stores it, and runs the generative AI model.

[0605] "Terminal" refers to a device that allows users to input information and view generated plans and daily reports, such as a smartphone or tablet.

[0606] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is mainly composed of a server, a terminal, and a user, and its specific operation is as follows.

[0607] System Configuration

[0608] 1. Server

[0609] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[0610] A generative AI model is used to analyze the information received and generate a personalized meal and exercise plan.

[0611] User performance data is collected, a daily report is created based on this data, and the generative AI model is then retrained.

[0612] The servers are installed with machine learning frameworks such as TensorFlow and PyTorch, which are used to train and retrain generative AI models.

[0613] 2. Terminal

[0614] The terminal provides an interface for users to input lifestyle information, dietary information, and health care information through the application.

[0615] Visually display the generated plans and daily reports received from the server.

[0616] The data performed by the user is sent to the server.

[0617] 3. Users

[0618] Users use a dedicated health management app to input their lifestyle, dietary, and health care information into the device.

[0619] Follow the suggested meal and exercise plan and re-enter your results into the app.

[0620] Check your own health management achievements and suggestions for improvement through daily reports.

[0621] Input and analysis of information

[0622] The user launches the health management app and enters information about their individual lifestyle habits (e.g., weekday working habits and exercise frequency), dietary information (e.g., favorite foods, disliked foods), and health information (e.g., heart rate, sleep duration). After input, the device converts this information into JSON format and sends it to the server.

[0623] The server parses the received JSON data and stores it in a database. The newly added information is checked against existing data to check for consistency and gaps, providing reliable data to feed into the generative AI model.

[0624] Plan generation using generative AI models

[0625] The data stored on the server is input into a generative AI model and analyzed using specific algorithms (using TensorFlow or PyTorch). This model generates optimal meal and exercise plans based on each user's data. For example, "For a user who works at a desk, we recommend yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner."

[0626] Presenting a plan and collecting implementation data

[0627] The generated plan is sent from the server to the device, which then visually displays the plan. The user follows the plan, practices diet and exercise, and re-enters the results into the app. The device then sends this data back to the server in JSON format.

[0628] Daily report creation and generation AI model retraining

[0629] Based on the user's activity data, the server generates a daily report that includes the user's achievements, nutrient deficiencies, and recommended actions for the next day. For example, specific feedback is provided, such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet."

[0630] In addition, data on plans that could not be completed is collected, and the generative AI model is retrained based on this data. This retraining process generates a new, more realistic and feasible plan and sends it back to the device. For example, adjustments may be made, such as suggesting light indoor exercise instead of an evening walk.

[0631] Prompt Sentence Examples

[0632] "What's the best meal plan for someone who works a desk job during the week?"

[0633] "Please suggest a recommended exercise plan for someone with a heart rate of 70."

[0634] This allows users to continuously manage their health and obtain the health plan that is best suited to them through the system.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1:

[0637] Entering information

[0638] The user launches the health management app and inputs lifestyle, diet, and health information. Specifically, the user enters "weekday work habits" (e.g., desk work), "weekend habits" (e.g., jogging), and "exercise frequency" (e.g., three times a week) into the interface. The input information is converted to JSON format, and the input amount is sent to the server in JSON format for subsequent processing.

[0639] Step 2:

[0640] Data transmission and storage

[0641] The device sends the lifestyle, diet, and health information entered to the server in JSON format. The server receives this information, parses the JSON data, analyzes the details of each item, and stores it in a database. Specifically, information such as how you work on weekdays, how you spend your days off, and how often you exercise is stored in the database.

[0642] Step 3:

[0643] Data analysis

[0644] The server performs an analysis based on the information stored in the database. This analysis includes checking the user's lifestyle information, consistency, and missing data. Each data item is collated to identify missing information or inconsistencies. The analysis results are used as input data for the generative AI model.

[0645] Step 4:

[0646] Plan generation using generative AI models

[0647] The server runs a generative AI model (trained using TensorFlow or PyTorch) based on the analyzed data. For example, if a user works at a desk, their favorite food is salad, and their heart rate is 70, the generative AI model will take these data as input and generate an optimal meal plan and exercise plan (e.g., yogurt and fruit for breakfast, vegetable soup for dinner). The output is the generated plan.

[0648] Step 5:

[0649] Presenting the plan

[0650] The server converts the generated plan back into JSON format and sends it to the device. The device visually displays the received generated plan. Specifically, the app screen displays "Today's meal plan" and "Today's exercise plan." For example, items such as "Yogurt and fruit for breakfast," "Chicken breast salad for lunch," and "Vegetable soup for dinner" are displayed.

[0651] Step 6:

[0652] Entering implementation data

[0653] The user puts the presented plan into practice and enters the results into the app. Specifically, they enter implementation data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects the implementation data entered by the user and sends it back to the server in JSON format.

[0654] Step 7:

[0655] Creating daily reports

[0656] The server receives and analyzes the user's exercise data. Based on this analysis, it generates a daily report on the user's exercise results for the day. The daily report includes the user's achievement level, any nutrient deficiencies, and recommended health behaviors for the next day. For example, the report may include specific feedback such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat foods rich in iron."

[0657] Step 8:

[0658] Retraining generative AI models

[0659] The server also collects data if the user is unable to complete the plan. For example, data such as "it was difficult to walk for 30 minutes" is input. This data is used to retrain the generative AI model. The generative AI model is retrained under new conditions and generates the optimal plan again. Specifically, a new suggestion such as "instead of walking in the evening, we suggest light indoor exercise" is generated and sent to the device.

[0660] (Application example 1)

[0661] 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."

[0662] While existing health management systems provide individually optimized meal and exercise plans, few of them offer integrated health content (e.g., blog posts, videos, recipes, etc.). Furthermore, they lacked systems that provide feedback on the effectiveness of the plans based on user data and enable continuous improvement by retraining generative models. This limited the sustainability and effectiveness of users' health management.

[0663] 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.

[0664] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan and exercise plan using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's implementation data and generating a daily report, means for relearning the generative model based on the collected implementation data and adjusting the plan, means for delivering the generated plan and related health-related content to the user, and means for collecting implementation data based on the generated plan and providing feedback. This allows the user to receive not only an individually optimized health management plan but also useful health information related to it, enabling sustainable and effective health management.

[0665] "Lifestyle information" refers to information about the user's behavioral patterns and habits in their daily lives, such as how they work, when they wake up and go to bed, and how often they exercise.

[0666] "Dietary information" refers to information about the user's eating habits, such as favorite foods, disliked foods, and the contents of daily meals.

[0667] "Healthcare information" refers to information about the user's health condition, such as data about heart rate, weight, height, and sleep duration.

[0668] A "database" is a storage device that stores collected lifestyle, dietary, and healthcare information and makes it accessible as needed.

[0669] A "generative model" is a model that uses AI technology to generate optimal meal and exercise plans based on a user's lifestyle, dietary, and healthcare information.

[0670] A "meal plan" is a plan that suggests meal plans suitable for the user based on a generative model.

[0671] An "exercise plan" is a plan that suggests exercise content suitable for the user based on a generative model.

[0672] A "daily report" is a report that includes an evaluation of the activities carried out that day and suggestions for improvement based on the user's implementation data.

[0673] "Retraining" refers to updating a generative model to improve its accuracy based on newly collected data.

[0674] "Related health content" is additional information to help users manage their health, such as health blog posts, videos, recipes, etc.

[0675] "Feedback" refers to the process of providing evaluations and advice based on the data the user has put into practice.

[0676] This invention relates to a system that utilizes a generative AI model based on a user's lifestyle, diet, and health information to propose optimal health management. The system has the function of allowing users to input information about their lifestyle and health status, and based on that information, provides personalized optimal meal and exercise plans. It also delivers related health content and receives feedback on implementation data, allowing the generative model to retrain and improve the quality of the plans.

[0677] System Configuration

[0678] The server receives lifestyle, dietary, and health information sent by the user and stores it in a database. It analyzes the stored information and uses a generative AI model to generate an optimal meal plan and exercise plan for each individual. It also collects the user's exercise data and creates a daily report. It then retrains the generative model based on the exercise data.

[0679] The terminal provides an interface for users to input lifestyle, diet, and health information, displays the generated plan and daily report received from the server, and transmits the user's implementation data to the server.

[0680] Users enter their lifestyle, dietary, and health information into the device, follow the suggested meal and exercise plans, and then enter the results into the device to check their health management progress and improvement suggestions through daily reports.

[0681] Detailed explanation of operation

[0682] The server is built using Python and provides a REST API using frameworks such as Django or Flask, data is processed in JSON format, databases are AWS DynamoDB or Firebase Firestore, and generative AI models are built using AI frameworks such as TensorFlow and PyTorch.

[0683] As a specific example, the following scenario can be considered.

[0684] The user opens the smartphone app "My Health Guide" and enters information about their lifestyle, diet, and health care. For example, they might enter data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They might also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. This information is sent to the server in JSON format.

[0685] The server analyzes the received data and stores it in a database. It then runs a generative AI model to generate optimal meal and exercise plans for each user. The generated plan is again sent to the smartphone in JSON format and displayed on the app's UI. For example, "Today's meal plan" might show "yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner." Additionally, "Today's exercise plan" might suggest "15 minutes of stretching every morning and 30 minutes of walking in the evening."

[0686] When a user practices diet and exercise and enters the results into the application, the device collects this data and sends it to the server. The server analyzes the data and generates a daily report. The daily report includes the level of achievement, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[0687] Furthermore, if the user is unable to complete the proposed plan, that data is also collected, and the server retrains the generative AI model based on the difficult-to-achieve data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device. For example, it may suggest something like, "Instead of walking in the evening, we suggest light indoor exercise."

[0688] Example prompt sentence:

[0689] You're a busy desk worker with a lifestyle where you only exercise three times a week. Your favorite food is salad and you hate fried food. Your heart rate is 70 and you get seven hours of sleep each night. Use this information to generate a meal and exercise plan that's perfect for you.

[0690] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0691] Step 1:

[0692] The user launches the smartphone app and inputs lifestyle, diet, and health information. Specifically, the user enters information such as their weekday work style (desk work), weekend habits (jogging), how often they exercise three times a week, their favorite food (salad), their least favorite food (fried food), their heart rate (70), and the amount of sleep they get (7 hours). This information is collected through the device's interface. Input formats include text fields and selection lists.

[0693] input:

[0694] Lifestyle information

[0695] Meal Information

[0696] Healthcare Information

[0697] output:

[0698] User information data in JSON format

[0699] Step 2:

[0700] The device converts the collected lifestyle, dietary, and health information into JSON format and sends it to the server. The HTTPS protocol is used for communication, ensuring secure data transfer. The server receives the request, analyzes the data, and stores it in a database. Specifically, a web framework such as Django or Flask is used.

[0701] input:

[0702] User information data in JSON format

[0703] output:

[0704] User information stored in a server-side database

[0705] Step 3:

[0706] The server runs a generative AI model based on user information stored in a database. The generative AI model receives the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. It also generates an exercise plan that includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[0707] input:

[0708] User information stored in a database

[0709] output:

[0710] Personalized meal and exercise plans

[0711] Step 4:

[0712] The generated meal and exercise plans are sent to the device in JSON format. The device visualizes the received plans and presents them to the user. Specifically, the app's UI displays "Today's meal plan" as "Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread." Additionally, "Today's exercise plan" displays "Every morning: 15 minutes of stretching, Evening: 30 minutes of walking."

[0713] input:

[0714] Meal and exercise plans in JSON format

[0715] output:

[0716] Plans displayed in the app UI

[0717] Step 5:

[0718] The user puts the suggested diet and exercise into practice and enters the results into the application. For example, they enter data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects this data and sends it to the server in JSON format.

[0719] input:

[0720] Dietary and exercise data

[0721] output:

[0722] JSON format implementation data

[0723] Step 6:

[0724] The server analyzes the received data and generates a daily report. The daily report includes the user's achievement level, nutrient deficiencies, and recommended actions. For example, it may include, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet." The generated report is sent to the device in JSON format, and the device displays it on the app's UI.

[0725] input:

[0726] JSON format implementation data

[0727] output:

[0728] JSON format health management daily report

[0729] Step 7:

[0730] If the user is unable to complete the proposed plan, that data is also collected in JSON format and sent to the server. The server then retrains the generative AI model based on the difficult-to-complete data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device in JSON format. For example, the system may suggest something like, "Instead of walking at night, we suggest light indoor exercise."

[0731] input:

[0732] Hard to achieve data in JSON format

[0733] output:

[0734] New plans from retrained generative AI models

[0735] 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.

[0736] The present invention relates to a system that proposes optimal health management based on a user's emotions by combining an emotion engine with the user's lifestyle, dietary information, and healthcare information. The system is configured as follows, and its specific operation is shown below.

[0737] System Configuration

[0738] 1. Server

[0739] The server receives lifestyle information, dietary information, health care information, and emotion data sent by the user and stores them in a database.

[0740] Generative AI models are used to analyze this information and emotional data to generate personalized meal plans, exercise plans, and activities to improve mental health.

[0741] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[0742] 2. Terminal

[0743] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data.

[0744] Display generated plans and daily reports received from the server, as well as mental health improvement activities.

[0745] The user's implementation data is sent to the server.

[0746] 3. Users

[0747] Users input their lifestyle, diet, and health information, as well as emotional data, into the device, which is collected from facial expressions, voice, and text input.

[0748] Follow the suggested meal plans, exercise plans, and mental health activities and enter the results into your device.

[0749] Check your own health management achievements and suggestions for improvement through daily reports.

[0750] Program processing

[0751] Entering information

[0752] A user launches a health management app and inputs lifestyle, diet, health, and emotional data. For example, the user enters data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. The user also provides information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. Emotional data is collected based on the user's facial expression analysis, tone of voice, and text input.

[0753] The device collects this information and converts it into JSON format, preparing the data for later transmission.

[0754] Data analysis and storage

[0755] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[0756] Plan generation using generative AI models

[0757] The server runs a generative AI model based on the stored data and emotional data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotional data as input, and generates individually optimized meal plans, exercise plans, and activities to improve mental health. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening. Furthermore, based on the emotional data, it also suggests meditation for relaxation and exercises to relieve stress.

[0758] Plan presentation

[0759] The server sends the generated plan to the terminal in JSON format.

[0760] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," while "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." Furthermore, "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[0761] Daily report creation

[0762] The user performs dietary, exercise, and relaxation activities and enters the results into the application. For example, they can enter "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[0763] The device collects these implementation data and sends them to the server in JSON format.

[0764] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[0765] Relearn

[0766] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[0767] The server retrains the generative AI model based on difficult-to-achieve data and emotional data. After retraining, it generates an optimal plan under the new conditions.

[0768] The server sends the regenerated plan to the terminal.

[0769] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[0770] Specific examples

[0771] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[0772] The server uses an AI model to generate a plan like the one below and displays it on the device.

[0773] Meal Plan:

[0774] Breakfast: Yogurt and fruit

[0775] Lunch: Chicken breast salad

[0776] Dinner: Vegetable soup and whole wheat bread

[0777] Exercise plan:

[0778] Every morning: 15 minutes of stretching

[0779] Evening: 30-minute walk

[0780] Mental Health Improvement Plan:

[0781] Meditation: 10 minutes

[0782] The next morning, the terminal presents the user with the following daily health management report:

[0783] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[0784] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[0785] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[0786] The processing flow will be explained below.

[0787] Step 1:

[0788] The user launches the health management app and inputs lifestyle information, dietary information, health information, and emotional data. Specifically, the user inputs data such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep." Emotional data is collected based on facial expression analysis, tone of voice, and text input.

[0789] Step 2:

[0790] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[0791] Step 3:

[0792] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[0793] Step 4:

[0794] The server analyzes the received data, extracts and validates the necessary fields, and stores them in the database. At the same time, emotion data is also stored in the database.

[0795] Step 5:

[0796] The server runs a generative AI model based on the stored information and emotional data. The generative AI model receives lifestyle, diet, health, and emotional data as inputs and generates an individually optimized meal plan, exercise plan, and activities to improve mental health.

[0797] Step 6:

[0798] The server sends the generated plan to the terminal in JSON format.

[0799] Step 7:

[0800] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread." "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[0801] Step 8:

[0802] Users follow the plan and enter their results into the app every day, for example, "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[0803] Step 9:

[0804] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[0805] Step 10:

[0806] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[0807] Step 11:

[0808] The server transmits the generated daily report to the terminal.

[0809] Step 12:

[0810] The terminal displays the daily report on the user interface, and the user can check the progress of their health management and suggestions for improvement.

[0811] Step 13:

[0812] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[0813] Step 14:

[0814] The server retrains the generative AI model based on difficult-to-achieve data and emotional data, and then generates an optimal plan under the new conditions.

[0815] Step 15:

[0816] The server sends the regenerated plan to the terminal.

[0817] Step 16:

[0818] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[0819] Specific examples

[0820] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[0821] The server uses an AI model to generate a plan like the one below and displays it on the device.

[0822] Meal Plan:

[0823] Breakfast: Yogurt and fruit

[0824] Lunch: Chicken breast salad

[0825] Dinner: Vegetable soup and whole wheat bread

[0826] Exercise plan:

[0827] Every morning: 15 minutes of stretching

[0828] Evening: 30-minute walk

[0829] Mental Health Improvement Plan:

[0830] Meditation: 10 minutes

[0831] The next morning, the terminal presents the user with the following daily health management report:

[0832] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[0833] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[0834] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[0835] Example 2

[0836] 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."

[0837] Conventional health management systems generally propose plans based on a user's lifestyle, diet, and healthcare information, but do not take into account factors such as emotional fluctuations and mental stress. Furthermore, these systems do not adequately analyze individual data or retrain models, making it difficult to provide users with optimal health management plans.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0839] In this invention, the server includes means for inputting lifestyle information, dietary information, and health care information of a user, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for relearning the generative model based on the collected performance data and adjusting the plan, means for collecting and analyzing emotional data, and means for adjusting the generated plan based on the emotional data, thereby enabling comprehensive health management including the user's emotional fluctuations.

[0840] "Lifestyle information" refers to information about the user's daily life, including how they work on weekdays, how they spend their holidays, how often they exercise, and so on.

[0841] "Dietary information" refers to information about the user's daily diet, including favorite foods, disliked foods, and frequency of intake.

[0842] "Healthcare information" refers to information about the user's health condition, including biometric data such as heart rate, sleep time, and blood pressure, as well as self-assessment of health condition.

[0843] "Emotional data" refers to information about a user's emotional state, including data obtained from facial expression analysis, tone of voice, text input, and the like.

[0844] A "generative model" refers to an algorithm or AI model that analyzes input data and generates the optimal plan.

[0845] "Meal Plan" means the specific dietary recommendations made to maintain and improve the User's health.

[0846] An "exercise plan" refers to specific exercise content proposed to maintain and improve the user's health.

[0847] "Mental health activities" refers to relaxation and stress relief activities suggested to improve the user's mental health.

[0848] "Implementation data" includes data showing the results of the diet, exercise, and activities that the user actually undertook.

[0849] A "daily report" is a report that compiles the results of actions taken by a user and shows the level of achievement and areas for improvement.

[0850] "Relearning" refers to the process of retraining the generative model based on collected implementation and emotion data to generate more accurate plans.

[0851] This invention is a system that collects lifestyle information, dietary information, health care information, and emotional data from users, and provides individually optimized health management plans based on the collected data. The main components of this system include a server, a terminal, and a user.

[0852] server

[0853] The server receives lifestyle, diet, health, and emotional data sent by users and stores it in a database. The server analyzes this information using a generative model (e.g., OpenAI's GPT-3) to generate optimal meal plans, exercise plans, and activities for improving mental health. It also creates daily reports based on the user's implementation data and retrains the generative model to continuously improve the plans.

[0854] Terminal

[0855] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data. The terminal displays the generated plan and daily report received from the server, collects the user's implementation data, and sends it to the server.

[0856] User

[0857] Users input their lifestyle, dietary, and health information, as well as emotional data, into the device. Emotional data is collected from facial expression analysis, tone of voice, and text input. Users also execute the proposed meal plan, exercise plan, and mental health improvement activities and input the results into the device, contributing to the system's plan generation and re-learning.

[0858] Specific examples

[0859] For example, suppose a user works at a desk on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but do not exercise often on a daily basis. Their favorite food is salad, and they dislike fried food. Their heart rate is 70, and they get 7 hours of sleep every night. Emotional data collected recently indicates that they tend to feel stressed.

[0860] The server runs a generative AI model based on this information and generates a plan like the one below.

[0861] Meal Plan:

[0862] Breakfast: Yogurt and fruit

[0863] Lunch: Chicken breast salad

[0864] Dinner: Vegetable soup and whole wheat bread

[0865] Exercise plan:

[0866] Every morning: 15 minutes of stretching

[0867] Evening: 30-minute walk

[0868] Mental Health Improvement Plan:

[0869] Meditation: 10 minutes

[0870] The next morning, the terminal presents the user with the following daily health management report:

[0871] "You exercised as planned today, but your iron intake is low. Eat more iron-rich foods tomorrow."

[0872] "I only meditated for five minutes, but I think it will be effective if I continue. Next time, I'll aim for 10 minutes."

[0873] Prompt Sentence Examples

[0874] "I currently have a desk job during the weekdays, waking up at 7am every day and working from 8am until 5pm. I go jogging on my days off. I've been feeling stressed a lot lately. Could you please suggest the best meal plan, exercise plan, and activities to improve my mental health?"

[0875] This system enables users to manage their health in an individually optimized way, enabling them to maintain and improve their health continuously. It also analyzes users' emotional data in real time and provides appropriate healthcare suggestions based on their emotional fluctuations, enabling them to live a balanced life both physically and mentally.

[0876] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0877] Step 1:

[0878] The user starts the health management app and inputs lifestyle information, dietary information, health information, and emotional data. The personal information is input in the following format. For example,

[0879] Lifestyle information: "Desk work on weekdays, jog on weekends, exercise three times a week"

[0880] Dietary information: "My favorite food is salad, and my least favorite food is fried food."

[0881] Health information: "Heart rate is 70, sleep time is 7 hours"

[0882] Emotional data: "I feel stressed easily these days"

[0883] The input information is sent to the terminal. The terminal converts this information into JSON format and prepares it for sending to the server. The input to the server includes the user data in JSON format.

[0884] Step 2:

[0885] The device converts the lifestyle, diet, health, and emotion data entered by the user into JSON format. The converted data is sent to the server. Specifically, the device organizes the data collected from the user interface and packages it as a JSON string. The output includes the user data in JSON format.

[0886] Step 3:

[0887] The server parses the JSON formatted user data received from the device and extracts the required fields. This parsing includes checking the data for consistency, eliminating duplicate data, etc. The input contains the JSON formatted user data, and the output is the extracted user data that is stored in the database.

[0888] Step 4:

[0889] The server runs a generative AI model (e.g., OpenAI GPT-3) based on the stored user data and emotion data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotion data as input, and generates optimal meal plans, exercise plans, and activities to improve mental health. Specifically, the model provides input data, performs calculations, and obtains plan data as output. The input includes the user's integrated data, and the output is plan data in JSON format.

[0890] Step 5:

[0891] The server sends the generated plan data to the terminal in JSON format. Specifically, it converts the plan data obtained by the generative AI model into JSON format and performs communication processing to send it to the terminal. The output includes the plan data in JSON format.

[0892] Step 6:

[0893] The device displays the received plan on the user interface. Specifically, it parses the plan data in JSON format and renders the UI to display it in a user-friendly format. The displayed information includes "Today's meal plan: Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread" and "Today's exercise plan: 15 minutes of stretching every morning, 30 minutes of walking in the evening." The output is displayed on the user interface.

[0894] Step 7:

[0895] The user puts the proposed meal plan, exercise plan, and activities to improve mental health into practice and enters the results into the application. For example, they might enter "I ate yogurt for breakfast," "I walked for 30 minutes in the evening," or "I meditated for 10 minutes." The entered information is sent to the device, which then converts it back into JSON format and sends it to the server. The input contains the user's activity data, and the output is JSON-formatted activity data.

[0896] Step 8:

[0897] The server analyzes the received behavior data and generates a daily report. This analysis includes validity checks on the behavior data and extraction of missing elements (e.g., nutrients, exercise). The daily report includes achievement, missing nutrients, and recommended actions. The input includes the behavior data in JSON format, and the output is the generated daily report.

[0898] Step 9:

[0899] The device displays the generated daily report on the user interface. Specifically, it analyzes the JSON format daily report data and processes it to display it on the user interface. For example, it displays a message such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Eat an iron-rich diet tomorrow." The output is the daily report displayed on the user interface.

[0900] Step 10:

[0901] The server retrains the generative AI model based on the collected performance data and emotion data. Specifically, it adds the newly collected data to the model's training set and executes a process to readjust the model's parameters. After retraining, it generates an optimal plan under the new conditions and sends it to the device. Specifically, it includes evaluating the model's performance and adding training data as needed. The input includes performance data and emotion data, and the output is regenerated plan data.

[0902] (Application example 2)

[0903] 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."

[0904] Current food delivery services have the problem of being unable to suggest and deliver optimal meals based on a user's individual health and emotional state. Furthermore, to effectively support users' health maintenance and emotional stability, it is desirable to integrate and analyze lifestyle habits, dietary content, healthcare information, and emotional data, and provide optimal plans using a generative AI model. However, no system exists that can effectively achieve this.

[0905] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting the user's lifestyle information, dietary information, health care information, and emotional data; means for analyzing the input lifestyle information, dietary information, health care information, and emotional data and storing them in a database; means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative AI model based on the stored information and emotional data; means for presenting the generated plan and activity to the user; means for collecting the user's implementation data and generating a daily report; and means for retraining the generative AI model based on the collected implementation data and adjusting the plan and activity. This makes it possible to propose a meal plan optimized for the user's health and emotional state and to deliver the plan directly via food delivery, thereby supporting the user's health maintenance and emotional stability.

[0906] "Lifestyle information" is information about the user's daily activities and habits, including, for example, how they work, how they spend their holidays, and how often they exercise.

[0907] "Dietary information" refers to information about a user's eating preferences and habits, including, for example, favorite foods, disliked foods, meal frequency and timing, and the like.

[0908] "Healthcare information" refers to information about the user's health condition, including, for example, heart rate, blood pressure, sleep time, and amount of exercise.

[0909] "Emotion data" refers to information relating to the user's emotional state, including, for example, stress levels and mood changes.

[0910] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate optimal plans based on received data.

[0911] A "meal plan" is a personalized meal plan created based on the user's health and lifestyle, including specific food and cooking recommendations.

[0912] An "exercise plan" is an optimal exercise suggestion generated based on the user's health condition and lifestyle, and includes specific exercise types, times, and frequency.

[0913] "Mental health activities" are suggested activities to improve the mental health of users, including meditation, stretching, and relaxation techniques.

[0914] "Generated Plan" means a personalized meal plan, exercise plan, and mental health activities created by a generative AI model based on lifestyle information, dietary information, healthcare information, and emotional data.

[0915] "Implementation Data" means data about the results of diet, exercise, and mental health improvement activities that you actually undertake, including the specific results you enter into the Application.

[0916] A "Daily Report" is a report summarizing the results of a user's diet, exercise, and mental health improvement activities, including achievements, nutrient deficiencies, and recommended actions.

[0917] "Relearning" refers to the retraining of the generative AI model based on collected implementation data, a technology that enables more accurate plan generation.

[0918] This system collects, integrates, and analyzes a user's lifestyle, diet, health, and emotional data to provide optimal meal plans, exercise plans, and activities to improve mental health. This system is composed of three elements: a server, a terminal, and the user.

[0919] server

[0920] The server first receives the user's lifestyle, dietary, health, and emotional data sent from the device and stores it in a database. The data is received in JSON format. The server then analyzes the stored data, extracts and verifies the necessary fields, and runs a generative AI model based on the analyzed data to generate individually optimized meal plans, exercise plans, and activities to improve mental health.

[0921] The generated plan is then sent back to the device in JSON format. The server then collects the user's implementation data and generates a daily report, which includes information such as progress, nutrient deficiencies, and recommended actions. The server also retrains the generation AI model based on the collected implementation and emotional data, adjusting the plan.

[0922] Terminal

[0923] The device provides an interface for users to input lifestyle, diet, health, and emotional data. This data is converted into JSON format by the device and sent to the server. The device also displays the generated plan, daily report, and activities for improving mental health received from the server to the user. The displayed content is optimal health management suggestions based on lifestyle and emotional state. The device also collects the user's implementation data and sends it to the server.

[0924] User

[0925] Users input their lifestyle, diet, health, and emotional data through the device. Emotional data may also be collected through facial expression analysis, tone of voice, and text input. They then implement the suggested meal plan, exercise plan, and mental health improvement activities and enter the results into the device. Users can view daily reports to check their health management progress and receive suggestions for improvement.

[0926] Specific examples

[0927] For example, suppose a user works at a desk, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but don't exercise much every day. Their favorite food is salad and they dislike fried food. Their heart rate is 70 and they get 7 hours of sleep every night. Furthermore, the emotion engine detects that the user has recently been prone to stress. Based on this information, the server uses a generative AI model to generate the following plan and displays it on the device.

[0928] Meal Plan

[0929] Breakfast: Yogurt and fruit

[0930] Lunch: Chicken breast salad

[0931] Dinner: Vegetable soup and whole wheat bread

[0932] Exercise plan

[0933] Every morning: 15 minutes of stretching

[0934] Evening: 30-minute walk

[0935] Mental Health Improvement Plan

[0936] Meditation: 10 minutes

[0937] When the user carries out these plans and enters the results into the terminal, the following health management daily report will be presented the next day.

[0938] "Today's exercise was completed as planned, but your iron intake is low. Tomorrow, eat an iron-rich diet. You only meditated for five minutes, but continued meditation can help. Next time, aim for 10 minutes."

[0939] Prompt Sentence Examples

[0940] "I have a desk job and have been experiencing a lot of stress lately. My favorite food is salad and I avoid fried foods. My heart rate is 70 and I get 7 hours of sleep each night. Based on these parameters, please suggest a meal plan for today."

[0941] As such, the present invention enables users to perform individually optimized health management and continuously maintain and improve their health.

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] The user inputs lifestyle information, dietary information, health information, and emotional data using the device, which then converts the input data into JSON format and sends it to the server.

[0945] Input information includes how you work during the week, how you spend your days off, your likes and dislikes, your heart rate, sleep time, stress level, and more.

[0946] The output is the customer data in JSON format.

[0947] Step 2:

[0948] The server receives the JSON format data sent from the terminal and stores it in a database.

[0949] After receiving the data, the server parses and validates each field and prepares to run a generative AI model based on the stored data.

[0950] The input information is the user data in JSON format sent from the terminal, and the output is the saved data and parsed field information.

[0951] Step 3:

[0952] The server uses stored user data and emotional data to run a generative AI model to generate optimal meal plans, exercise plans, and activities to improve mental health.

[0953] The generative AI model takes into account the user's lifestyle habits, dietary preferences, healthcare information, and emotional data, and performs data calculations to suggest the optimal plan.

[0954] The input information is the user information stored in the database, and the output is the generated plan.

[0955] Step 4:

[0956] The server converts the generated plan into JSON format and sends it to the terminal.

[0957] The device receives the plan and displays it on the user's screen, including meal plans, exercise plans, and activities to improve mental health.

[0958] The input information is the generated plan, and the output is the plan information displayed on the terminal.

[0959] Step 5:

[0960] The user carries out a meal plan, an exercise plan, and mental health improvement activities and inputs the results into the device.

[0961] Specifically, users enter details about the meals they ate, the exercise they did, and the mental health activities they engaged in. The device converts this data into JSON format and sends it to the server.

[0962] The input information is the implementation data entered by the user, and the output is the implementation data in JSON format.

[0963] Step 6:

[0964] The server receives and analyzes the implementation data sent by the user.

[0965] The implementation data is verified and compiled into a daily report, which includes achievements, nutrient deficiencies, and recommended actions.

[0966] The input information is the performance data sent by the user, and the output is a daily report.

[0967] Step 7:

[0968] The server generates a daily report and sends it back to the terminal.

[0969] The device displays the received daily report to the user, who can then check their progress and areas for improvement and consider their next action plan.

[0970] The input information is the generated daily report, and the output is the daily report displayed on the terminal.

[0971] Step 8:

[0972] The server retrains the generative AI model based on the implementation data and emotion data.

[0973] Re-learning improves the accuracy of plan generation from the next time onwards.

[0974] The input information is analyzed performance and emotion data, and the output is a retrained generative AI model.

[0975] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0976] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0977] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0978] [Third embodiment]

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

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

[0981] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0982] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0983] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0984] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

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

[0986] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0987] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0988] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0989] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0990] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0991] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is configured as follows, and its specific operation is shown below.

[0992] System Configuration

[0993] 1. Server

[0994] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[0995] A generative AI model is used to analyze this information and generate personalized meal and exercise plans.

[0996] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[0997] 2. Terminal

[0998] The terminal provides an interface for users to input lifestyle, dietary, and health care information.

[0999] Displays the generated plans and daily reports received from the server.

[1000] The user's implementation data is sent to the server.

[1001] 3. Users

[1002] The user inputs his / her lifestyle information, dietary information, and health care information into the terminal.

[1003] Follow the suggested diet and exercise plan and enter the results into the device.

[1004] Check your own health management achievements and suggestions for improvement through daily reports.

[1005] Program processing

[1006] Entering information

[1007] The user launches the health management app and inputs information about their lifestyle, diet, and health care. For example, they input data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours.

[1008] The device collects this information and sends it to the server in JSON format.

[1009] Data analysis and storage

[1010] The server parses the data it receives and stores the information for each field in a database, adding new data and checking it against existing data for missing information or inconsistencies.

[1011] Plan generation using generative AI models

[1012] The server runs a generative AI model based on the stored data. The generative AI model takes the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[1013] Plan presentation

[1014] The server sends the generated plan to the device, which then visualizes the plan and presents it to the user. For example, the screen displays "Today's Meal Plan" and "Today's Exercise Plan."

[1015] Daily report creation

[1016] The user practices diet and exercise and inputs the results into the application. For example, they input data such as "I had yogurt for breakfast today" or "I walked for 30 minutes in the evening."

[1017] The device collects this performance data and sends it to a server. The server analyzes the performance data and generates a daily report. The daily report includes achievement levels, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[1018] Relearn

[1019] If the user is unable to complete the proposed plan, that data is also collected, for example, "I had difficulty completing 30 minutes of walking."

[1020] The server retrains the generative AI model based on difficult-to-achieve data. The generative AI model generates an optimal plan under the new conditions and sends it back to the device. For example, it suggests "instead of walking at night, we suggest light indoor exercise."

[1021] Specific examples

[1022] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on his days off, but doesn't exercise much every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night.

[1023] The server uses an AI model to generate a plan like the one below and displays it on the device.

[1024] Meal Plan:

[1025] Breakfast: Yogurt and fruit

[1026] Lunch: Chicken breast salad

[1027] Dinner: Vegetable soup and whole wheat bread

[1028] Exercise plan:

[1029] Every morning: 15 minutes of stretching

[1030] Evening: 30-minute walk

[1031] The next morning, the terminal presents the user with the following daily health management report:

[1032] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[1033] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[1034] The processing flow will be explained below.

[1035] Step 1:

[1036] The user launches the health management app and inputs lifestyle, diet, and health information, such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep."

[1037] Step 2:

[1038] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[1039] Step 3:

[1040] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[1041] Step 4:

[1042] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[1043] Step 5:

[1044] The server runs a generative AI model based on the stored information. Specifically, it inputs lifestyle, dietary, and health information into the model to generate optimal meal and exercise plans.

[1045] Step 6:

[1046] The server sends the generated plan to the terminal in JSON format.

[1047] Step 7:

[1048] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," and "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking."

[1049] Step 8:

[1050] The user follows the plan and enters the results into the app every day, for example, "I ate yogurt for breakfast" or "I walked for 30 minutes in the evening."

[1051] Step 9:

[1052] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[1053] Step 10:

[1054] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[1055] Step 11:

[1056] The server transmits the generated daily report to the terminal.

[1057] Step 12:

[1058] The terminal displays the daily report on the user interface, allowing the user to check their own health management achievements and suggestions for next actions.

[1059] Step 13:

[1060] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[1061] Step 14:

[1062] The server retrains the generative AI model based on difficult-to-achieve data, and after retraining, generates an optimal plan under new conditions.

[1063] Step 15:

[1064] The server sends the regenerated plan to the terminal.

[1065] Step 16:

[1066] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[1067] Example 1

[1068] 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."

[1069] In modern society, many people lead busy lives and often find it difficult to find enough time for health management. As a result, the risk of lifestyle-related diseases increases, making it difficult to maintain good health. Existing health management systems have issues such as difficulty in providing optimal diet and exercise plans tailored to each user's individual needs and inability to flexibly adapt to changes in the user's lifestyle. Furthermore, the mechanisms for evaluating the effectiveness of the generated plans and relearning them are inadequate, making it difficult to expect long-term health management effects.

[1070] 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.

[1071] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing the information in a database, means for generating an individually optimized meal plan and exercise plan using a generative AI model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for retraining the generative AI model based on the collected performance data and adjusting the plan, means for communicating the user's input information and performance data in JSON format, means for visually displaying the generated plan and daily report, means for the server to receive and parse the JSON format data and store it in a database, means for the generative model to be trained using TensorFlow or PyTorch, and means for the retrained generative model to generate and retransmit an optimal plan under new conditions. This not only enables the provision of an optimal health management plan tailored to the user's individual needs, but also enables the user to maintain and improve their health over the long term by evaluating and relearning the plan's effectiveness.

[1072] "Lifestyle information" refers to behavioral patterns and habits related to the user's daily life, specifically information such as how they work on weekdays, how they spend their holidays, and how often they exercise.

[1073] "Dietary information" refers to information including the user's daily food and drink preferences, disliked foods, allergy information, etc.

[1074] "Healthcare information" refers to specific data that indicates the user's health status, including health indicators such as heart rate, sleep time, and weight.

[1075] A "generative AI model" is an algorithm trained using machine learning that generates an optimal plan for each individual user based on their input information.

[1076] "JSON format" refers to JavaScript Object Notation (JSON), a format that represents data in a lightweight, structured way and is used for text-based data exchange.

[1077] A "daily report" is a document that reports on a day's health management activities and includes achievement levels, nutrient deficiencies, and recommended actions.

[1078] "Database" refers to a system for efficiently storing, managing, and accessing information, and refers to a place where a user's lifestyle information, dietary information, and healthcare information are stored.

[1079] "Parsing" refers to the process of interpreting and structurally analyzing received data.

[1080] "TensorFlow" is an open-source machine learning framework and software tool used to train neural networks.

[1081] "PyTorch" is an open-source library that makes it easy to train and run machine learning models, and refers to a software tool used to train neural networks, similar to TensorFlow.

[1082] "Server" refers to the computer system that receives data sent by users, processes and stores it, and runs the generative AI model.

[1083] "Terminal" refers to a device that allows users to input information and view generated plans and daily reports, such as a smartphone or tablet.

[1084] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is mainly composed of a server, a terminal, and a user, and its specific operation is as follows.

[1085] System Configuration

[1086] 1. Server

[1087] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[1088] A generative AI model is used to analyze the information received and generate a personalized meal and exercise plan.

[1089] User performance data is collected, a daily report is created based on this data, and the generative AI model is then retrained.

[1090] The servers are installed with machine learning frameworks such as TensorFlow and PyTorch, which are used to train and retrain generative AI models.

[1091] 2. Terminal

[1092] The terminal provides an interface for users to input lifestyle information, dietary information, and health care information through the application.

[1093] Visually display the generated plans and daily reports received from the server.

[1094] The data performed by the user is sent to the server.

[1095] 3. Users

[1096] Users use a dedicated health management app to input their lifestyle, dietary, and health care information into the device.

[1097] Follow the suggested meal and exercise plan and re-enter your results into the app.

[1098] Check your own health management achievements and suggestions for improvement through daily reports.

[1099] Input and analysis of information

[1100] The user launches the health management app and enters information about their individual lifestyle habits (e.g., weekday working habits and exercise frequency), dietary information (e.g., favorite foods, disliked foods), and health information (e.g., heart rate, sleep duration). After input, the device converts this information into JSON format and sends it to the server.

[1101] The server parses the received JSON data and stores it in a database. The newly added information is checked against existing data to check for consistency and gaps, providing reliable data to feed into the generative AI model.

[1102] Plan generation using generative AI models

[1103] The data stored on the server is input into a generative AI model and analyzed using specific algorithms (using TensorFlow or PyTorch). This model generates optimal meal and exercise plans based on each user's data. For example, "For a user who works at a desk, we recommend yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner."

[1104] Presenting a plan and collecting implementation data

[1105] The generated plan is sent from the server to the device, which then visually displays the plan. The user follows the plan, practices diet and exercise, and re-enters the results into the app. The device then sends this data back to the server in JSON format.

[1106] Daily report creation and generation AI model retraining

[1107] Based on the user's activity data, the server generates a daily report that includes the user's achievements, nutrient deficiencies, and recommended actions for the next day. For example, specific feedback is provided, such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet."

[1108] In addition, data on plans that could not be completed is collected, and the generative AI model is retrained based on this data. This retraining process generates a new, more realistic and feasible plan and sends it back to the device. For example, adjustments may be made, such as suggesting light indoor exercise instead of an evening walk.

[1109] Prompt Sentence Examples

[1110] "What's the best meal plan for someone who works a desk job during the week?"

[1111] "Please suggest a recommended exercise plan for someone with a heart rate of 70."

[1112] This allows users to continuously manage their health and obtain the health plan that is best suited to them through the system.

[1113] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1114] Step 1:

[1115] Entering information

[1116] The user launches the health management app and inputs lifestyle, diet, and health information. Specifically, the user enters "weekday work habits" (e.g., desk work), "weekend habits" (e.g., jogging), and "exercise frequency" (e.g., three times a week) into the interface. The input information is converted to JSON format, and the input amount is sent to the server in JSON format for subsequent processing.

[1117] Step 2:

[1118] Data transmission and storage

[1119] The device sends the lifestyle, diet, and health information entered to the server in JSON format. The server receives this information, parses the JSON data, analyzes the details of each item, and stores it in a database. Specifically, information such as how you work on weekdays, how you spend your days off, and how often you exercise is stored in the database.

[1120] Step 3:

[1121] Data analysis

[1122] The server performs an analysis based on the information stored in the database. This analysis includes checking the user's lifestyle information, consistency, and missing data. Each data item is collated to identify missing information or inconsistencies. The analysis results are used as input data for the generative AI model.

[1123] Step 4:

[1124] Plan generation using generative AI models

[1125] The server runs a generative AI model (trained using TensorFlow or PyTorch) based on the analyzed data. For example, if a user works at a desk, their favorite food is salad, and their heart rate is 70, the generative AI model will take these data as input and generate an optimal meal plan and exercise plan (e.g., yogurt and fruit for breakfast, vegetable soup for dinner). The output is the generated plan.

[1126] Step 5:

[1127] Presenting the plan

[1128] The server converts the generated plan back into JSON format and sends it to the device. The device visually displays the received generated plan. Specifically, the app screen displays "Today's meal plan" and "Today's exercise plan." For example, items such as "Yogurt and fruit for breakfast," "Chicken breast salad for lunch," and "Vegetable soup for dinner" are displayed.

[1129] Step 6:

[1130] Entering implementation data

[1131] The user puts the presented plan into practice and enters the results into the app. Specifically, they enter implementation data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects the implementation data entered by the user and sends it back to the server in JSON format.

[1132] Step 7:

[1133] Creating daily reports

[1134] The server receives and analyzes the user's exercise data. Based on this analysis, it generates a daily report on the user's exercise results for the day. The daily report includes the user's achievement level, any nutrient deficiencies, and recommended health behaviors for the next day. For example, the report may include specific feedback such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat foods rich in iron."

[1135] Step 8:

[1136] Retraining generative AI models

[1137] The server also collects data if the user is unable to complete the plan. For example, data such as "it was difficult to walk for 30 minutes" is input. This data is used to retrain the generative AI model. The generative AI model is retrained under new conditions and generates the optimal plan again. Specifically, a new suggestion such as "instead of walking in the evening, we suggest light indoor exercise" is generated and sent to the device.

[1138] (Application example 1)

[1139] 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."

[1140] While existing health management systems provide individually optimized meal and exercise plans, few of them offer integrated health content (e.g., blog posts, videos, recipes, etc.). Furthermore, they lacked systems that provide feedback on the effectiveness of the plans based on user data and enable continuous improvement by retraining generative models. This limited the sustainability and effectiveness of users' health management.

[1141] 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.

[1142] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan and exercise plan using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's implementation data and generating a daily report, means for relearning the generative model based on the collected implementation data and adjusting the plan, means for delivering the generated plan and related health-related content to the user, and means for collecting implementation data based on the generated plan and providing feedback. This allows the user to receive not only an individually optimized health management plan but also useful health information related to it, enabling sustainable and effective health management.

[1143] "Lifestyle information" refers to information about the user's behavioral patterns and habits in their daily lives, such as how they work, when they wake up and go to bed, and how often they exercise.

[1144] "Dietary information" refers to information about the user's eating habits, such as favorite foods, disliked foods, and the contents of daily meals.

[1145] "Healthcare information" refers to information about the user's health condition, such as data about heart rate, weight, height, and sleep duration.

[1146] A "database" is a storage device that stores collected lifestyle, dietary, and healthcare information and makes it accessible as needed.

[1147] A "generative model" is a model that uses AI technology to generate optimal meal and exercise plans based on a user's lifestyle, dietary, and healthcare information.

[1148] A "meal plan" is a plan that suggests meal plans suitable for the user based on a generative model.

[1149] An "exercise plan" is a plan that suggests exercise content suitable for the user based on a generative model.

[1150] A "daily report" is a report that includes an evaluation of the activities carried out that day and suggestions for improvement based on the user's implementation data.

[1151] "Retraining" refers to updating a generative model to improve its accuracy based on newly collected data.

[1152] "Related health content" is additional information to help users manage their health, such as health blog posts, videos, recipes, etc.

[1153] "Feedback" refers to the process of providing evaluations and advice based on the data the user has put into practice.

[1154] This invention relates to a system that utilizes a generative AI model based on a user's lifestyle, diet, and health information to propose optimal health management. The system has the function of allowing users to input information about their lifestyle and health status, and based on that information, provides personalized optimal meal and exercise plans. It also delivers related health content and receives feedback on implementation data, allowing the generative model to retrain and improve the quality of the plans.

[1155] System Configuration

[1156] The server receives lifestyle, dietary, and health information sent by the user and stores it in a database. It analyzes the stored information and uses a generative AI model to generate an optimal meal plan and exercise plan for each individual. It also collects the user's exercise data and creates a daily report. It then retrains the generative model based on the exercise data.

[1157] The terminal provides an interface for users to input lifestyle, diet, and health information, displays the generated plan and daily report received from the server, and transmits the user's implementation data to the server.

[1158] Users enter their lifestyle, dietary, and health information into the device, follow the suggested meal and exercise plans, and then enter the results into the device to check their health management progress and improvement suggestions through daily reports.

[1159] Detailed explanation of operation

[1160] The server is built using Python and provides a REST API using frameworks such as Django or Flask, data is processed in JSON format, databases are AWS DynamoDB or Firebase Firestore, and generative AI models are built using AI frameworks such as TensorFlow and PyTorch.

[1161] As a specific example, the following scenario can be considered.

[1162] The user opens the smartphone app "My Health Guide" and enters information about their lifestyle, diet, and health care. For example, they might enter data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They might also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. This information is sent to the server in JSON format.

[1163] The server analyzes the received data and stores it in a database. It then runs a generative AI model to generate optimal meal and exercise plans for each user. The generated plan is again sent to the smartphone in JSON format and displayed on the app's UI. For example, "Today's meal plan" might show "yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner." Additionally, "Today's exercise plan" might suggest "15 minutes of stretching every morning and 30 minutes of walking in the evening."

[1164] When a user practices diet and exercise and enters the results into the application, the device collects this data and sends it to the server. The server analyzes the data and generates a daily report. The daily report includes the level of achievement, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[1165] Furthermore, if the user is unable to complete the proposed plan, that data is also collected, and the server retrains the generative AI model based on the difficult-to-achieve data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device. For example, it may suggest something like, "Instead of walking in the evening, we suggest light indoor exercise."

[1166] Example prompt sentence:

[1167] You're a busy desk worker with a lifestyle where you only exercise three times a week. Your favorite food is salad and you hate fried food. Your heart rate is 70 and you get seven hours of sleep each night. Use this information to generate a meal and exercise plan that's perfect for you.

[1168] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1169] Step 1:

[1170] The user launches the smartphone app and inputs lifestyle, diet, and health information. Specifically, the user enters information such as their weekday work style (desk work), weekend habits (jogging), how often they exercise three times a week, their favorite food (salad), their least favorite food (fried food), their heart rate (70), and the amount of sleep they get (7 hours). This information is collected through the device's interface. Input formats include text fields and selection lists.

[1171] input:

[1172] Lifestyle information

[1173] Meal Information

[1174] Healthcare Information

[1175] output:

[1176] User information data in JSON format

[1177] Step 2:

[1178] The device converts the collected lifestyle, dietary, and health information into JSON format and sends it to the server. The HTTPS protocol is used for communication, ensuring secure data transfer. The server receives the request, analyzes the data, and stores it in a database. Specifically, a web framework such as Django or Flask is used.

[1179] input:

[1180] User information data in JSON format

[1181] output:

[1182] User information stored in a server-side database

[1183] Step 3:

[1184] The server runs a generative AI model based on user information stored in a database. The generative AI model receives the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. It also generates an exercise plan that includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[1185] input:

[1186] User information stored in a database

[1187] output:

[1188] Personalized meal and exercise plans

[1189] Step 4:

[1190] The generated meal and exercise plans are sent to the device in JSON format. The device visualizes the received plans and presents them to the user. Specifically, the app's UI displays "Today's meal plan" as "Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread." Additionally, "Today's exercise plan" displays "Every morning: 15 minutes of stretching, Evening: 30 minutes of walking."

[1191] input:

[1192] Meal and exercise plans in JSON format

[1193] output:

[1194] Plans displayed in the app UI

[1195] Step 5:

[1196] The user puts the suggested diet and exercise into practice and enters the results into the application. For example, they enter data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects this data and sends it to the server in JSON format.

[1197] input:

[1198] Dietary and exercise data

[1199] output:

[1200] JSON format implementation data

[1201] Step 6:

[1202] The server analyzes the received data and generates a daily report. The daily report includes the user's achievement level, nutrient deficiencies, and recommended actions. For example, it may include, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet." The generated report is sent to the device in JSON format, and the device displays it on the app's UI.

[1203] input:

[1204] JSON format implementation data

[1205] output:

[1206] JSON format health management daily report

[1207] Step 7:

[1208] If the user is unable to complete the proposed plan, that data is also collected in JSON format and sent to the server. The server then retrains the generative AI model based on the difficult-to-complete data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device in JSON format. For example, the system may suggest something like, "Instead of walking at night, we suggest light indoor exercise."

[1209] input:

[1210] Hard to achieve data in JSON format

[1211] output:

[1212] New plans from retrained generative AI models

[1213] 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.

[1214] The present invention relates to a system that proposes optimal health management based on a user's emotions by combining an emotion engine with the user's lifestyle, dietary information, and healthcare information. The system is configured as follows, and its specific operation is shown below.

[1215] System Configuration

[1216] 1. Server

[1217] The server receives lifestyle information, dietary information, health care information, and emotion data sent by the user and stores them in a database.

[1218] Generative AI models are used to analyze this information and emotional data to generate personalized meal plans, exercise plans, and activities to improve mental health.

[1219] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[1220] 2. Terminal

[1221] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data.

[1222] Display generated plans and daily reports received from the server, as well as mental health improvement activities.

[1223] The user's implementation data is sent to the server.

[1224] 3. Users

[1225] Users input their lifestyle, diet, and health information, as well as emotional data, into the device, which is collected from facial expressions, voice, and text input.

[1226] Follow the suggested meal plans, exercise plans, and mental health activities and enter the results into your device.

[1227] Check your own health management achievements and suggestions for improvement through daily reports.

[1228] Program processing

[1229] Entering information

[1230] A user launches a health management app and inputs lifestyle, diet, health, and emotional data. For example, the user enters data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. The user also provides information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. Emotional data is collected based on the user's facial expression analysis, tone of voice, and text input.

[1231] The device collects this information and converts it into JSON format, preparing the data for later transmission.

[1232] Data analysis and storage

[1233] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[1234] Plan generation using generative AI models

[1235] The server runs a generative AI model based on the stored data and emotional data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotional data as input, and generates individually optimized meal plans, exercise plans, and activities to improve mental health. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening. Furthermore, based on the emotional data, it also suggests meditation for relaxation and exercises to relieve stress.

[1236] Plan presentation

[1237] The server sends the generated plan to the terminal in JSON format.

[1238] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," while "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." Furthermore, "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[1239] Daily report creation

[1240] The user performs dietary, exercise, and relaxation activities and enters the results into the application. For example, they can enter "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[1241] The device collects these implementation data and sends them to the server in JSON format.

[1242] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[1243] Relearn

[1244] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[1245] The server retrains the generative AI model based on difficult-to-achieve data and emotional data. After retraining, it generates an optimal plan under the new conditions.

[1246] The server sends the regenerated plan to the terminal.

[1247] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[1248] Specific examples

[1249] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[1250] The server uses an AI model to generate a plan like the one below and displays it on the device.

[1251] Meal Plan:

[1252] Breakfast: Yogurt and fruit

[1253] Lunch: Chicken breast salad

[1254] Dinner: Vegetable soup and whole wheat bread

[1255] Exercise plan:

[1256] Every morning: 15 minutes of stretching

[1257] Evening: 30-minute walk

[1258] Mental Health Improvement Plan:

[1259] Meditation: 10 minutes

[1260] The next morning, the terminal presents the user with the following daily health management report:

[1261] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[1262] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[1263] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[1264] The processing flow will be explained below.

[1265] Step 1:

[1266] The user launches the health management app and inputs lifestyle information, dietary information, health information, and emotional data. Specifically, the user inputs data such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep." Emotional data is collected based on facial expression analysis, tone of voice, and text input.

[1267] Step 2:

[1268] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[1269] Step 3:

[1270] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[1271] Step 4:

[1272] The server analyzes the received data, extracts and validates the necessary fields, and stores them in the database. At the same time, emotion data is also stored in the database.

[1273] Step 5:

[1274] The server runs a generative AI model based on the stored information and emotional data. The generative AI model receives lifestyle, diet, health, and emotional data as inputs and generates an individually optimized meal plan, exercise plan, and activities to improve mental health.

[1275] Step 6:

[1276] The server sends the generated plan to the terminal in JSON format.

[1277] Step 7:

[1278] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread." "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[1279] Step 8:

[1280] Users follow the plan and enter their results into the app every day, for example, "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[1281] Step 9:

[1282] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[1283] Step 10:

[1284] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[1285] Step 11:

[1286] The server transmits the generated daily report to the terminal.

[1287] Step 12:

[1288] The terminal displays the daily report on the user interface, and the user can check the progress of their health management and suggestions for improvement.

[1289] Step 13:

[1290] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[1291] Step 14:

[1292] The server retrains the generative AI model based on difficult-to-achieve data and emotional data, and then generates an optimal plan under the new conditions.

[1293] Step 15:

[1294] The server sends the regenerated plan to the terminal.

[1295] Step 16:

[1296] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[1297] Specific examples

[1298] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[1299] The server uses an AI model to generate a plan like the one below and displays it on the device.

[1300] Meal Plan:

[1301] Breakfast: Yogurt and fruit

[1302] Lunch: Chicken breast salad

[1303] Dinner: Vegetable soup and whole wheat bread

[1304] Exercise plan:

[1305] Every morning: 15 minutes of stretching

[1306] Evening: 30-minute walk

[1307] Mental Health Improvement Plan:

[1308] Meditation: 10 minutes

[1309] The next morning, the terminal presents the user with the following daily health management report:

[1310] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[1311] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[1312] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[1313] Example 2

[1314] 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."

[1315] Conventional health management systems generally propose plans based on a user's lifestyle, diet, and healthcare information, but do not take into account factors such as emotional fluctuations and mental stress. Furthermore, these systems do not adequately analyze individual data or retrain models, making it difficult to provide users with optimal health management plans.

[1316] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1317] In this invention, the server includes means for inputting lifestyle information, dietary information, and health care information of a user, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for relearning the generative model based on the collected performance data and adjusting the plan, means for collecting and analyzing emotional data, and means for adjusting the generated plan based on the emotional data, thereby enabling comprehensive health management including the user's emotional fluctuations.

[1318] "Lifestyle information" refers to information about the user's daily life, including how they work on weekdays, how they spend their holidays, how often they exercise, and so on.

[1319] "Dietary information" refers to information about the user's daily diet, including favorite foods, disliked foods, and frequency of intake.

[1320] "Healthcare information" refers to information about the user's health condition, including biometric data such as heart rate, sleep time, and blood pressure, as well as self-assessment of health condition.

[1321] "Emotional data" refers to information about a user's emotional state, including data obtained from facial expression analysis, tone of voice, text input, and the like.

[1322] A "generative model" refers to an algorithm or AI model that analyzes input data and generates the optimal plan.

[1323] "Meal Plan" means the specific dietary recommendations made to maintain and improve the User's health.

[1324] An "exercise plan" refers to specific exercise content proposed to maintain and improve the user's health.

[1325] "Mental health activities" refers to relaxation and stress relief activities suggested to improve the user's mental health.

[1326] "Implementation data" includes data showing the results of the diet, exercise, and activities that the user actually undertook.

[1327] A "daily report" is a report that compiles the results of actions taken by a user and shows the level of achievement and areas for improvement.

[1328] "Relearning" refers to the process of retraining the generative model based on collected implementation and emotion data to generate more accurate plans.

[1329] This invention is a system that collects lifestyle information, dietary information, health care information, and emotional data from users, and provides individually optimized health management plans based on the collected data. The main components of this system include a server, a terminal, and a user.

[1330] server

[1331] The server receives lifestyle, diet, health, and emotional data sent by users and stores it in a database. The server analyzes this information using a generative model (e.g., OpenAI's GPT-3) to generate optimal meal plans, exercise plans, and activities for improving mental health. It also creates daily reports based on the user's implementation data and retrains the generative model to continuously improve the plans.

[1332] Terminal

[1333] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data. The terminal displays the generated plan and daily report received from the server, collects the user's implementation data, and sends it to the server.

[1334] User

[1335] Users input their lifestyle, dietary, and health information, as well as emotional data, into the device. Emotional data is collected from facial expression analysis, tone of voice, and text input. Users also execute the proposed meal plan, exercise plan, and mental health improvement activities and input the results into the device, contributing to the system's plan generation and re-learning.

[1336] Specific examples

[1337] For example, suppose a user works at a desk on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but do not exercise often on a daily basis. Their favorite food is salad, and they dislike fried food. Their heart rate is 70, and they get 7 hours of sleep every night. Emotional data collected recently indicates that they tend to feel stressed.

[1338] The server runs a generative AI model based on this information and generates a plan like the one below.

[1339] Meal Plan:

[1340] Breakfast: Yogurt and fruit

[1341] Lunch: Chicken breast salad

[1342] Dinner: Vegetable soup and whole wheat bread

[1343] Exercise plan:

[1344] Every morning: 15 minutes of stretching

[1345] Evening: 30-minute walk

[1346] Mental Health Improvement Plan:

[1347] Meditation: 10 minutes

[1348] The next morning, the terminal presents the user with the following daily health management report:

[1349] "You exercised as planned today, but your iron intake is low. Eat more iron-rich foods tomorrow."

[1350] "I only meditated for five minutes, but I think it will be effective if I continue. Next time, I'll aim for 10 minutes."

[1351] Prompt Sentence Examples

[1352] "I currently have a desk job during the weekdays, waking up at 7am every day and working from 8am until 5pm. I go jogging on my days off. I've been feeling stressed a lot lately. Could you please suggest the best meal plan, exercise plan, and activities to improve my mental health?"

[1353] This system enables users to manage their health in an individually optimized way, enabling them to maintain and improve their health continuously. It also analyzes users' emotional data in real time and provides appropriate healthcare suggestions based on their emotional fluctuations, enabling them to live a balanced life both physically and mentally.

[1354] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1355] Step 1:

[1356] The user starts the health management app and inputs lifestyle information, dietary information, health information, and emotional data. The personal information is input in the following format. For example,

[1357] Lifestyle information: "Desk work on weekdays, jog on weekends, exercise three times a week"

[1358] Dietary information: "My favorite food is salad, and my least favorite food is fried food."

[1359] Health information: "Heart rate is 70, sleep time is 7 hours"

[1360] Emotional data: "I feel stressed easily these days"

[1361] The input information is sent to the terminal. The terminal converts this information into JSON format and prepares it for sending to the server. The input to the server includes the user data in JSON format.

[1362] Step 2:

[1363] The device converts the lifestyle, diet, health, and emotion data entered by the user into JSON format. The converted data is sent to the server. Specifically, the device organizes the data collected from the user interface and packages it as a JSON string. The output includes the user data in JSON format.

[1364] Step 3:

[1365] The server parses the JSON formatted user data received from the device and extracts the required fields. This parsing includes checking the data for consistency, eliminating duplicate data, etc. The input contains the JSON formatted user data, and the output is the extracted user data that is stored in the database.

[1366] Step 4:

[1367] The server runs a generative AI model (e.g., OpenAI GPT-3) based on the stored user data and emotion data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotion data as input, and generates optimal meal plans, exercise plans, and activities to improve mental health. Specifically, the model provides input data, performs calculations, and obtains plan data as output. The input includes the user's integrated data, and the output is plan data in JSON format.

[1368] Step 5:

[1369] The server sends the generated plan data to the terminal in JSON format. Specifically, it converts the plan data obtained by the generative AI model into JSON format and performs communication processing to send it to the terminal. The output includes the plan data in JSON format.

[1370] Step 6:

[1371] The device displays the received plan on the user interface. Specifically, it parses the plan data in JSON format and renders the UI to display it in a user-friendly format. The displayed information includes "Today's meal plan: Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread" and "Today's exercise plan: 15 minutes of stretching every morning, 30 minutes of walking in the evening." The output is displayed on the user interface.

[1372] Step 7:

[1373] The user puts the proposed meal plan, exercise plan, and activities to improve mental health into practice and enters the results into the application. For example, they might enter "I ate yogurt for breakfast," "I walked for 30 minutes in the evening," or "I meditated for 10 minutes." The entered information is sent to the device, which then converts it back into JSON format and sends it to the server. The input contains the user's activity data, and the output is JSON-formatted activity data.

[1374] Step 8:

[1375] The server analyzes the received behavior data and generates a daily report. This analysis includes validity checks on the behavior data and extraction of missing elements (e.g., nutrients, exercise). The daily report includes achievement, missing nutrients, and recommended actions. The input includes the behavior data in JSON format, and the output is the generated daily report.

[1376] Step 9:

[1377] The device displays the generated daily report on the user interface. Specifically, it analyzes the JSON format daily report data and processes it to display it on the user interface. For example, it displays a message such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Eat an iron-rich diet tomorrow." The output is the daily report displayed on the user interface.

[1378] Step 10:

[1379] The server retrains the generative AI model based on the collected performance data and emotion data. Specifically, it adds the newly collected data to the model's training set and executes a process to readjust the model's parameters. After retraining, it generates an optimal plan under the new conditions and sends it to the device. Specifically, it includes evaluating the model's performance and adding training data as needed. The input includes performance data and emotion data, and the output is regenerated plan data.

[1380] (Application example 2)

[1381] 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."

[1382] Current food delivery services have the problem of being unable to suggest and deliver optimal meals based on a user's individual health and emotional state. Furthermore, to effectively support users' health maintenance and emotional stability, it is desirable to integrate and analyze lifestyle habits, dietary content, healthcare information, and emotional data, and provide optimal plans using a generative AI model. However, no system exists that can effectively achieve this.

[1383] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting the user's lifestyle information, dietary information, health care information, and emotional data; means for analyzing the input lifestyle information, dietary information, health care information, and emotional data and storing them in a database; means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative AI model based on the stored information and emotional data; means for presenting the generated plan and activity to the user; means for collecting the user's implementation data and generating a daily report; and means for retraining the generative AI model based on the collected implementation data and adjusting the plan and activity. This makes it possible to propose a meal plan optimized for the user's health and emotional state and to deliver the plan directly via food delivery, thereby supporting the user's health maintenance and emotional stability.

[1384] "Lifestyle information" is information about the user's daily activities and habits, including, for example, how they work, how they spend their holidays, and how often they exercise.

[1385] "Dietary information" refers to information about a user's eating preferences and habits, including, for example, favorite foods, disliked foods, meal frequency and timing, and the like.

[1386] "Healthcare information" refers to information about the user's health condition, including, for example, heart rate, blood pressure, sleep time, and amount of exercise.

[1387] "Emotion data" refers to information relating to the user's emotional state, including, for example, stress levels and mood changes.

[1388] A "generative AI model" is an artificial intelligence model that uses machine learning and deep learning to generate optimal plans based on received data.

[1389] A "meal plan" is a personalized meal plan created based on the user's health and lifestyle, including specific food and cooking recommendations.

[1390] An "exercise plan" is an optimal exercise suggestion generated based on the user's health condition and lifestyle, and includes specific exercise types, times, and frequency.

[1391] "Mental health activities" are suggested activities to improve the mental health of users, including meditation, stretching, and relaxation techniques.

[1392] "Generated Plan" means a personalized meal plan, exercise plan, and mental health activities created by a generative AI model based on lifestyle information, dietary information, healthcare information, and emotional data.

[1393] "Implementation Data" means data about the results of diet, exercise, and mental health improvement activities that you actually undertake, including the specific results you enter into the Application.

[1394] A "Daily Report" is a report summarizing the results of a user's diet, exercise, and mental health improvement activities, including achievements, nutrient deficiencies, and recommended actions.

[1395] "Relearning" refers to the retraining of the generative AI model based on collected implementation data, a technology that enables more accurate plan generation.

[1396] This system collects, integrates, and analyzes a user's lifestyle, diet, health, and emotional data to provide optimal meal plans, exercise plans, and activities to improve mental health. This system is composed of three elements: a server, a terminal, and the user.

[1397] server

[1398] The server first receives the user's lifestyle, dietary, health, and emotional data sent from the device and stores it in a database. The data is received in JSON format. The server then analyzes the stored data, extracts and verifies the necessary fields, and runs a generative AI model based on the analyzed data to generate individually optimized meal plans, exercise plans, and activities to improve mental health.

[1399] The generated plan is then sent back to the device in JSON format. The server then collects the user's implementation data and generates a daily report, which includes information such as progress, nutrient deficiencies, and recommended actions. The server also retrains the generation AI model based on the collected implementation and emotional data, adjusting the plan.

[1400] Terminal

[1401] The device provides an interface for users to input lifestyle, diet, health, and emotional data. This data is converted into JSON format by the device and sent to the server. The device also displays the generated plan, daily report, and activities for improving mental health received from the server to the user. The displayed content is optimal health management suggestions based on lifestyle and emotional state. The device also collects the user's implementation data and sends it to the server.

[1402] User

[1403] Users input their lifestyle, diet, health, and emotional data through the device. Emotional data may also be collected through facial expression analysis, tone of voice, and text input. They then implement the suggested meal plan, exercise plan, and mental health improvement activities and enter the results into the device. Users can view daily reports to check their health management progress and receive suggestions for improvement.

[1404] Specific examples

[1405] For example, suppose a user works at a desk, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but don't exercise much every day. Their favorite food is salad and they dislike fried food. Their heart rate is 70 and they get 7 hours of sleep every night. Furthermore, the emotion engine detects that the user has recently been prone to stress. Based on this information, the server uses a generative AI model to generate the following plan and displays it on the device.

[1406] Meal Plan

[1407] Breakfast: Yogurt and fruit

[1408] Lunch: Chicken breast salad

[1409] Dinner: Vegetable soup and whole wheat bread

[1410] Exercise plan

[1411] Every morning: 15 minutes of stretching

[1412] Evening: 30-minute walk

[1413] Mental Health Improvement Plan

[1414] Meditation: 10 minutes

[1415] When the user carries out these plans and enters the results into the terminal, the following health management daily report will be presented the next day.

[1416] "Today's exercise was completed as planned, but your iron intake is low. Tomorrow, eat an iron-rich diet. You only meditated for five minutes, but continued meditation can help. Next time, aim for 10 minutes."

[1417] Prompt Sentence Examples

[1418] "I have a desk job and have been experiencing a lot of stress lately. My favorite food is salad and I avoid fried foods. My heart rate is 70 and I get 7 hours of sleep each night. Based on these parameters, please suggest a meal plan for today."

[1419] As such, the present invention enables users to perform individually optimized health management and continuously maintain and improve their health.

[1420] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1421] Step 1:

[1422] The user inputs lifestyle information, dietary information, health information, and emotional data using the device, which then converts the input data into JSON format and sends it to the server.

[1423] Input information includes how you work during the week, how you spend your days off, your likes and dislikes, your heart rate, sleep time, stress level, and more.

[1424] The output is the customer data in JSON format.

[1425] Step 2:

[1426] The server receives the JSON format data sent from the terminal and stores it in a database.

[1427] After receiving the data, the server parses and validates each field and prepares to run a generative AI model based on the stored data.

[1428] The input information is the user data in JSON format sent from the terminal, and the output is the saved data and parsed field information.

[1429] Step 3:

[1430] The server uses stored user data and emotional data to run a generative AI model to generate optimal meal plans, exercise plans, and activities to improve mental health.

[1431] The generative AI model takes into account the user's lifestyle habits, dietary preferences, healthcare information, and emotional data, and performs data calculations to suggest the optimal plan.

[1432] The input information is the user information stored in the database, and the output is the generated plan.

[1433] Step 4:

[1434] The server converts the generated plan into JSON format and sends it to the terminal.

[1435] The device receives the plan and displays it on the user's screen, including meal plans, exercise plans, and activities to improve mental health.

[1436] The input information is the generated plan, and the output is the plan information displayed on the terminal.

[1437] Step 5:

[1438] The user carries out a meal plan, an exercise plan, and mental health improvement activities and inputs the results into the device.

[1439] Specifically, users enter details about the meals they ate, the exercise they did, and the mental health activities they engaged in. The device converts this data into JSON format and sends it to the server.

[1440] The input information is the implementation data entered by the user, and the output is the implementation data in JSON format.

[1441] Step 6:

[1442] The server receives and analyzes the implementation data sent by the user.

[1443] The implementation data is verified and compiled into a daily report, which includes achievements, nutrient deficiencies, and recommended actions.

[1444] The input information is the performance data sent by the user, and the output is a daily report.

[1445] Step 7:

[1446] The server generates a daily report and sends it back to the terminal.

[1447] The device displays the received daily report to the user, who can then check their progress and areas for improvement and consider their next action plan.

[1448] The input information is the generated daily report, and the output is the daily report displayed on the terminal.

[1449] Step 8:

[1450] The server retrains the generative AI model based on the implementation data and emotion data.

[1451] Re-learning improves the accuracy of plan generation from the next time onwards.

[1452] The input information is analyzed performance and emotion data, and the output is a retrained generative AI model.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] [Fourth embodiment]

[1457] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1458] 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.

[1459] 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).

[1460] 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.

[1461] 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.

[1462] 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).

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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."

[1470] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is configured as follows, and its specific operation is shown below.

[1471] System Configuration

[1472] 1. Server

[1473] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[1474] A generative AI model is used to analyze this information and generate personalized meal and exercise plans.

[1475] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[1476] 2. Terminal

[1477] The terminal provides an interface for users to input lifestyle, dietary, and health care information.

[1478] Displays the generated plans and daily reports received from the server.

[1479] The user's implementation data is sent to the server.

[1480] 3. Users

[1481] The user inputs his / her lifestyle information, dietary information, and health care information into the terminal.

[1482] Follow the suggested diet and exercise plan and enter the results into the device.

[1483] Check your own health management achievements and suggestions for improvement through daily reports.

[1484] Program processing

[1485] Entering information

[1486] The user launches the health management app and inputs information about their lifestyle, diet, and health care. For example, they input data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours.

[1487] The device collects this information and sends it to the server in JSON format.

[1488] Data analysis and storage

[1489] The server parses the data it receives and stores the information for each field in a database, adding new data and checking it against existing data for missing information or inconsistencies.

[1490] Plan generation using generative AI models

[1491] The server runs a generative AI model based on the stored data. The generative AI model takes the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[1492] Plan presentation

[1493] The server sends the generated plan to the device, which then visualizes the plan and presents it to the user. For example, the screen displays "Today's Meal Plan" and "Today's Exercise Plan."

[1494] Daily report creation

[1495] The user practices diet and exercise and inputs the results into the application. For example, they input data such as "I had yogurt for breakfast today" or "I walked for 30 minutes in the evening."

[1496] The device collects this performance data and sends it to a server. The server analyzes the performance data and generates a daily report. The daily report includes achievement levels, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[1497] Relearn

[1498] If the user is unable to complete the proposed plan, that data is also collected, for example, "I had difficulty completing 30 minutes of walking."

[1499] The server retrains the generative AI model based on difficult-to-achieve data. The generative AI model generates an optimal plan under the new conditions and sends it back to the device. For example, it suggests "instead of walking at night, we suggest light indoor exercise."

[1500] Specific examples

[1501] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on his days off, but doesn't exercise much every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night.

[1502] The server uses an AI model to generate a plan like the one below and displays it on the device.

[1503] Meal Plan:

[1504] Breakfast: Yogurt and fruit

[1505] Lunch: Chicken breast salad

[1506] Dinner: Vegetable soup and whole wheat bread

[1507] Exercise plan:

[1508] Every morning: 15 minutes of stretching

[1509] Evening: 30-minute walk

[1510] The next morning, the terminal presents the user with the following daily health management report:

[1511] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[1512] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[1513] The processing flow will be explained below.

[1514] Step 1:

[1515] The user launches the health management app and inputs lifestyle, diet, and health information, such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep."

[1516] Step 2:

[1517] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[1518] Step 3:

[1519] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[1520] Step 4:

[1521] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[1522] Step 5:

[1523] The server runs a generative AI model based on the stored information. Specifically, it inputs lifestyle, dietary, and health information into the model to generate optimal meal and exercise plans.

[1524] Step 6:

[1525] The server sends the generated plan to the terminal in JSON format.

[1526] Step 7:

[1527] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," and "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking."

[1528] Step 8:

[1529] The user follows the plan and enters the results into the app every day, for example, "I ate yogurt for breakfast" or "I walked for 30 minutes in the evening."

[1530] Step 9:

[1531] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[1532] Step 10:

[1533] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[1534] Step 11:

[1535] The server transmits the generated daily report to the terminal.

[1536] Step 12:

[1537] The terminal displays the daily report on the user interface, allowing the user to check their own health management achievements and suggestions for next actions.

[1538] Step 13:

[1539] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[1540] Step 14:

[1541] The server retrains the generative AI model based on difficult-to-achieve data, and after retraining, generates an optimal plan under new conditions.

[1542] Step 15:

[1543] The server sends the regenerated plan to the terminal.

[1544] Step 16:

[1545] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[1546] Example 1

[1547] 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."

[1548] In modern society, many people lead busy lives and often find it difficult to find enough time for health management. As a result, the risk of lifestyle-related diseases increases, making it difficult to maintain good health. Existing health management systems have issues such as difficulty in providing optimal diet and exercise plans tailored to each user's individual needs and inability to flexibly adapt to changes in the user's lifestyle. Furthermore, the mechanisms for evaluating the effectiveness of the generated plans and relearning them are inadequate, making it difficult to expect long-term health management effects.

[1549] 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.

[1550] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing the information in a database, means for generating an individually optimized meal plan and exercise plan using a generative AI model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for retraining the generative AI model based on the collected performance data and adjusting the plan, means for communicating the user's input information and performance data in JSON format, means for visually displaying the generated plan and daily report, means for the server to receive and parse the JSON format data and store it in a database, means for the generative model to be trained using TensorFlow or PyTorch, and means for the retrained generative model to generate and retransmit an optimal plan under new conditions. This not only enables the provision of an optimal health management plan tailored to the user's individual needs, but also enables the user to maintain and improve their health over the long term by evaluating and relearning the plan's effectiveness.

[1551] "Lifestyle information" refers to behavioral patterns and habits related to the user's daily life, specifically information such as how they work on weekdays, how they spend their holidays, and how often they exercise.

[1552] "Dietary information" refers to information including the user's daily food and drink preferences, disliked foods, allergy information, etc.

[1553] "Healthcare information" refers to specific data that indicates the user's health status, including health indicators such as heart rate, sleep time, and weight.

[1554] A "generative AI model" is an algorithm trained using machine learning that generates an optimal plan for each individual user based on their input information.

[1555] "JSON format" refers to JavaScript Object Notation (JSON), a format that represents data in a lightweight, structured way and is used for text-based data exchange.

[1556] A "daily report" is a document that reports on a day's health management activities and includes achievement levels, nutrient deficiencies, and recommended actions.

[1557] "Database" refers to a system for efficiently storing, managing, and accessing information, and refers to a place where a user's lifestyle information, dietary information, and healthcare information are stored.

[1558] "Parsing" refers to the process of interpreting and structurally analyzing received data.

[1559] "TensorFlow" is an open-source machine learning framework and software tool used to train neural networks.

[1560] "PyTorch" is an open-source library that makes it easy to train and run machine learning models, and refers to a software tool used to train neural networks, similar to TensorFlow.

[1561] "Server" refers to the computer system that receives data sent by users, processes and stores it, and runs the generative AI model.

[1562] "Terminal" refers to a device that allows users to input information and view generated plans and daily reports, such as a smartphone or tablet.

[1563] This invention relates to a system that proposes optimal health management using a generative AI model based on a user's lifestyle, dietary information, and healthcare information. This system is mainly composed of a server, a terminal, and a user, and its specific operation is as follows.

[1564] System Configuration

[1565] 1. Server

[1566] The server receives the lifestyle information, dietary information, and health care information sent by the user and stores it in a database.

[1567] A generative AI model is used to analyze the information received and generate a personalized meal and exercise plan.

[1568] User performance data is collected, a daily report is created based on this data, and the generative AI model is then retrained.

[1569] The servers are installed with machine learning frameworks such as TensorFlow and PyTorch, which are used to train and retrain generative AI models.

[1570] 2. Terminal

[1571] The terminal provides an interface for users to input lifestyle information, dietary information, and health care information through the application.

[1572] Visually display the generated plans and daily reports received from the server.

[1573] The data performed by the user is sent to the server.

[1574] 3. Users

[1575] Users use a dedicated health management app to input their lifestyle, dietary, and health care information into the device.

[1576] Follow the suggested meal and exercise plan and re-enter your results into the app.

[1577] Check your own health management achievements and suggestions for improvement through daily reports.

[1578] Input and analysis of information

[1579] The user launches the health management app and enters information about their individual lifestyle habits (e.g., weekday working habits and exercise frequency), dietary information (e.g., favorite foods, disliked foods), and health information (e.g., heart rate, sleep duration). After input, the device converts this information into JSON format and sends it to the server.

[1580] The server parses the received JSON data and stores it in a database. The newly added information is checked against existing data to check for consistency and gaps, providing reliable data to feed into the generative AI model.

[1581] Plan generation using generative AI models

[1582] The data stored on the server is input into a generative AI model and analyzed using specific algorithms (using TensorFlow or PyTorch). This model generates optimal meal and exercise plans based on each user's data. For example, "For a user who works at a desk, we recommend yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner."

[1583] Presenting a plan and collecting implementation data

[1584] The generated plan is sent from the server to the device, which then visually displays the plan. The user follows the plan, practices diet and exercise, and re-enters the results into the app. The device then sends this data back to the server in JSON format.

[1585] Daily report creation and generation AI model retraining

[1586] Based on the user's activity data, the server generates a daily report that includes the user's achievements, nutrient deficiencies, and recommended actions for the next day. For example, specific feedback is provided, such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet."

[1587] In addition, data on plans that could not be completed is collected, and the generative AI model is retrained based on this data. This retraining process generates a new, more realistic and feasible plan and sends it back to the device. For example, adjustments may be made, such as suggesting light indoor exercise instead of an evening walk.

[1588] Prompt Sentence Examples

[1589] "What's the best meal plan for someone who works a desk job during the week?"

[1590] "Please suggest a recommended exercise plan for someone with a heart rate of 70."

[1591] This allows users to continuously manage their health and obtain the health plan that is best suited to them through the system.

[1592] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1593] Step 1:

[1594] Entering information

[1595] The user launches the health management app and inputs lifestyle, diet, and health information. Specifically, the user enters "weekday work habits" (e.g., desk work), "weekend habits" (e.g., jogging), and "exercise frequency" (e.g., three times a week) into the interface. The input information is converted to JSON format, and the input amount is sent to the server in JSON format for subsequent processing.

[1596] Step 2:

[1597] Data transmission and storage

[1598] The device sends the lifestyle, diet, and health information entered to the server in JSON format. The server receives this information, parses the JSON data, analyzes the details of each item, and stores it in a database. Specifically, information such as how you work on weekdays, how you spend your days off, and how often you exercise is stored in the database.

[1599] Step 3:

[1600] Data analysis

[1601] The server performs an analysis based on the information stored in the database. This analysis includes checking the user's lifestyle information, consistency, and missing data. Each data item is collated to identify missing information or inconsistencies. The analysis results are used as input data for the generative AI model.

[1602] Step 4:

[1603] Plan generation using generative AI models

[1604] The server runs a generative AI model (trained using TensorFlow or PyTorch) based on the analyzed data. For example, if a user works at a desk, their favorite food is salad, and their heart rate is 70, the generative AI model will take these data as input and generate an optimal meal plan and exercise plan (e.g., yogurt and fruit for breakfast, vegetable soup for dinner). The output is the generated plan.

[1605] Step 5:

[1606] Presenting the plan

[1607] The server converts the generated plan back into JSON format and sends it to the device. The device visually displays the received generated plan. Specifically, the app screen displays "Today's meal plan" and "Today's exercise plan." For example, items such as "Yogurt and fruit for breakfast," "Chicken breast salad for lunch," and "Vegetable soup for dinner" are displayed.

[1608] Step 6:

[1609] Entering implementation data

[1610] The user puts the presented plan into practice and enters the results into the app. Specifically, they enter implementation data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects the implementation data entered by the user and sends it back to the server in JSON format.

[1611] Step 7:

[1612] Creating daily reports

[1613] The server receives and analyzes the user's exercise data. Based on this analysis, it generates a daily report on the user's exercise results for the day. The daily report includes the user's achievement level, any nutrient deficiencies, and recommended health behaviors for the next day. For example, the report may include specific feedback such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat foods rich in iron."

[1614] Step 8:

[1615] Retraining generative AI models

[1616] The server also collects data if the user is unable to complete the plan. For example, data such as "it was difficult to walk for 30 minutes" is input. This data is used to retrain the generative AI model. The generative AI model is retrained under new conditions and generates the optimal plan again. Specifically, a new suggestion such as "instead of walking in the evening, we suggest light indoor exercise" is generated and sent to the device.

[1617] (Application example 1)

[1618] 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."

[1619] While existing health management systems provide individually optimized meal and exercise plans, few of them offer integrated health content (e.g., blog posts, videos, recipes, etc.). Furthermore, they lacked systems that provide feedback on the effectiveness of the plans based on user data and enable continuous improvement by retraining generative models. This limited the sustainability and effectiveness of users' health management.

[1620] 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.

[1621] In this invention, the server includes means for inputting a user's lifestyle information, dietary information, and health care information, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan and exercise plan using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's implementation data and generating a daily report, means for relearning the generative model based on the collected implementation data and adjusting the plan, means for delivering the generated plan and related health-related content to the user, and means for collecting implementation data based on the generated plan and providing feedback. This allows the user to receive not only an individually optimized health management plan but also useful health information related to it, enabling sustainable and effective health management.

[1622] "Lifestyle information" refers to information about the user's behavioral patterns and habits in their daily lives, such as how they work, when they wake up and go to bed, and how often they exercise.

[1623] "Dietary information" refers to information about the user's eating habits, such as favorite foods, disliked foods, and the contents of daily meals.

[1624] "Healthcare information" refers to information about the user's health condition, such as data about heart rate, weight, height, and sleep duration.

[1625] A "database" is a storage device that stores collected lifestyle, dietary, and healthcare information and makes it accessible as needed.

[1626] A "generative model" is a model that uses AI technology to generate optimal meal and exercise plans based on a user's lifestyle, dietary, and healthcare information.

[1627] A "meal plan" is a plan that suggests meal plans suitable for the user based on a generative model.

[1628] An "exercise plan" is a plan that suggests exercise content suitable for the user based on a generative model.

[1629] A "daily report" is a report that includes an evaluation of the activities carried out that day and suggestions for improvement based on the user's implementation data.

[1630] "Retraining" refers to updating a generative model to improve its accuracy based on newly collected data.

[1631] "Related health content" is additional information to help users manage their health, such as health blog posts, videos, recipes, etc.

[1632] "Feedback" refers to the process of providing evaluations and advice based on the data the user has put into practice.

[1633] This invention relates to a system that utilizes a generative AI model based on a user's lifestyle, diet, and health information to propose optimal health management. The system has the function of allowing users to input information about their lifestyle and health status, and based on that information, provides personalized optimal meal and exercise plans. It also delivers related health content and receives feedback on implementation data, allowing the generative model to retrain and improve the quality of the plans.

[1634] System Configuration

[1635] The server receives lifestyle, dietary, and health information sent by the user and stores it in a database. It analyzes the stored information and uses a generative AI model to generate an optimal meal plan and exercise plan for each individual. It also collects the user's exercise data and creates a daily report. It then retrains the generative model based on the exercise data.

[1636] The terminal provides an interface for users to input lifestyle, diet, and health information, displays the generated plan and daily report received from the server, and transmits the user's implementation data to the server.

[1637] Users enter their lifestyle, dietary, and health information into the device, follow the suggested meal and exercise plans, and then enter the results into the device to check their health management progress and improvement suggestions through daily reports.

[1638] Detailed explanation of operation

[1639] The server is built using Python and provides a REST API using frameworks such as Django or Flask, data is processed in JSON format, databases are AWS DynamoDB or Firebase Firestore, and generative AI models are built using AI frameworks such as TensorFlow and PyTorch.

[1640] As a specific example, the following scenario can be considered.

[1641] The user opens the smartphone app "My Health Guide" and enters information about their lifestyle, diet, and health care. For example, they might enter data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. They might also provide information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. This information is sent to the server in JSON format.

[1642] The server analyzes the received data and stores it in a database. It then runs a generative AI model to generate optimal meal and exercise plans for each user. The generated plan is again sent to the smartphone in JSON format and displayed on the app's UI. For example, "Today's meal plan" might show "yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner." Additionally, "Today's exercise plan" might suggest "15 minutes of stretching every morning and 30 minutes of walking in the evening."

[1643] When a user practices diet and exercise and enters the results into the application, the device collects this data and sends it to the server. The server analyzes the data and generates a daily report. The daily report includes the level of achievement, nutrient deficiencies, and recommended actions. For example, it might say, "Today's exercise was completed as planned, but your iron intake is insufficient. Try eating iron-rich foods tomorrow."

[1644] Furthermore, if the user is unable to complete the proposed plan, that data is also collected, and the server retrains the generative AI model based on the difficult-to-achieve data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device. For example, it may suggest something like, "Instead of walking in the evening, we suggest light indoor exercise."

[1645] Example prompt sentence:

[1646] You're a busy desk worker with a lifestyle where you only exercise three times a week. Your favorite food is salad and you hate fried food. Your heart rate is 70 and you get seven hours of sleep each night. Use this information to generate a meal and exercise plan that's perfect for you.

[1647] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1648] Step 1:

[1649] The user launches the smartphone app and inputs lifestyle, diet, and health information. Specifically, the user enters information such as their weekday work style (desk work), weekend habits (jogging), how often they exercise three times a week, their favorite food (salad), their least favorite food (fried food), their heart rate (70), and the amount of sleep they get (7 hours). This information is collected through the device's interface. Input formats include text fields and selection lists.

[1650] input:

[1651] Lifestyle information

[1652] Meal Information

[1653] Healthcare Information

[1654] output:

[1655] User information data in JSON format

[1656] Step 2:

[1657] The device converts the collected lifestyle, dietary, and health information into JSON format and sends it to the server. The HTTPS protocol is used for communication, ensuring secure data transfer. The server receives the request, analyzes the data, and stores it in a database. Specifically, a web framework such as Django or Flask is used.

[1658] input:

[1659] User information data in JSON format

[1660] output:

[1661] User information stored in a server-side database

[1662] Step 3:

[1663] The server runs a generative AI model based on user information stored in a database. The generative AI model receives the user's lifestyle, eating habits, and health care information as input and generates an optimal meal and exercise plan for each individual. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. It also generates an exercise plan that includes 15 minutes of stretching every morning and 30 minutes of walking in the evening.

[1664] input:

[1665] User information stored in a database

[1666] output:

[1667] Personalized meal and exercise plans

[1668] Step 4:

[1669] The generated meal and exercise plans are sent to the device in JSON format. The device visualizes the received plans and presents them to the user. Specifically, the app's UI displays "Today's meal plan" as "Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread." Additionally, "Today's exercise plan" displays "Every morning: 15 minutes of stretching, Evening: 30 minutes of walking."

[1670] input:

[1671] Meal and exercise plans in JSON format

[1672] output:

[1673] Plans displayed in the app UI

[1674] Step 5:

[1675] The user puts the suggested diet and exercise into practice and enters the results into the application. For example, they enter data such as "I ate yogurt for breakfast today" or "I walked for 30 minutes in the evening." The device collects this data and sends it to the server in JSON format.

[1676] input:

[1677] Dietary and exercise data

[1678] output:

[1679] JSON format implementation data

[1680] Step 6:

[1681] The server analyzes the received data and generates a daily report. The daily report includes the user's achievement level, nutrient deficiencies, and recommended actions. For example, it may include, "Today's exercise was completed as planned, but your iron intake is insufficient. Tomorrow, you should eat an iron-rich diet." The generated report is sent to the device in JSON format, and the device displays it on the app's UI.

[1682] input:

[1683] JSON format implementation data

[1684] output:

[1685] JSON format health management daily report

[1686] Step 7:

[1687] If the user is unable to complete the proposed plan, that data is also collected in JSON format and sent to the server. The server then retrains the generative AI model based on the difficult-to-complete data. The generative AI model then generates an optimal plan under the new conditions and sends it back to the device in JSON format. For example, the system may suggest something like, "Instead of walking at night, we suggest light indoor exercise."

[1688] input:

[1689] Hard to achieve data in JSON format

[1690] output:

[1691] New plans from retrained generative AI models

[1692] 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.

[1693] The present invention relates to a system that proposes optimal health management based on a user's emotions by combining an emotion engine with the user's lifestyle, dietary information, and healthcare information. The system is configured as follows, and its specific operation is shown below.

[1694] System Configuration

[1695] 1. Server

[1696] The server receives lifestyle information, dietary information, health care information, and emotion data sent by the user and stores them in a database.

[1697] Generative AI models are used to analyze this information and emotional data to generate personalized meal plans, exercise plans, and activities to improve mental health.

[1698] We collect user implementation data, create daily reports, and retrain the generative model based on the implementation data.

[1699] 2. Terminal

[1700] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data.

[1701] Display generated plans and daily reports received from the server, as well as mental health improvement activities.

[1702] The user's implementation data is sent to the server.

[1703] 3. Users

[1704] Users input their lifestyle, diet, and health information, as well as emotional data, into the device, which is collected from facial expressions, voice, and text input.

[1705] Follow the suggested meal plans, exercise plans, and mental health activities and enter the results into your device.

[1706] Check your own health management achievements and suggestions for improvement through daily reports.

[1707] Program processing

[1708] Entering information

[1709] A user launches a health management app and inputs lifestyle, diet, health, and emotional data. For example, the user enters data such as desk work as their weekday work style, jogging as their weekend activity, and exercising three times a week. The user also provides information such as their favorite food being salad, their least favorite food being fried food, their heart rate being 70, and their sleep time being 7 hours. Emotional data is collected based on the user's facial expression analysis, tone of voice, and text input.

[1710] The device collects this information and converts it into JSON format, preparing the data for later transmission.

[1711] Data analysis and storage

[1712] The server parses the received data, extracts and validates the necessary fields, and then stores them in the database.

[1713] Plan generation using generative AI models

[1714] The server runs a generative AI model based on the stored data and emotional data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotional data as input, and generates individually optimized meal plans, exercise plans, and activities to improve mental health. For example, for a user who works at a desk, it suggests yogurt and fruit for breakfast, chicken breast salad for lunch, and vegetable soup and whole wheat bread for dinner. The exercise plan includes 15 minutes of stretching every morning and 30 minutes of walking in the evening. Furthermore, based on the emotional data, it also suggests meditation for relaxation and exercises to relieve stress.

[1715] Plan presentation

[1716] The server sends the generated plan to the terminal in JSON format.

[1717] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread," while "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." Furthermore, "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[1718] Daily report creation

[1719] The user performs dietary, exercise, and relaxation activities and enters the results into the application. For example, they can enter "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[1720] The device collects these implementation data and sends them to the server in JSON format.

[1721] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[1722] Relearn

[1723] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[1724] The server retrains the generative AI model based on difficult-to-achieve data and emotional data. After retraining, it generates an optimal plan under the new conditions.

[1725] The server sends the regenerated plan to the terminal.

[1726] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[1727] Specific examples

[1728] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[1729] The server uses an AI model to generate a plan like the one below and displays it on the device.

[1730] Meal Plan:

[1731] Breakfast: Yogurt and fruit

[1732] Lunch: Chicken breast salad

[1733] Dinner: Vegetable soup and whole wheat bread

[1734] Exercise plan:

[1735] Every morning: 15 minutes of stretching

[1736] Evening: 30-minute walk

[1737] Mental Health Improvement Plan:

[1738] Meditation: 10 minutes

[1739] The next morning, the terminal presents the user with the following daily health management report:

[1740] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[1741] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[1742] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[1743] The processing flow will be explained below.

[1744] Step 1:

[1745] The user launches the health management app and inputs lifestyle information, dietary information, health information, and emotional data. Specifically, the user inputs data such as "I do desk work on weekdays," "I jog on weekends," "I exercise three times a week," "My favorite food is salad," "My least favorite food is fried food," "My heart rate is 70," and "I get seven hours of sleep." Emotional data is collected based on facial expression analysis, tone of voice, and text input.

[1746] Step 2:

[1747] The device collects the information provided by the user and converts it into JSON format, preparing this data for later transmission.

[1748] Step 3:

[1749] The device sends the collected information in JSON format to the server using a secure communication protocol to ensure data integrity and confidentiality.

[1750] Step 4:

[1751] The server analyzes the received data, extracts and validates the necessary fields, and stores them in the database. At the same time, emotion data is also stored in the database.

[1752] Step 5:

[1753] The server runs a generative AI model based on the stored information and emotional data. The generative AI model receives lifestyle, diet, health, and emotional data as inputs and generates an individually optimized meal plan, exercise plan, and activities to improve mental health.

[1754] Step 6:

[1755] The server sends the generated plan to the terminal in JSON format.

[1756] Step 7:

[1757] The device displays the received plan on the user interface. For example, "Today's meal plan" may be displayed as "Breakfast: Yogurt and fruit," "Lunch: Chicken breast salad," and "Dinner: Vegetable soup and whole wheat bread." "Today's exercise plan" may be displayed as "Every morning: 15 minutes of stretching," and "Evening: 30 minutes of walking." "Today's relaxation plan" may be displayed as "10 minutes of meditation."

[1758] Step 8:

[1759] Users follow the plan and enter their results into the app every day, for example, "I ate yogurt for breakfast," "I took a 30-minute walk in the evening," or "I meditated for 10 minutes."

[1760] Step 9:

[1761] The terminal collects the implementation data entered by the user and sends it to the server in JSON format.

[1762] Step 10:

[1763] The server analyzes the data and generates a daily report that includes progress, nutrient deficiencies, and recommended actions. For example, "Today's exercise was completed as planned, but iron intake is insufficient. Eat more iron-rich foods tomorrow."

[1764] Step 11:

[1765] The server transmits the generated daily report to the terminal.

[1766] Step 12:

[1767] The terminal displays the daily report on the user interface, and the user can check the progress of their health management and suggestions for improvement.

[1768] Step 13:

[1769] If the user is unable to complete the proposed plan, that data is also collected, for example, by entering "I had difficulty walking for 30 minutes."

[1770] Step 14:

[1771] The server retrains the generative AI model based on difficult-to-achieve data and emotional data, and then generates an optimal plan under the new conditions.

[1772] Step 15:

[1773] The server sends the regenerated plan to the terminal.

[1774] Step 16:

[1775] The device displays the regenerated plan on the user interface and suggests ways to achieve it, such as "Instead of walking in the evening, we suggest light exercise indoors."

[1776] Specific examples

[1777] Let's say the user has a desk job on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. He jogs on weekends, but exercises little every day. His favorite food is salad, and he hates fried food. His heart rate is 70, and he gets 7 hours of sleep every night. Furthermore, the emotion engine has detected that the user has recently been prone to stress.

[1778] The server uses an AI model to generate a plan like the one below and displays it on the device.

[1779] Meal Plan:

[1780] Breakfast: Yogurt and fruit

[1781] Lunch: Chicken breast salad

[1782] Dinner: Vegetable soup and whole wheat bread

[1783] Exercise plan:

[1784] Every morning: 15 minutes of stretching

[1785] Evening: 30-minute walk

[1786] Mental Health Improvement Plan:

[1787] Meditation: 10 minutes

[1788] The next morning, the terminal presents the user with the following daily health management report:

[1789] You exercised as planned today, but your iron intake is low. Eat an iron-rich diet tomorrow.

[1790] Although the meditation was only for 5 minutes, you can expect results if you continue. Next time, aim for 10 minutes.

[1791] This allows users to manage their health in an individually optimized way, enabling them to maintain and improve their health in a sustainable manner.

[1792] Example 2

[1793] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1794] Conventional health management systems generally propose plans based on a user's lifestyle, diet, and healthcare information, but do not take into account factors such as emotional fluctuations and mental stress. Furthermore, these systems do not adequately analyze individual data or retrain models, making it difficult to provide users with optimal health management plans.

[1795] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1796] In this invention, the server includes means for inputting lifestyle information, dietary information, and health care information of a user, means for analyzing the input lifestyle information, dietary information, and health care information and storing it in a database, means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative model based on the stored information, means for presenting the generated plan to the user, means for collecting the user's performance data and generating a daily report, means for relearning the generative model based on the collected performance data and adjusting the plan, means for collecting and analyzing emotional data, and means for adjusting the generated plan based on the emotional data, thereby enabling comprehensive health management including the user's emotional fluctuations.

[1797] "Lifestyle information" refers to information about the user's daily life, including how they work on weekdays, how they spend their holidays, how often they exercise, and so on.

[1798] "Dietary information" refers to information about the user's daily diet, including favorite foods, disliked foods, and frequency of intake.

[1799] "Healthcare information" refers to information about the user's health condition, including biometric data such as heart rate, sleep time, and blood pressure, as well as self-assessment of health condition.

[1800] "Emotional data" refers to information about a user's emotional state, including data obtained from facial expression analysis, tone of voice, text input, and the like.

[1801] A "generative model" refers to an algorithm or AI model that analyzes input data and generates the optimal plan.

[1802] "Meal Plan" means the specific dietary recommendations made to maintain and improve the User's health.

[1803] An "exercise plan" refers to specific exercise content proposed to maintain and improve the user's health.

[1804] "Mental health activities" refers to relaxation and stress relief activities suggested to improve the user's mental health.

[1805] "Implementation data" includes data showing the results of the diet, exercise, and activities that the user actually undertook.

[1806] A "daily report" is a report that compiles the results of actions taken by a user and shows the level of achievement and areas for improvement.

[1807] "Relearning" refers to the process of retraining the generative model based on collected implementation and emotion data to generate more accurate plans.

[1808] This invention is a system that collects lifestyle information, dietary information, health care information, and emotional data from users, and provides individually optimized health management plans based on the collected data. The main components of this system include a server, a terminal, and a user.

[1809] server

[1810] The server receives lifestyle, diet, health, and emotional data sent by users and stores it in a database. The server analyzes this information using a generative model (e.g., OpenAI's GPT-3) to generate optimal meal plans, exercise plans, and activities for improving mental health. It also creates daily reports based on the user's implementation data and retrains the generative model to continuously improve the plans.

[1811] Terminal

[1812] The terminal provides an interface for users to input lifestyle information, dietary information, health care information, and emotional data. The terminal displays the generated plan and daily report received from the server, collects the user's implementation data, and sends it to the server.

[1813] User

[1814] Users input their lifestyle, dietary, and health information, as well as emotional data, into the device. Emotional data is collected from facial expression analysis, tone of voice, and text input. Users also execute the proposed meal plan, exercise plan, and mental health improvement activities and input the results into the device, contributing to the system's plan generation and re-learning.

[1815] Specific examples

[1816] For example, suppose a user works at a desk on weekdays, wakes up at 7am every morning, and works from 8am to 5pm. They jog on their days off, but do not exercise often on a daily basis. Their favorite food is salad, and they dislike fried food. Their heart rate is 70, and they get 7 hours of sleep every night. Emotional data collected recently indicates that they tend to feel stressed.

[1817] The server runs a generative AI model based on this information and generates a plan like the one below.

[1818] Meal Plan:

[1819] Breakfast: Yogurt and fruit

[1820] Lunch: Chicken breast salad

[1821] Dinner: Vegetable soup and whole wheat bread

[1822] Exercise plan:

[1823] Every morning: 15 minutes of stretching

[1824] Evening: 30-minute walk

[1825] Mental Health Improvement Plan:

[1826] Meditation: 10 minutes

[1827] The next morning, the terminal presents the user with the following daily health management report:

[1828] "You exercised as planned today, but your iron intake is low. Eat more iron-rich foods tomorrow."

[1829] "I only meditated for five minutes, but I think it will be effective if I continue. Next time, I'll aim for 10 minutes."

[1830] Prompt Sentence Examples

[1831] "I currently have a desk job during the weekdays, waking up at 7am every day and working from 8am until 5pm. I go jogging on my days off. I've been feeling stressed a lot lately. Could you please suggest the best meal plan, exercise plan, and activities to improve my mental health?"

[1832] This system enables users to manage their health in an individually optimized way, enabling them to maintain and improve their health continuously. It also analyzes users' emotional data in real time and provides appropriate healthcare suggestions based on their emotional fluctuations, enabling them to live a balanced life both physically and mentally.

[1833] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1834] Step 1:

[1835] The user starts the health management app and inputs lifestyle information, dietary information, health information, and emotional data. The personal information is input in the following format. For example,

[1836] Lifestyle information: "Desk work on weekdays, jog on weekends, exercise three times a week"

[1837] Dietary information: "My favorite food is salad, and my least favorite food is fried food."

[1838] Health information: "Heart rate is 70, sleep time is 7 hours"

[1839] Emotional data: "I feel stressed easily these days"

[1840] The input information is sent to the terminal. The terminal converts this information into JSON format and prepares it for sending to the server. The input to the server includes the user data in JSON format.

[1841] Step 2:

[1842] The device converts the lifestyle, diet, health, and emotion data entered by the user into JSON format. The converted data is sent to the server. Specifically, the device organizes the data collected from the user interface and packages it as a JSON string. The output includes the user data in JSON format.

[1843] Step 3:

[1844] The server parses the JSON formatted user data received from the device and extracts the required fields. This parsing includes checking the data for consistency, eliminating duplicate data, etc. The input contains the JSON formatted user data, and the output is the extracted user data that is stored in the database.

[1845] Step 4:

[1846] The server runs a generative AI model (e.g., OpenAI GPT-3) based on the stored user data and emotion data. The generative AI model receives lifestyle information, dietary information, healthcare information, and emotion data as input, and generates optimal meal plans, exercise plans, and activities to improve mental health. Specifically, the model provides input data, performs calculations, and obtains plan data as output. The input includes the user's integrated data, and the output is plan data in JSON format.

[1847] Step 5:

[1848] The server sends the generated plan data to the terminal in JSON format. Specifically, it converts the plan data obtained by the generative AI model into JSON format and performs communication processing to send it to the terminal. The output includes the plan data in JSON format.

[1849] Step 6:

[1850] The device displays the received plan on the user interface. Specifically, it parses the plan data in JSON format and renders the UI to display it in a user-friendly format. The displayed information includes "Today's meal plan: Breakfast: Yogurt and fruit, Lunch: Chicken breast salad, Dinner: Vegetable soup and whole wheat bread" and "Today's exercise plan: 15 minutes of stretching every morning, 30 minutes of walking in the evening." The output is displayed on the user interface.

[1851] Step 7:

[1852] The user puts the proposed meal plan, exercise plan, and activities to improve mental health into practice and enters the results into the application. For example, they might enter "I ate yogurt for breakfast," "I walked for 30 minutes in the evening," or "I meditated for 10 minutes." The entered information is sent to the device, which then converts it back into JSON format and sends it to the server. The input contains the user's activity data, and the output is JSON-formatted activity data.

[1853] Step 8:

[1854] The server analyzes the received behavior data and generates a daily report. This analysis includes validity checks on the behavior data and extraction of missing elements (e.g., nutrients, exercise). The daily report includes achievement, missing nutrients, and recommended actions. The input includes the behavior data in JSON format, and the output is the generated daily report.

[1855] Step 9:

[1856] The device displays the generated daily report on the user interface. Specifically, it analyzes the JSON format daily report data and processes it to display it on the user interface. For example, it displays a message such as, "Today's exercise was completed as planned, but your iron intake is insufficient. Eat an iron-rich diet tomorrow." The output is the daily report displayed on the user interface.

[1857] Step 10:

[1858] The server retrains the generative AI model based on the collected performance data and emotion data. Specifically, it adds the newly collected data to the model's training set and executes a process to readjust the model's parameters. After retraining, it generates an optimal plan under the new conditions and sends it to the device. Specifically, it includes evaluating the model's performance and adding training data as needed. The input includes performance data and emotion data, and the output is regenerated plan data.

[1859] (Application example 2)

[1860] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1861] Current food delivery services have the problem of being unable to suggest and deliver optimal meals based on a user's individual health and emotional state. Furthermore, to effectively support users' health maintenance and emotional stability, it is desirable to integrate and analyze lifestyle habits, dietary content, healthcare information, and emotional data, and provide optimal plans using a generative AI model. However, no system exists that can effectively achieve this.

[1862] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for inputting the user's lifestyle information, dietary information, health care information, and emotional data; means for analyzing the input lifestyle information, dietary information, health care information, and emotional data and storing them in a database; means for generating an individually optimized meal plan, exercise plan, and activity for improving mental health using a generative AI model based on the stored information and emotional data; means for presenting the generated plan and activity to the user; means for collecting the user's implementation data and generating a daily report; and means for retraining the generative AI model based on the collected implementation data and adjusting the plan and activity. This makes it possible to propose a meal plan optimized for the user's health and emotional state and to deliver the plan directly via food delivery, thereby supporting the user's health maintenance and emotional stability.

[1863] "Lifestyle information" is information about the user's daily activities and habits, including, for example, how they work, how they spend their holidays, and how often they exercise.

[1864] "Dietary information" refers to information about a user's eating preferences and habits, including, for example, favorite foods, disliked foods, meal frequency...

Claims

1. A means for inputting lifestyle information, dietary information, and health care information of a user; A means for analyzing the input lifestyle information, dietary information, and health care information and storing the information in a database; A means for generating an optimal individualized meal plan and exercise plan using a generative model based on the stored information; A means for presenting the generated plan to a user; means for collecting user performance data and generating daily reports; The system includes a means for retraining the generative model based on collected implementation data and adjusting the plan.

2. 2. The system according to claim 1, wherein the lifestyle information includes how the user works on weekdays, how the user spends their days off, and how often the user exercises.

3. The system according to claim 1 , wherein the dietary information includes favorite foods and disliked foods.

4. 10. The system of claim 1, wherein the health care information includes heart rate, sleep data, and daily calorie intake.

5. 10. The system of claim 1, further comprising means for notifying a user of a daily report containing the generated individual plan.

6. 2. The system according to claim 1, further comprising means for presenting improvement suggestions for the plan generated based on the implementation status of the user.

7. 2. The system according to claim 1, further comprising means for optimizing subsequent plans by incorporating the user's implementation data into the generation model and re-learning it.

Images