system

Abstract

Provide a system. A method for collecting health data from a user; means for pre-processing the health data transmitted to the server; means for analyzing the pre-processed data to generate an individualized health plan; means for providing the generated health plan to the user; a means of collecting progress data and providing feedback; A system including:

Description

[Technical Field]

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

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

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

[0004] In modern society, despite growing awareness of individual health management, there is a lack of personalized health advice. Many people are unable to accurately grasp their own health status and are often unsure of what lifestyle habits they should adopt. Furthermore, with the vast amount of health information available, it is difficult to determine what to trust. There is a need for a system that can solve these issues and enable individual users to effectively manage, maintain, and improve their health. [Means for solving the problem]

[0005] This invention provides a means for collecting health data from a user and a means for preprocessing the health data sent to a server. It also includes a means for analyzing the preprocessed data and generating an individual health plan. It also includes a means for providing the generated health plan to the user and a means for collecting progress data and providing feedback, thereby realizing a system that allows users to continuously manage their health. This allows users to accurately understand their own health status and take action based on appropriate advice.

[0006] "User" refers to an individual who uses the System, provides Health Data, and receives a Health Plan.

[0007] "Health data" refers to data related to the user's daily life, and specifically includes information about diet, exercise, and sleep.

[0008] "Means of collection" refers to the interface or device that allows the user to input health data, as well as any associated software or hardware.

[0009] "Server" refers to the central computer system that receives, processes, analyzes and stores health data submitted by users.

[0010] "Preprocessing means" refers to methods and algorithms for converting received health data into a format that is easy to analyze, and for filling in missing values ​​and standardizing the data.

[0011] "Means for analyzing" refers to the methods and techniques for analyzing pre-processed data using a generative AI model to assess the user's health status.

[0012] A "health plan" is a specific action plan generated based on the user's health status, and includes recommendations for diet, exercise, and sleep.

[0013] "Means for providing" refers to an interface or application for informing the user of the generated health plan and presenting appropriate advice and instructions.

[0014] "Progress Data" refers to data regarding the actions a user takes in accordance with a health plan and the results of those actions.

[0015] "Means for providing feedback" refers to a method or system for analyzing progress data and providing ongoing support and motivation to the user.

[0016] "Generative AI model" refers to artificial intelligence technology that analyzes health conditions and generates optimal health plans based on collected health data. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

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

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[0038] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[0039] Program processing (natural language explanation)

[0040] Data collection

[0041] 1. User: Enters daily meal information through a smartphone application, providing detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[0042] 2. Device: The application stores the entered data and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[0043] 3. Terminal: Consolidates all data into one package and sends it to the server.

[0044] Data Preprocessing

[0045] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data.

[0046] 2. Server: Standardizes the data format and converts it into a form suitable for analysis.

[0047] Data analysis

[0048] 1. Server: Analyzes the user's health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc.

[0049] 2. Server: Evaluates calories burned and exercise intensity based on exercise data.

[0050] 3. Server: Based on sleep data, evaluates sleep duration and quality and assesses overall health.

[0051] Health plan generation

[0052] 1. Server: Based on the results of data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it generates a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[0053] 2. Server: Sends the generated health plan to the terminal.

[0054] Feedback and Support

[0055] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[0056] 2. User: Carries out the actions according to the plan and enters progress into the application.

[0057] 3. Terminal: Collects new data from the user and sends it to the server.

[0058] 4. Server: Analyzes new data and assesses progress toward goals and areas for improvement.

[0059] 5. Server: Generates feedback and sends it to the device. For example, it provides feedback to the user such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[0060] Specific examples

[0061] Example 1: User trying to lose weight

[0062] 1. User: Opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[0063] 2. Terminal: Organizes the entered data and sends it to the server.

[0064] 3. Server: Based on the received data, calculates the total daily calorie intake and calories burned and performs analysis based on the user's weight loss goal.

[0065] 4. Server: Based on the analysis results, a specific health plan is generated, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed by 10 p.m.", and sent to the device.

[0066] 5. Terminal: Notifies the user and displays specific instructions for action.

[0067] 6. User: Follows the plan and enters progress into the app.

[0068] 7. Terminal: Organizes new data and sends it to the server.

[0069] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[0070] In this way, users can get the best health plan based on real data and get continuous improvement and support.

[0071] The processing flow will be explained below.

[0072] Step 1:

[0073] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, enters "I had toast and scrambled eggs for breakfast." Also, enters data for lunch and dinner in the same way.

[0074] Step 2:

[0075] Device: Stores the entered food data and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[0076] Step 3:

[0077] Device: All collected data (diet, exercise, sleep) is organized into a single data package and sent to the server.

[0078] Step 4:

[0079] Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[0080] Step 5:

[0081] Server: Analyzes pre-processed health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance.

[0082] Step 6:

[0083] Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined to analyze overall health status.

[0084] Step 7:

[0085] Server: Based on the analysis results, a customized health plan is generated for each user. For example, a specific health plan such as "30 minutes of aerobic exercise three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated.

[0086] Step 8:

[0087] Server: Sends the generated health plan to the device.

[0088] Step 9:

[0089] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0090] Step 10:

[0091] User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[0092] Step 11:

[0093] Device: Organizes newly collected progress data and sends it to the server.

[0094] Step 12:

[0095] Server: Analyzes new progress data and evaluates goal achievement and areas for improvement, generating feedback such as "You're on track to achieve your goal" or "You could be even more effective if you cut back on the calories at dinner."

[0096] Step 13:

[0097] Server: Sends feedback to the device.

[0098] Step 14:

[0099] Device: Provides feedback to the user, suggests next steps, and provides advice to help maintain motivation.

[0100] Through these steps, users can continuously manage their health status and act in accordance with an optimal health plan.

[0101] Example 1

[0102] 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."

[0103] Health management is an important issue in modern society. However, many people find it difficult to properly collect and analyze their own health data and develop effective health plans. Furthermore, many health management systems on the market lack the ability to comprehensively analyze individual data and provide feedback, making it difficult for users to achieve optimal health management. This invention aims to provide a system that collects and analyzes individual users' health data and provides customized health plans and continuous feedback.

[0104] 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.

[0105] In this invention, the server includes a means for collecting health data from users, a means for pre-processing the health data transmitted to the server, and a means for analyzing the pre-processed data to generate an individual health plan, thereby enabling the health data of each individual user to be appropriately collected and analyzed and a customized health plan to be provided.

[0106] "Health data" refers to information necessary for assessing a user's health status, such as diet, exercise, and sleep information.

[0107] "Server" refers to the central management system that processes data received from users, generates health plans, and provides feedback.

[0108] "Preprocessing" refers to the data preparation work required before data analysis, such as imputing missing values ​​and standardizing the format of received health data.

[0109] "Health Plan" refers to a plan that includes specific diet, exercise, and sleep instructions customized based on the user's health status.

[0110] "Feedback" refers to evaluations and advice provided based on a user's actions and progress.

[0111] "Generative AI models" refer to artificial intelligence algorithms and models used to analyze data and generate health plans.

[0112] "Tracking" refers to recording a user's activities and status and collecting data on an ongoing basis.

[0113] "Data Package" means all health data collected from a user in one format.

[0114] The system of this invention is an AI system that collects and analyzes individual health data of users and provides optimal health plans. This system is capable of evaluating individual health conditions based on the user's diet, exercise, and sleep data, generating customized health plans, and providing feedback.

[0115] Hardware and Software

[0116] The system is implemented using the following hardware and software:

[0117] Smartphone (user device)

[0118] Wearable devices (e.g., Fitbit, Apple Watch)

[0119] Server (cloud server)

[0120] Smartphone application (health management app)

[0121] Python libraries for running generative AI models (e.g., Tensorflow, PyTorch)

[0122] Program Implementation

[0123] The program for this system is executed as follows:

[0124] Data collection

[0125] Users input their daily meal plans through a smartphone application. For example, they can provide detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." Furthermore, the device connects to a wearable device and automatically synchronizes exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality).

[0126] All data is packaged in JSON format and sent securely to the server over HTTPS. Specifically, the device makes an API request and sends the data to the server via a POST request.

[0127] Data Preprocessing

[0128] The server analyzes the received data package and performs preprocessing on the data. For example, if there are missing values, it fills them in using statistical methods or past data. It also standardizes the data format and stores it in a unified format in a table in the database. Specifically, it parses the data and executes a script to convert it into a unified format (e.g., unifying the timestamp format).

[0129] Data analysis

[0130] The server uses the generative AI model to analyze the user's health data. For example, it categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc. It also evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. This allows for an assessment of the user's overall health.

[0131] Health plan generation

[0132] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[0133] Feedback and Support

[0134] The device notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Plan to go to the gym tomorrow." The user carries out the actions according to the plan and enters their progress into the application. The new data is organized and sent to the server, which analyzes it, evaluates the progress of goal achievement and areas for improvement, and generates feedback and sends it to the device.

[0135] Specific examples

[0136] Example 1: User trying to lose weight

[0137] 1. A user opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[0138] 2. The terminal organizes the entered data and sends it to the server.

[0139] 3. Based on the received data, the server calculates the total daily calorie intake and calories burned and analyzes it based on the user's weight loss goal.

[0140] 4. Based on the analysis results, the server generates a specific health plan such as "walk for 30 minutes three times a week," "eat no more than 1,500 calories a day," and "go to bed by 10 p.m." and sends it to the device.

[0141] 5. The device notifies the user and displays specific instructions for action.

[0142] 6. The user acts according to the plan and enters their progress into the app.

[0143] 7. The device organizes the new data and sends it to the server.

[0144] 8. The server analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[0145] Using this system, users can obtain the optimal health plan based on their individual health condition and receive ongoing support and feedback.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] Step 1:

[0148] Data collection

[0149] Users manually enter their daily dietary information using a smartphone application, providing detailed dietary information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner."

[0150] Input: User's meal information (text format).

[0151] How it works: The user enters specific meal details into the app's input form.

[0152] Output: The entered meal information is saved in the app's database.

[0153] The device works with wearable devices (e.g., Fitbit, Apple Watch) and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality).

[0154] Input: Exercise and sleep data from wearable devices.

[0155] How it works: The app uses the wearable device API to retrieve data.

[0156] Output: The acquired data is saved in the app's database.

[0157] The device then compiles all the data into a single package in JSON format and sends it securely to the server using HTTPS.

[0158] Input: Integrated health data (diet, exercise, sleep) converted to JSON format.

[0159] How it works: The device makes an API request and sends data to the server in a POST request.

[0160] Output: JSON formatted data is sent to the server.

[0161] Step 2:

[0162] Data Preprocessing

[0163] The server analyzes the received data package and performs preprocessing on the data, for example, imputing missing values ​​using statistical methods or past data.

[0164] Input: Health data package in JSON format sent to the server.

[0165] How it works: A server-side script validates the data (e.g., checks for blanks) and imputes missing values.

[0166] Output: Data with missing values ​​imputed and passing validation.

[0167] The server standardizes the data format and stores it in a uniform format in tables within the database.

[0168] Input: Health data that has passed validation.

[0169] What it does: Runs a script that parses the data and converts it to a unified format (e.g. unified timestamp format).

[0170] Output: The data converted into a unified format is saved in the database.

[0171] Step 3:

[0172] Data analysis

[0173] The server analyzes the user's health data using a generative AI model, inputting dietary data into the model, classifying it by nutrient, and evaluating calorie intake, protein, fat, carbohydrates, etc.

[0174] Input: Health data converted into a unified format.

[0175] How it works: Food data is input into the AI ​​model, which then classifies and evaluates each nutrient.

[0176] Output: Classification and evaluation results for each nutrient.

[0177] The server evaluates exercise intensity and calories burned based on the exercise data.

[0178] Input: Motion data converted into a unified format.

[0179] Operation: Obtains exercise data from the database and calculates calories burned using calculation logic.

[0180] Output: Evaluation results of exercise intensity and calories burned.

[0181] The server evaluates sleep duration and quality based on sleep data, and assesses overall health.

[0182] Input: Sleep data converted into a unified format.

[0183] How it works: Sleep data is fed into the AI ​​model, and the output is interpreted using evaluation logic.

[0184] Output: Sleep duration and quality assessment, overall health status.

[0185] Step 4:

[0186] Health plan generation

[0187] Based on the data analysis results, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it provides a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[0188] Input: Data analysis results.

[0189] What it does: Analyzes the output of the AI ​​model and runs a script to set specific values ​​(e.g., calorie limit).

[0190] Output: A specific health plan for each user.

[0191] The server sends the generated health plan to the terminal in JSON format.

[0192] Input: Generated health plan.

[0193] Operation: Generates a health plan as an API response and sends it to the device. Ensures secure communication using HTTPS.

[0194] Output: Health plan sent to the device.

[0195] Step 5:

[0196] Feedback and Support

[0197] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[0198] Input: Health plan received from server.

[0199] What it does: Sends a push notification to the user using the notification system and displays details in the app.

[0200] Output: Specific instructions for action displayed to the user.

[0201] The user performs actions according to the plan and enters their progress into the application.

[0202] Input: User behavior progress data.

[0203] How it works: The user fills in a form within the app with progress information and submits it.

[0204] Output: Behavioral progress data stored within the app.

[0205] The terminal organizes new data from the user and sends it to the server.

[0206] Input: Progress data.

[0207] Behavior: The entered data is stored in an internal database and sent back to the server.

[0208] Output: Progress data sent to the server.

[0209] The server analyzes the new data and assesses progress toward achieving goals and areas for improvement.

[0210] Input: Newly received progress data.

[0211] What it does: Feeds new data back into the AI ​​model, running the logic to calculate goal achievement.

[0212] Output: Evaluation of goal achievement and identification of areas for improvement.

[0213] The server generates feedback based on the evaluation results and sends it to the device, providing specific feedback such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[0214] Input: Evaluation results and improvements.

[0215] Behavior: Runs a script that generates a feedback message and sends it to the device as an API response.

[0216] Output: Feedback message sent to the terminal.

[0217] (Application example 1)

[0218] 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."

[0219] Properly assessing individual users' health status and providing customized health plans are important in modern health management. However, current systems struggle to generate and provide effective health plans for users due to incomplete collection of health data and incomprehensive analysis. Furthermore, they lack the means to provide feedback based on progress data and continuously support health management. This makes it difficult for users to effectively achieve their health goals.

[0220] 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.

[0221] In this invention, the server includes means for collecting health data from a user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data using a generative AI model to generate an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, means for transmitting data to the server as an integrated package, and means for collecting dietary information, exercise data, and sleep data from the user and evaluating the individual's health condition based on the data. This makes it possible to comprehensively collect and analyze various health data entered by the user and provide a customized health plan tailored to the individual's health condition and continuous feedback.

[0222] A "user" is an individual who uses the system to provide health data.

[0223] "Health data" refers to health-related information such as a user's dietary information, exercise data, and sleep data.

[0224] "Server" means a computer system that collects, pre-processes, and analyzes health data, and generates and provides health plans.

[0225] "Preprocessing" refers to processing collected health data such as filling in missing values ​​and standardizing the data.

[0226] A "generative AI model" is an artificial intelligence model that evaluates a user's health status based on health data and generates a customized health plan.

[0227] "Health Plan" refers to specific behavioral guidelines generated based on a user's individual health status.

[0228] "Progress data" refers to data resulting from a user's actions in accordance with a health plan.

[0229] "Feedback" refers to evaluations and suggestions for improvement provided to users based on new progress data.

[0230] "Packaging" refers to the integration of multiple collected health data into a single dataset.

[0231] A "smartphone" is a portable device for inputting or displaying a user's health data.

[0232] A "wearable device" is a device worn by a user to automatically collect exercise and sleep data.

[0233] "Dietary information" is data relating to the types and amounts of food consumed by the user.

[0234] "Exercise data" refers to data such as the amount of exercise, exercise time, and heart rate of the user.

[0235] "Sleep data" refers to data relating to the user's sleep time and sleep quality.

[0236] "Tracking" refers to the continuous monitoring and recording of a user's diet, exercise, and sleep data.

[0237] An "action plan" is a plan that provides specific guidelines for the actions a user must take to achieve their health goals.

[0238] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[0239] Hardware and software used

[0240] This system is composed of a smartphone, a wearable device, and a server. The smartphone is used as a means for users to input daily dietary data and receive health plans and feedback. The wearable device is used as a means for automatically collecting exercise and sleep data. The server plays a central role in analyzing the collected data and generating and providing health plans.

[0241] Data collection

[0242] The smartphone application allows users to input their daily dietary information, such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." In addition, exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality) are automatically synchronized from the wearable device. All data is integrated into a single package and sent to the server.

[0243] Data Preprocessing

[0244] The server analyzes the received data package and performs pre-processing such as imputing and standardizing missing values. For example, if there are missing values, they are imputed using statistical methods or historical data.

[0245] Data analysis

[0246] The server uses the generative AI model to analyze the user's health data. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality. The overall health status is evaluated based on the analysis results.

[0247] Health plan generation

[0248] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, improved sleep) and generates a specific action plan. A specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[0249] Feedback and Support

[0250] The server collects new data as needed and evaluates the user's progress. For example, based on the newly collected data, it generates feedback such as "You're steadily moving towards your goal" or "Your dinner is a little high in calories, so please improve it." The smartphone app notifies the user and displays specific instructions and suggestions for action.

[0251] Specific prompt sentences

[0252] Here is an example of what the user might enter:

[0253] text

[0254] User ID: 12345

[0255] Please enter the following data today:

[0256] Breakfast: Yogurt and banana

[0257] Lunch: Greek salad

[0258] Dinner: Stir-fried chicken and vegetables

[0259] Exercise: Sync your fitness tracker data

[0260] Sleep: Sync your sleep tracker data

[0261] The AI ​​system will analyze your health condition and notify you of the results.

[0262] Through this system, users can obtain an optimal health plan based on actual data and effectively achieve their health goals with ongoing support.

[0263] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0264] Step 1:

[0265] Users enter their daily meal information into a smartphone application, recording detailed meal details such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[0266] Input: Meal details (text data)

[0267] Output: Food data recorded on a smartphone

[0268] Step 2:

[0269] The device automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[0270] Input: Sensor data from a wearable device

[0271] Output: Exercise and sleep data recorded on a smartphone

[0272] Step 3:

[0273] The device consolidates all data (food, exercise, and sleep data) into a single package and sends it to the server, where it is packaged in a standard format such as JSON.

[0274] Input: Food data, exercise data, sleep data

[0275] Output: Consolidated data package sent to the server

[0276] Step 4:

[0277] The server analyzes the received data package and performs preprocessing such as imputing missing values ​​and standardizing the data. For example, if there are missing values, they are imputed using statistical methods or past data.

[0278] Input: Integrated Data Package

[0279] Output: Preprocessed data

[0280] Step 5:

[0281] The server analyzes the preprocessed data using a generative AI model. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality.

[0282] Input: Preprocessed data

[0283] Output: Various health indicators and analysis results

[0284] Step 6:

[0285] The server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) based on the analysis results and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[0286] Input: Various health indicators and analysis results

[0287] Output: Specific health plan

[0288] Step 7:

[0289] The device will notify the user of the generated health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[0290] Input: Specific Health Plan

[0291] Output: Instructions and suggestions for action communicated to the user

[0292] Step 8:

[0293] As users follow their health plan and enter their progress into a smartphone application, new data is collected and sent to a server.

[0294] Input: User progress data (text data, sensor data)

[0295] Output: Progress data sent to the server

[0296] Step 9:

[0297] The server analyzes the new progress data, assesses the degree of goal achievement and areas for improvement, and then reanalyzes it using a generative AI model to generate feedback such as "You're on track" or "Your dinner is on the high side, so please improve it."

[0298] Input: New progress data

[0299] Output: Feedback and evaluation results

[0300] Step 10:

[0301] The device receives the feedback and notifies the user, who can then review their health plan based on the feedback and reflect it in their next actions.

[0302] Input: Feedback and evaluation results

[0303] Output: Feedback given to the user

[0304] Through this series of processing steps, users will receive an optimal health plan based on their individual data, and will receive continuous feedback and support to achieve their health goals.

[0305] 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.

[0306] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. This system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on this data. Furthermore, it is possible to generate a customized health plan and provide feedback on progress.

[0307] Program processing (natural language explanation)

[0308] Data collection

[0309] 1. User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user might enter "I had toast and scrambled eggs for breakfast." The user also enters data for lunch and dinner in the same way. The user also enters their emotional state for the day through the application. For example, the user might enter "I feel very energetic today."

[0310] 2. Device: The application stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[0311] 3. Terminal: Consolidates all data into one data package and sends it to the server.

[0312] Data Preprocessing

[0313] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or historical data, and standardizing the data format.

[0314] 2. Server: Using the emotion engine, analyze the user's emotion data and quantify their emotional state.

[0315] Data analysis

[0316] 1. Server: Analyzes pre-processed health and emotion data using generative AI models. For example, categorize dietary data by nutrient and evaluate calorie intake and nutritional balance.

[0317] 2. Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined with emotional data to analyze overall health status.

[0318] Health plan generation

[0319] 1. Server: Based on the results of data analysis, it generates a customized health plan for each user. It takes into account emotional data and provides a specific action plan with appropriate feedback and encouraging messages. For example, it generates a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[0320] 2. Server: Sends the generated health plan to the terminal.

[0321] Feedback and Support

[0322] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0323] 2. User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[0324] 3. Terminal: Organizes the newly collected progress data and emotion data and sends them to the server.

[0325] 4. Server: Analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[0326] 5. Server: Sends feedback to the device.

[0327] Specific examples

[0328] 1. User: Through a smartphone application, the user inputs, "I had yogurt and fruit for breakfast today. I feel very energetic." The application also automatically syncs exercise and sleep data from a fitness tracker.

[0329] 2. Terminal: Organizes the entered data and sends it to the server.

[0330] 3. Server: Based on the received data, analyzes the total daily calorie intake, calories burned, and emotional state, and generates a health plan based on the user's weight loss goals.

[0331] 4. Server: Based on the analysis results, a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[0332] 5. Device: Notifies the user and displays specific instructions for action. Provides advice tailored to the user's emotional state, such as "Try this recipe today."

[0333] 6. User: Follows the health plan and enters progress and emotional state into the app. For example, "I ate a low-calorie dinner today and I feel good."

[0334] 7. Terminal: Organizes new data and sends it to the server.

[0335] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[0336] In this way, users can get the optimal health plan according to their emotional state on that day, and receive continuous improvement and support.

[0337] The processing flow will be explained below.

[0338] Step 1:

[0339] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user enters, "I had oatmeal and a banana for breakfast." The user also enters the user's emotional state for that day through the application. For example, the user enters, "I feel very tired today."

[0340] Step 2:

[0341] Device: Stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[0342] Step 3:

[0343] Terminal: Organizes all data into a single data package and sends it to the server.

[0344] Step 4:

[0345] Server: Analyzes the received data package and performs preprocessing of the data, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[0346] Step 5:

[0347] Server: Using the emotion engine, analyzes the user's emotion data and quantifies their emotional state. In this process, each emotion is converted into a numerical value, which can be used for calculations.

[0348] Step 6:

[0349] Server: Analyzes preprocessed health and emotion data using a generative AI model. For example, it categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance. It also evaluates calories burned and exercise intensity based on exercise data, and sleep duration and quality based on sleep data.

[0350] Step 7:

[0351] Server: Integrates the assessment results and emotional data to analyze the overall health status, deriving specific insights such as, "Your calorie intake is high, but your emotional state is fatigued, so light exercise is recommended."

[0352] Step 8:

[0353] Server: Based on the analysis results, a customized health plan is generated for each user. Emotional data is also taken into consideration, providing a specific action plan with appropriate feedback and encouraging messages. For example, a specific health plan is generated, such as "Today you feel tired, so we suggest doing some light stretching" or "Tomorrow, reduce your calorie intake a little."

[0354] Step 9:

[0355] Server: Sends the generated health plan to the device.

[0356] Step 10:

[0357] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Do 30 minutes of relaxing yoga today."

[0358] Step 11:

[0359] User: Takes actions according to the health plan and enters their daily progress and emotional state into the application. For example, they might enter, "This time, I ate a lighter dinner to match my emotional state."

[0360] Step 12:

[0361] Terminal: Organizes newly collected progress data and emotion data and sends it to the server.

[0362] Step 13:

[0363] Server: Analyzes new progress and emotional data to assess goal achievement and areas for improvement. For example, it generates feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[0364] Step 14:

[0365] Server: Sends feedback to the device.

[0366] Step 15:

[0367] On-device: Provides feedback to users, suggests next steps, and provides advice to help them stay motivated, such as "If you keep going at this pace, you'll soon reach your goal weight" or "Reminder: Make sure you go to bed by 9 o'clock tonight."

[0368] Through these steps, users can continuously manage their health and act according to an optimal health plan that also takes into account their emotional state.

[0369] Example 2

[0370] 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."

[0371] In modern society, there is a demand for efficient management of people's health status and the provision of individually optimized health plans. However, conventional systems have difficulty integrating and analyzing a user's health and emotional data to provide feedback tailored to their individual health status. It is also difficult to generate a customized plan that takes into account the user's emotional state. In particular, there is a lack of systems that can collect and analyze health and emotional data separately and provide comprehensive health management, making it difficult to provide consistent health management.

[0372] 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.

[0373] In this invention, the server includes means for collecting health data and emotional data from a user, means for analyzing and quantifying the emotional data, and means for analyzing the preprocessed health data and emotional data using a generative AI model, thereby enabling the server to comprehensively analyze the user's health data and emotional data, generate a health plan optimized for each individual user, and provide feedback.

[0374] A "user" is an individual who utilizes the system to provide their health and emotional data.

[0375] "Health data" refers to information about a user's daily diet, exercise, and sleep.

[0376] "Emotion data" is information that indicates the user's emotional state, and is input as text or numerical values.

[0377] A "wearable device" is a device that automatically collects a user's exercise and sleep data. Examples include fitness trackers and smartwatches.

[0378] A "data package" is a consolidated form of all collected data that is sent to the server.

[0379] "Preprocessing" is the process of analyzing the data package sent to the server, filling in missing values, and standardizing the data format.

[0380] An "emotion engine" is a technology that analyzes emotional data and quantifies emotional states from text data.

[0381] A "generative AI model" is an artificial intelligence model that performs analysis using preprocessed health data and emotion data.

[0382] A "health plan" is a plan for maintaining and improving health that is customized for each individual user and created based on the results of data analysis.

[0383] "Feedback" refers to evaluations and advice provided to users based on progress data and analysis results.

[0384] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. The system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on that data. It is also capable of generating a customized health plan and providing feedback on progress.

[0385] Data collection

[0386] 1. The user opens a dedicated smartphone application and manually enters the details of their daily meals. For example, they might enter, "I had toast and scrambled eggs for breakfast." They also enter their emotional state. For example, they might record, "I feel very energetic today."

[0387] 2. The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches).

[0388] 3. The device aggregates all data into a single data package and sends it to the server, specifically via a REST API using JSON format.

[0389] Data Preprocessing

[0390] 1. The server analyzes the received data package, imputes missing values ​​using statistical methods and past data, and standardizes the data format. Specifically, this process is performed using the Python Pandas library.

[0391] 2. The server analyzes the emotion data using an emotion engine to quantify the user's emotional state, for example by using the Google® Cloud Natural Language API to extract an emotion score from the text data.

[0392] Data analysis

[0393] 1. The server analyzes the preprocessed health and emotion data using a generative AI model. Specifically, it uses a neural network model with TensorFlow to classify the dietary data by nutrient and evaluate calorie intake and nutritional balance. For example, it calculates the calories and nutrients of "toast and scrambled eggs."

[0394] 2. The server evaluates the calorie consumption and exercise intensity based on the exercise data, and evaluates the sleep duration and quality based on the sleep data. These evaluation results are combined with the emotional data to analyze the user's overall health status. Specifically, the server evaluates heart rate and step count using the SciKit-Learn library.

[0395] Health plan generation

[0396] 1. Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[0397] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[0398] 2. The server sends the generated health plan to the terminal.

[0399] Feedback and Support

[0400] 1. The device notifies the user of the received health plan and displays specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0401] 2. The user acts according to the health plan and enters their daily progress into the application, for example, "I ate less calories at dinner today."

[0402] 3. The device organizes the progress data and new emotion data and sends them to the server.

[0403] 4. The server analyzes the new progress and emotion data to evaluate the progress of the goal and areas for improvement, generating feedback such as, "You're making good progress toward your goal," or "You'd be even more effective if you reduced the calories in your dinner a little more."

[0404] 5. The server sends the generated feedback to the device.

[0405] Specific examples

[0406] 1. A user enters into a smartphone application: "I had yogurt and fruit for breakfast today. My emotional state is very good." The application also syncs exercise and sleep data from a fitness tracker.

[0407] 2. The device organizes the data and sends it to the server.

[0408] 3. The server analyzes the data, including the total daily calorie intake, calories burned, and emotional state, and generates a health plan. For example, "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[0409] 4. The server sends the generated health plan to the terminal.

[0410] 5. The device displays notifications and instructions to the user, such as advice like "Try this recipe today."

[0411] 6. The user acts according to the health plan and enters their progress into the app. For example, "I ate a low-calorie dinner today and I feel good."

[0412] 7. The device organizes the new data and sends it to the server.

[0413] 8. The server analyzes the new data and generates feedback, such as "You're on track to reach your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more."

[0414] In this way, the entire system manages users' health and emotional data in an integrated manner, and provides individually optimized health plans and feedback, thereby supporting users in maintaining and improving their health.

[0415] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0416] Step 1:

[0417] The user opens a dedicated smartphone application and manually inputs the details of their daily meals, for example, "I had toast and scrambled eggs for breakfast," and their emotional state for that day, for example, "I feel very energetic today."

[0418] Input: User's daily diet and emotional state

[0419] Output: Food and emotion data stored on the user's smartphone

[0420] Step 2:

[0421] The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise duration) and sleep data (sleep duration, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches) using Bluetooth and Wi-Fi.

[0422] Input: User's dietary data, emotional data, exercise data, sleep data

[0423] Output: Integrated dataset on smartphone

[0424] Step 3:

[0425] The device integrates all data into a single data package and sends it to the server. Specifically, it creates the data in JSON format and sends it to the server using a REST API.

[0426] Input: Integrated dataset

[0427] Output: Data package sent to the server

[0428] Step 4:

[0429] The server analyzes the received data package and performs preprocessing on the data. Specifically, it uses the Python Pandas library to impute missing values ​​and standardize the data format. For example, it imputes missing sleep data with the average value from the past.

[0430] Input: Data package sent to the server

[0431] Output: Preprocessed dataset

[0432] Step 5:

[0433] The server analyzes the emotion data using an emotion engine (e.g., Google Cloud Natural Language API) and quantifies the emotional state. Specifically, it quantifies the input "very energetic" with a positive score.

[0434] Input: Preprocessed dataset

[0435] Output: Quantified emotion data

[0436] Step 6:

[0437] The server uses a generative AI model (e.g., a neural network model using TensorFlow) to analyze the preprocessed health and emotion data. Specifically, it categorizes the dietary data by nutrient and evaluates calorie intake and nutritional balance.

[0438] Input: Preprocessed health data, quantified emotion data

[0439] Output: Analysis results (nutritional balance, calories burned, quality of sleep, etc.)

[0440] Step 7:

[0441] Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[0442] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[0443] Input: Analysis results

[0444] Output: Customized health plan

[0445] Step 8:

[0446] The server sends the generated health plan to the device. Specifically, it creates the data in JSON format and sends it to the device using a REST API.

[0447] Enter: Customized Health Plan

[0448] Output: Health plan sent to the device

[0449] Step 9:

[0450] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0451] Input: Received Health Plan

[0452] Output: User notification and instructions for action

[0453] Step 10:

[0454] The user acts according to the health plan and inputs their daily progress into the application, for example, "I had a low-calorie dinner today."

[0455] Input: User progress data

[0456] Output: Progress data saved on the device

[0457] Step 11:

[0458] The device organizes the new progress data and emotion data and sends it to the server. Specifically, the newly collected data is again integrated in JSON format and sent via a REST API.

[0459] Input: New progress and emotion data

[0460] Output: Data package sent to the server

[0461] Step 12:

[0462] The server analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as, "You're on track with your goal," or "You'd be better off if you reduced the calories in your dinner a little more."

[0463] Input: New progress and emotion data

[0464] Output: Evaluation results and feedback

[0465] Step 13:

[0466] The server sends the evaluation results and feedback to the device. Specifically, the feedback is formatted in JSON and sent to the device using a REST API.

[0467] Input: Evaluation results and feedback

[0468] Output: Feedback sent to the terminal

[0469] Step 14:

[0470] The device will then notify the user of the received feedback and provide instructions and suggestions for the next steps, such as "You're on track to reach your goal" or "You'll be even more effective if you cut back on the calories at dinner."

[0471] Input: Feedback received

[0472] Output: Notification to the user and next action instructions

[0473] Through these steps, users can obtain the optimal health plan based on their emotional state that day, and receive continuous improvement and support.

[0474] (Application example 2)

[0475] 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."

[0476] Many conventional health management systems track a user's diet, exercise, and sleep data and provide a health plan. However, these systems do not take emotional states into account, limiting the effectiveness of personalized health plans. Furthermore, the content provided is uniform, lacking a means to provide personalized content that addresses the user's individual health status and emotions. As a result, users lose motivation to continue following their health plan. This invention aims to solve this problem by proposing a system that integrates a user's individual health data and emotional data to provide an optimal health plan and personalized health and wellness-related content.

[0477] 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 collecting health data from the user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data and generating an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, and means for providing personalized health and wellness-related content based on the health plan. This enables the user to obtain an optimal health plan and personalized content according to their emotional state and health condition on that day, thereby increasing their motivation to continuously implement the health plan.

[0478] "Health Data" refers to information about a user's diet, exercise, sleep, and other health conditions.

[0479] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze. Specifically, this includes imputing missing values, standardizing data, and standardizing formats.

[0480] "Health Plan" refers to specific guidelines and advice generated based on a user's individual health and emotional data, including exercise regimes, meal plans, sleep schedules, etc.

[0481] "Personalized Content" means personalized health and wellness related information, videos, audio, articles, etc. that are delivered to you based on your individual health and emotional state.

[0482] "Generative AI model" refers to the artificial intelligence algorithms used to analyze collected data and generate health plans and content.

[0483] "Feedback" refers to evaluating the progress of the user's health plan and providing suggestions for improvement or further advice.

[0484] "Emotion data" refers to information that indicates the user's emotional state using numerical values ​​or categories. Specifically, it includes emotional states such as "energetic," "tired easily," and "high stress."

[0485] "Individualization" refers to providing optimal information and plans according to each user's different needs and circumstances.

[0486] This invention relates to a system that collects individual user health and emotional data and provides health plans and personalized health and wellness-related content based on that data. The following describes the processing of the program that realizes this system.

[0487] Data collection

[0488] Users manually input their daily diet and emotional state using a dedicated application on their smartphone or head-mounted display. For example, they can enter information such as "I had yogurt and fruit for breakfast" or "I feel very energetic today." Additionally, exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) are automatically synchronized using a fitness tracker.

[0489] Data Preprocessing

[0490] The server receives the collected data and performs preprocessing. Specifically, it fills in missing values ​​and standardizes the format. It then uses an emotion engine to analyze the user's emotion data and convert it into numerical values ​​and categories.

[0491] Data analysis and health plan generation

[0492] The server analyzes the preprocessed health and emotion data using a generative AI model. Based on the analysis results, it generates a customized health plan for each user. This health plan includes specific guidelines and advice. For example, it suggests things like "walking for 30 minutes three times a week," "eating less than 1,500 calories a day," and "going to bed at 10 p.m. every night."

[0493] Content Recommendation

[0494] Based on the generated health plan, the server provides users with personalized health and wellness content, including health-related videos, audio, and articles, which users can view and interact with through a dedicated application.

[0495] Feedback and Support

[0496] The user carries out actions according to the health plan and enters their progress and emotional state into a dedicated application. For example, they might enter information such as, "I ate less calories at dinner today, and I'm feeling good." The server analyzes the new data collected and evaluates their progress and areas for improvement. Based on this, it provides feedback to the user. For example, it may provide specific advice such as, "You're on track to reach your goal," or "You'd be even more effective if you reduced the calories at dinner a little more."

[0497] Examples of concrete examples and prompts

[0498] For example, if a user inputs "I had yogurt and fruit for breakfast today. I feel very energetic," and synchronizes exercise data (7,000 steps, 45 minutes of exercise, average heart rate 70 BPM) and sleep data (7 hours of sleep, good quality of sleep) from a fitness tracker, the server will generate a health plan based on this data and recommend appropriate content.

[0499] An example of a prompt sentence for input to a generative AI model is as follows:

[0500] User's dietary data: yogurt and fruit

[0501] User's emotional state: Very energetic

[0502] Exercise data: 7000 steps, exercise time 45 minutes, average heart rate 70 BPM

[0503] Sleep data: 7 hours of sleep, good quality

[0504] Use this data to generate an optimal health plan and personalized content to support its implementation.

[0505] In this way, users can obtain the optimal health plan and personalized content based on their emotional and health state on that day, which increases their motivation to continue implementing the health plan and enables effective health management.

[0506] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0507] Step 1:

[0508] Device: Using a dedicated application on a smartphone or head-mounted display, the user manually inputs their daily diet and emotional state. Examples of input data include "I had yogurt and fruit for breakfast" and "I feel very energetic today." In addition, the wearable device automatically synchronizes exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality). All of this health-related information is included in the input data.

[0509] Input: Food data, Emotion data, Exercise data, Sleep data

[0510] Output: Integrated health data package

[0511] Step 2:

[0512] Terminal: Sends collected health data to the server using a secure and reliable communication protocol and uploads the data package to the server.

[0513] Input: Integrated Health Data Package

[0514] Output: Sending the data package to the server

[0515] Step 3:

[0516] Server: Preprocesses the received data package. If there is missing or incomplete data, it is filled in using statistical methods or past data. Next, the data format is standardized and an emotion engine is used to convert emotion data into numerical values ​​or categories. This results in a consistent dataset.

[0517] Input: Integrated Health Data Package

[0518] Output: Preprocessed dataset

[0519] Step 4:

[0520] Server: The preprocessed data is input into the generative AI model and analyzed. Specifically, nutritional value and calories are evaluated from dietary data, calories burned and exercise intensity from exercise data, and sleep quality and duration from sleep data. The model integrates this data and analyzes overall health status.

[0521] Input: Preprocessed dataset

[0522] Output: Analysis results

[0523] Step 5:

[0524] Server: Based on the analysis results, an individual health plan is generated. The generated health plan includes specific guidelines and advice. For example, a customized plan may be created, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[0525] Input: Analysis results

[0526] Output: Health Plan

[0527] Step 6:

[0528] Server: Based on the generated health plan, retrieves and provides personalized health and wellness-related content to the user. Content includes health-related videos, audio, articles, etc. The server selects appropriate content and sends it to the device.

[0529] Enter: Health Plan

[0530] Output: personalized content

[0531] Step 7:

[0532] Device: Informs the user of their health plan and personalized content, allowing them to take specific courses of action or view the content provided.

[0533] Input: Health plans, personalized content

[0534] Output: Notification to terminal

[0535] Step 8:

[0536] User: Takes actions according to the health plan and inputs their progress and emotional state into a dedicated application. For example, they receive feedback such as, "I ate less calories at dinner today. I'm feeling good."

[0537] Input: User results and feedback

[0538] Output: Updated progress data

[0539] Step 9:

[0540] Device: Sends newly collected progress and emotion data to the server, where it is stored for the next analysis.

[0541] Input: Updated progress data

[0542] Output: Sending progress data to the server

[0543] Step 10:

[0544] Server: Analyzes the latest progress data and evaluates the degree of goal achievement and areas for improvement. For example, it generates feedback such as "You are making good progress toward your goal" or "You would be more effective if you reduced the calories in your dinner a little more" and sends it to the device.

[0545] Input: Latest progress data

[0546] Output: Evaluation results and feedback

[0547] In this way, specific data processing and actions are performed at each step, allowing users to be provided with the optimal health plan and personalized content based on their emotional and health state on that day, enabling them to continuously implement their health plan.

[0548] 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.

[0549] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0550] 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.

[0551] [Second embodiment]

[0552] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0553] 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.

[0554] 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).

[0555] 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.

[0556] 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.

[0557] 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).

[0558] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] In the smart glasses 214, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0563] 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."

[0564] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[0565] Program processing (natural language explanation)

[0566] Data collection

[0567] 1. User: Enters daily meal information through a smartphone application, providing detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[0568] 2. Device: The application stores the entered data and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[0569] 3. Terminal: Consolidates all data into one package and sends it to the server.

[0570] Data Preprocessing

[0571] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data.

[0572] 2. Server: Standardizes the data format and converts it into a form suitable for analysis.

[0573] Data analysis

[0574] 1. Server: Analyzes the user's health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc.

[0575] 2. Server: Evaluates calories burned and exercise intensity based on exercise data.

[0576] 3. Server: Based on sleep data, evaluates sleep duration and quality and assesses overall health.

[0577] Health plan generation

[0578] 1. Server: Based on the results of data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it generates a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[0579] 2. Server: Sends the generated health plan to the terminal.

[0580] Feedback and Support

[0581] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[0582] 2. User: Carries out the actions according to the plan and enters progress into the application.

[0583] 3. Terminal: Collects new data from the user and sends it to the server.

[0584] 4. Server: Analyzes new data and assesses progress toward goals and areas for improvement.

[0585] 5. Server: Generates feedback and sends it to the device. For example, it provides feedback to the user such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[0586] Specific examples

[0587] Example 1: User trying to lose weight

[0588] 1. User: Opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[0589] 2. Terminal: Organizes the entered data and sends it to the server.

[0590] 3. Server: Based on the received data, calculates the total daily calorie intake and calories burned and performs analysis based on the user's weight loss goal.

[0591] 4. Server: Based on the analysis results, a specific health plan is generated, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed by 10 p.m.", and sent to the device.

[0592] 5. Terminal: Notifies the user and displays specific instructions for action.

[0593] 6. User: Follows the plan and enters progress into the app.

[0594] 7. Terminal: Organizes new data and sends it to the server.

[0595] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[0596] In this way, users can get the best health plan based on real data and get continuous improvement and support.

[0597] The processing flow will be explained below.

[0598] Step 1:

[0599] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, enters "I had toast and scrambled eggs for breakfast." Also, enters data for lunch and dinner in the same way.

[0600] Step 2:

[0601] Device: Stores the entered food data and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[0602] Step 3:

[0603] Device: All collected data (diet, exercise, sleep) is organized into a single data package and sent to the server.

[0604] Step 4:

[0605] Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[0606] Step 5:

[0607] Server: Analyzes pre-processed health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance.

[0608] Step 6:

[0609] Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined to analyze overall health status.

[0610] Step 7:

[0611] Server: Based on the analysis results, a customized health plan is generated for each user. For example, a specific health plan such as "30 minutes of aerobic exercise three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated.

[0612] Step 8:

[0613] Server: Sends the generated health plan to the device.

[0614] Step 9:

[0615] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0616] Step 10:

[0617] User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[0618] Step 11:

[0619] Device: Organizes newly collected progress data and sends it to the server.

[0620] Step 12:

[0621] Server: Analyzes new progress data and evaluates goal achievement and areas for improvement, generating feedback such as "You're on track to achieve your goal" or "You could be even more effective if you cut back on the calories at dinner."

[0622] Step 13:

[0623] Server: Sends feedback to the device.

[0624] Step 14:

[0625] Device: Provides feedback to the user, suggests next steps, and provides advice to help maintain motivation.

[0626] Through these steps, users can continuously manage their health status and act in accordance with an optimal health plan.

[0627] Example 1

[0628] 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."

[0629] Health management is an important issue in modern society. However, many people find it difficult to properly collect and analyze their own health data and develop effective health plans. Furthermore, many health management systems on the market lack the ability to comprehensively analyze individual data and provide feedback, making it difficult for users to achieve optimal health management. This invention aims to provide a system that collects and analyzes individual users' health data and provides customized health plans and continuous feedback.

[0630] 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.

[0631] In this invention, the server includes a means for collecting health data from users, a means for pre-processing the health data transmitted to the server, and a means for analyzing the pre-processed data to generate an individual health plan, thereby enabling the health data of each individual user to be appropriately collected and analyzed and a customized health plan to be provided.

[0632] "Health data" refers to information necessary for assessing a user's health status, such as diet, exercise, and sleep information.

[0633] "Server" refers to the central management system that processes data received from users, generates health plans, and provides feedback.

[0634] "Preprocessing" refers to the data preparation work required before data analysis, such as imputing missing values ​​and standardizing the format of received health data.

[0635] "Health Plan" refers to a plan that includes specific diet, exercise, and sleep instructions customized based on the user's health status.

[0636] "Feedback" refers to evaluations and advice provided based on a user's actions and progress.

[0637] "Generative AI models" refer to artificial intelligence algorithms and models used to analyze data and generate health plans.

[0638] "Tracking" refers to recording a user's activities and status and collecting data on an ongoing basis.

[0639] "Data Package" means all health data collected from a user in one format.

[0640] The system of this invention is an AI system that collects and analyzes individual health data of users and provides optimal health plans. This system is capable of evaluating individual health conditions based on the user's diet, exercise, and sleep data, generating customized health plans, and providing feedback.

[0641] Hardware and Software

[0642] The system is implemented using the following hardware and software:

[0643] Smartphone (user device)

[0644] Wearable devices (e.g., Fitbit, Apple Watch)

[0645] Server (cloud server)

[0646] Smartphone application (health management app)

[0647] Python libraries for running generative AI models (e.g., TensorFlow, PyTorch)

[0648] Program Implementation

[0649] The program for this system is executed as follows:

[0650] Data collection

[0651] Users input their daily meal plans through a smartphone application. For example, they can provide detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." Furthermore, the device connects to a wearable device and automatically synchronizes exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality).

[0652] All data is packaged in JSON format and sent securely to the server over HTTPS. Specifically, the device makes an API request and sends the data to the server via a POST request.

[0653] Data Preprocessing

[0654] The server analyzes the received data package and performs preprocessing on the data. For example, if there are missing values, it fills them in using statistical methods or past data. It also standardizes the data format and stores it in a unified format in a table in the database. Specifically, it parses the data and executes a script to convert it into a unified format (e.g., unifying the timestamp format).

[0655] Data analysis

[0656] The server uses the generative AI model to analyze the user's health data. For example, it categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc. It also evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. This allows for an assessment of the user's overall health.

[0657] Health plan generation

[0658] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[0659] Feedback and Support

[0660] The device notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Plan to go to the gym tomorrow." The user carries out the actions according to the plan and enters their progress into the application. The new data is organized and sent to the server, which analyzes it, evaluates the progress of goal achievement and areas for improvement, and generates feedback and sends it to the device.

[0661] Specific examples

[0662] Example 1: User trying to lose weight

[0663] 1. A user opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[0664] 2. The terminal organizes the entered data and sends it to the server.

[0665] 3. Based on the received data, the server calculates the total daily calorie intake and calories burned and analyzes it based on the user's weight loss goal.

[0666] 4. Based on the analysis results, the server generates a specific health plan such as "walk for 30 minutes three times a week," "eat no more than 1,500 calories a day," and "go to bed by 10 p.m." and sends it to the device.

[0667] 5. The device notifies the user and displays specific instructions for action.

[0668] 6. The user acts according to the plan and enters their progress into the app.

[0669] 7. The device organizes the new data and sends it to the server.

[0670] 8. The server analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[0671] Using this system, users can obtain the optimal health plan based on their individual health condition and receive ongoing support and feedback.

[0672] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0673] Step 1:

[0674] Data collection

[0675] Users manually enter their daily dietary information using a smartphone application, providing detailed dietary information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner."

[0676] Input: User's meal information (text format).

[0677] How it works: The user enters specific meal details into the app's input form.

[0678] Output: The entered meal information is saved in the app's database.

[0679] The device works with wearable devices (e.g., Fitbit, Apple Watch) and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality).

[0680] Input: Exercise and sleep data from wearable devices.

[0681] How it works: The app uses the wearable device API to retrieve data.

[0682] Output: The acquired data is saved in the app's database.

[0683] The device then compiles all the data into a single package in JSON format and sends it securely to the server using HTTPS.

[0684] Input: Integrated health data (diet, exercise, sleep) converted to JSON format.

[0685] How it works: The device makes an API request and sends data to the server in a POST request.

[0686] Output: JSON formatted data is sent to the server.

[0687] Step 2:

[0688] Data Preprocessing

[0689] The server analyzes the received data package and performs preprocessing on the data, for example, imputing missing values ​​using statistical methods or past data.

[0690] Input: Health data package in JSON format sent to the server.

[0691] How it works: A server-side script validates the data (e.g., checks for blanks) and imputes missing values.

[0692] Output: Data with missing values ​​imputed and passing validation.

[0693] The server standardizes the data format and stores it in a uniform format in tables within the database.

[0694] Input: Health data that has passed validation.

[0695] What it does: Runs a script that parses the data and converts it to a unified format (e.g. unified timestamp format).

[0696] Output: The data converted into a unified format is saved in the database.

[0697] Step 3:

[0698] Data analysis

[0699] The server analyzes the user's health data using a generative AI model, inputting dietary data into the model, classifying it by nutrient, and evaluating calorie intake, protein, fat, carbohydrates, etc.

[0700] Input: Health data converted into a unified format.

[0701] How it works: Food data is input into the AI ​​model, which then classifies and evaluates each nutrient.

[0702] Output: Classification and evaluation results for each nutrient.

[0703] The server evaluates exercise intensity and calories burned based on the exercise data.

[0704] Input: Motion data converted into a unified format.

[0705] Operation: Obtains exercise data from the database and calculates calories burned using calculation logic.

[0706] Output: Evaluation results of exercise intensity and calories burned.

[0707] The server evaluates sleep duration and quality based on sleep data, and assesses overall health.

[0708] Input: Sleep data converted into a unified format.

[0709] How it works: Sleep data is fed into the AI ​​model, and the output is interpreted using evaluation logic.

[0710] Output: Sleep duration and quality assessment, overall health status.

[0711] Step 4:

[0712] Health plan generation

[0713] Based on the data analysis results, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it provides a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[0714] Input: Data analysis results.

[0715] What it does: Analyzes the output of the AI ​​model and runs a script to set specific values ​​(e.g., calorie limit).

[0716] Output: A specific health plan for each user.

[0717] The server sends the generated health plan to the terminal in JSON format.

[0718] Input: Generated health plan.

[0719] Operation: Generates a health plan as an API response and sends it to the device. Ensures secure communication using HTTPS.

[0720] Output: Health plan sent to the device.

[0721] Step 5:

[0722] Feedback and Support

[0723] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[0724] Input: Health plan received from server.

[0725] What it does: Sends a push notification to the user using the notification system and displays details in the app.

[0726] Output: Specific instructions for action displayed to the user.

[0727] The user performs actions according to the plan and enters their progress into the application.

[0728] Input: User behavior progress data.

[0729] How it works: The user fills in a form within the app with progress information and submits it.

[0730] Output: Behavioral progress data stored within the app.

[0731] The terminal organizes new data from the user and sends it to the server.

[0732] Input: Progress data.

[0733] Behavior: The entered data is stored in an internal database and sent back to the server.

[0734] Output: Progress data sent to the server.

[0735] The server analyzes the new data and assesses progress toward achieving goals and areas for improvement.

[0736] Input: Newly received progress data.

[0737] What it does: Feeds new data back into the AI ​​model, running the logic to calculate goal achievement.

[0738] Output: Evaluation of goal achievement and identification of areas for improvement.

[0739] The server generates feedback based on the evaluation results and sends it to the device, providing specific feedback such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[0740] Input: Evaluation results and improvements.

[0741] Behavior: Runs a script that generates a feedback message and sends it to the device as an API response.

[0742] Output: Feedback message sent to the terminal.

[0743] (Application example 1)

[0744] 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."

[0745] Properly assessing individual users' health status and providing customized health plans are important in modern health management. However, current systems struggle to generate and provide effective health plans for users due to incomplete collection of health data and incomprehensive analysis. Furthermore, they lack the means to provide feedback based on progress data and continuously support health management. This makes it difficult for users to effectively achieve their health goals.

[0746] 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.

[0747] In this invention, the server includes means for collecting health data from a user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data using a generative AI model to generate an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, means for transmitting data to the server as an integrated package, and means for collecting dietary information, exercise data, and sleep data from the user and evaluating the individual's health condition based on the data. This makes it possible to comprehensively collect and analyze various health data entered by the user and provide a customized health plan tailored to the individual's health condition and continuous feedback.

[0748] A "user" is an individual who uses the system to provide health data.

[0749] "Health data" refers to health-related information such as a user's dietary information, exercise data, and sleep data.

[0750] "Server" means a computer system that collects, pre-processes, and analyzes health data, and generates and provides health plans.

[0751] "Preprocessing" refers to processing collected health data such as filling in missing values ​​and standardizing the data.

[0752] A "generative AI model" is an artificial intelligence model that evaluates a user's health status based on health data and generates a customized health plan.

[0753] "Health Plan" refers to specific behavioral guidelines generated based on a user's individual health status.

[0754] "Progress data" refers to data resulting from a user's actions in accordance with a health plan.

[0755] "Feedback" refers to evaluations and suggestions for improvement provided to users based on new progress data.

[0756] "Packaging" refers to the integration of multiple collected health data into a single dataset.

[0757] A "smartphone" is a portable device for inputting or displaying a user's health data.

[0758] A "wearable device" is a device worn by a user to automatically collect exercise and sleep data.

[0759] "Dietary information" is data relating to the types and amounts of food consumed by the user.

[0760] "Exercise data" refers to data such as the amount of exercise, exercise time, and heart rate of the user.

[0761] "Sleep data" refers to data relating to the user's sleep time and sleep quality.

[0762] "Tracking" refers to the continuous monitoring and recording of a user's diet, exercise, and sleep data.

[0763] An "action plan" is a plan that provides specific guidelines for the actions a user must take to achieve their health goals.

[0764] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[0765] Hardware and software used

[0766] This system is composed of a smartphone, a wearable device, and a server. The smartphone is used as a means for users to input daily dietary data and receive health plans and feedback. The wearable device is used as a means for automatically collecting exercise and sleep data. The server plays a central role in analyzing the collected data and generating and providing health plans.

[0767] Data collection

[0768] The smartphone application allows users to input their daily dietary information, such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." In addition, exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality) are automatically synchronized from the wearable device. All data is integrated into a single package and sent to the server.

[0769] Data Preprocessing

[0770] The server analyzes the received data package and performs pre-processing such as imputing and standardizing missing values. For example, if there are missing values, they are imputed using statistical methods or historical data.

[0771] Data analysis

[0772] The server uses the generative AI model to analyze the user's health data. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality. The overall health status is evaluated based on the analysis results.

[0773] Health plan generation

[0774] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, improved sleep) and generates a specific action plan. A specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[0775] Feedback and Support

[0776] The server collects new data as needed and evaluates the user's progress. For example, based on the newly collected data, it generates feedback such as "You're steadily moving towards your goal" or "Your dinner is a little high in calories, so please improve it." The smartphone app notifies the user and displays specific instructions and suggestions for action.

[0777] Specific prompt sentences

[0778] Here is an example of what the user might enter:

[0779] text

[0780] User ID: 12345

[0781] Please enter the following data today:

[0782] Breakfast: Yogurt and banana

[0783] Lunch: Greek salad

[0784] Dinner: Stir-fried chicken and vegetables

[0785] Exercise: Sync your fitness tracker data

[0786] Sleep: Sync your sleep tracker data

[0787] The AI ​​system will analyze your health condition and notify you of the results.

[0788] Through this system, users can obtain an optimal health plan based on actual data and effectively achieve their health goals with ongoing support.

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

[0790] Step 1:

[0791] Users enter their daily meal information into a smartphone application, recording detailed meal details such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[0792] Input: Meal details (text data)

[0793] Output: Food data recorded on a smartphone

[0794] Step 2:

[0795] The device automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[0796] Input: Sensor data from a wearable device

[0797] Output: Exercise and sleep data recorded on a smartphone

[0798] Step 3:

[0799] The device consolidates all data (food, exercise, and sleep data) into a single package and sends it to the server, where it is packaged in a standard format such as JSON.

[0800] Input: Food data, exercise data, sleep data

[0801] Output: Consolidated data package sent to the server

[0802] Step 4:

[0803] The server analyzes the received data package and performs preprocessing such as imputing missing values ​​and standardizing the data. For example, if there are missing values, they are imputed using statistical methods or past data.

[0804] Input: Integrated Data Package

[0805] Output: Preprocessed data

[0806] Step 5:

[0807] The server analyzes the preprocessed data using a generative AI model. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality.

[0808] Input: Preprocessed data

[0809] Output: Various health indicators and analysis results

[0810] Step 6:

[0811] The server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) based on the analysis results and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[0812] Input: Various health indicators and analysis results

[0813] Output: Specific health plan

[0814] Step 7:

[0815] The device will notify the user of the generated health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[0816] Input: Specific Health Plan

[0817] Output: Instructions and suggestions for action communicated to the user

[0818] Step 8:

[0819] As users follow their health plan and enter their progress into a smartphone application, new data is collected and sent to a server.

[0820] Input: User progress data (text data, sensor data)

[0821] Output: Progress data sent to the server

[0822] Step 9:

[0823] The server analyzes the new progress data, assesses the degree of goal achievement and areas for improvement, and then reanalyzes it using a generative AI model to generate feedback such as "You're on track" or "Your dinner is on the high side, so please improve it."

[0824] Input: New progress data

[0825] Output: Feedback and evaluation results

[0826] Step 10:

[0827] The device receives the feedback and notifies the user, who can then review their health plan based on the feedback and reflect it in their next actions.

[0828] Input: Feedback and evaluation results

[0829] Output: Feedback given to the user

[0830] Through this series of processing steps, users will receive an optimal health plan based on their individual data, and will receive continuous feedback and support to achieve their health goals.

[0831] 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.

[0832] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. This system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on this data. Furthermore, it is possible to generate a customized health plan and provide feedback on progress.

[0833] Program processing (natural language explanation)

[0834] Data collection

[0835] 1. User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user might enter "I had toast and scrambled eggs for breakfast." The user also enters data for lunch and dinner in the same way. The user also enters their emotional state for the day through the application. For example, the user might enter "I feel very energetic today."

[0836] 2. Device: The application stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[0837] 3. Terminal: Consolidates all data into one data package and sends it to the server.

[0838] Data Preprocessing

[0839] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or historical data, and standardizing the data format.

[0840] 2. Server: Using the emotion engine, analyze the user's emotion data and quantify their emotional state.

[0841] Data analysis

[0842] 1. Server: Analyzes pre-processed health and emotion data using generative AI models. For example, categorize dietary data by nutrient and evaluate calorie intake and nutritional balance.

[0843] 2. Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined with emotional data to analyze overall health status.

[0844] Health plan generation

[0845] 1. Server: Based on the results of data analysis, it generates a customized health plan for each user. It takes into account emotional data and provides a specific action plan with appropriate feedback and encouraging messages. For example, it generates a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[0846] 2. Server: Sends the generated health plan to the terminal.

[0847] Feedback and Support

[0848] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0849] 2. User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[0850] 3. Terminal: Organizes the newly collected progress data and emotion data and sends them to the server.

[0851] 4. Server: Analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[0852] 5. Server: Sends feedback to the device.

[0853] Specific examples

[0854] 1. User: Through a smartphone application, the user inputs, "I had yogurt and fruit for breakfast today. I feel very energetic." The application also automatically syncs exercise and sleep data from a fitness tracker.

[0855] 2. Terminal: Organizes the entered data and sends it to the server.

[0856] 3. Server: Based on the received data, analyzes the total daily calorie intake, calories burned, and emotional state, and generates a health plan based on the user's weight loss goals.

[0857] 4. Server: Based on the analysis results, a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[0858] 5. Device: Notifies the user and displays specific instructions for action. Provides advice tailored to the user's emotional state, such as "Try this recipe today."

[0859] 6. User: Follows the health plan and enters progress and emotional state into the app. For example, "I ate a low-calorie dinner today and I feel good."

[0860] 7. Terminal: Organizes new data and sends it to the server.

[0861] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[0862] In this way, users can get the optimal health plan according to their emotional state on that day, and receive continuous improvement and support.

[0863] The processing flow will be explained below.

[0864] Step 1:

[0865] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user enters, "I had oatmeal and a banana for breakfast." The user also enters the user's emotional state for that day through the application. For example, the user enters, "I feel very tired today."

[0866] Step 2:

[0867] Device: Stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[0868] Step 3:

[0869] Terminal: Organizes all data into a single data package and sends it to the server.

[0870] Step 4:

[0871] Server: Analyzes the received data package and performs preprocessing of the data, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[0872] Step 5:

[0873] Server: Using the emotion engine, analyzes the user's emotion data and quantifies their emotional state. In this process, each emotion is converted into a numerical value, which can be used for calculations.

[0874] Step 6:

[0875] Server: Analyzes preprocessed health and emotion data using a generative AI model. For example, it categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance. It also evaluates calories burned and exercise intensity based on exercise data, and sleep duration and quality based on sleep data.

[0876] Step 7:

[0877] Server: Integrates the assessment results and emotional data to analyze the overall health status, deriving specific insights such as, "Your calorie intake is high, but your emotional state is fatigued, so light exercise is recommended."

[0878] Step 8:

[0879] Server: Based on the analysis results, a customized health plan is generated for each user. Emotional data is also taken into consideration, providing a specific action plan with appropriate feedback and encouraging messages. For example, a specific health plan is generated, such as "Today you feel tired, so we suggest doing some light stretching" or "Tomorrow, reduce your calorie intake a little."

[0880] Step 9:

[0881] Server: Sends the generated health plan to the device.

[0882] Step 10:

[0883] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Do 30 minutes of relaxing yoga today."

[0884] Step 11:

[0885] User: Takes actions according to the health plan and enters their daily progress and emotional state into the application. For example, they might enter, "This time, I ate a lighter dinner to match my emotional state."

[0886] Step 12:

[0887] Terminal: Organizes newly collected progress data and emotion data and sends it to the server.

[0888] Step 13:

[0889] Server: Analyzes new progress and emotional data to assess goal achievement and areas for improvement. For example, it generates feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[0890] Step 14:

[0891] Server: Sends feedback to the device.

[0892] Step 15:

[0893] On-device: Provides feedback to users, suggests next steps, and provides advice to help them stay motivated, such as "If you keep going at this pace, you'll soon reach your goal weight" or "Reminder: Make sure you go to bed by 9 o'clock tonight."

[0894] Through these steps, users can continuously manage their health and act according to an optimal health plan that also takes into account their emotional state.

[0895] Example 2

[0896] 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."

[0897] In modern society, there is a demand for efficient management of people's health status and the provision of individually optimized health plans. However, conventional systems have difficulty integrating and analyzing a user's health and emotional data to provide feedback tailored to their individual health status. It is also difficult to generate a customized plan that takes into account the user's emotional state. In particular, there is a lack of systems that can collect and analyze health and emotional data separately and provide comprehensive health management, making it difficult to provide consistent health management.

[0898] 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.

[0899] In this invention, the server includes means for collecting health data and emotional data from a user, means for analyzing and quantifying the emotional data, and means for analyzing the preprocessed health data and emotional data using a generative AI model, thereby enabling the server to comprehensively analyze the user's health data and emotional data, generate a health plan optimized for each individual user, and provide feedback.

[0900] A "user" is an individual who utilizes the system to provide their health and emotional data.

[0901] "Health data" refers to information about a user's daily diet, exercise, and sleep.

[0902] "Emotion data" is information that indicates the user's emotional state, and is input as text or numerical values.

[0903] A "wearable device" is a device that automatically collects a user's exercise and sleep data. Examples include fitness trackers and smartwatches.

[0904] A "data package" is a consolidated form of all collected data that is sent to the server.

[0905] "Preprocessing" is the process of analyzing the data package sent to the server, filling in missing values, and standardizing the data format.

[0906] An "emotion engine" is a technology that analyzes emotional data and quantifies emotional states from text data.

[0907] A "generative AI model" is an artificial intelligence model that performs analysis using preprocessed health data and emotion data.

[0908] A "health plan" is a plan for maintaining and improving health that is customized for each individual user and created based on the results of data analysis.

[0909] "Feedback" refers to evaluations and advice provided to users based on progress data and analysis results.

[0910] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. The system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on that data. It is also capable of generating a customized health plan and providing feedback on progress.

[0911] Data collection

[0912] 1. The user opens a dedicated smartphone application and manually enters the details of their daily meals. For example, they might enter, "I had toast and scrambled eggs for breakfast." They also enter their emotional state. For example, they might record, "I feel very energetic today."

[0913] 2. The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches).

[0914] 3. The device aggregates all data into a single data package and sends it to the server, specifically via a REST API using JSON format.

[0915] Data Preprocessing

[0916] 1. The server analyzes the received data package, imputes missing values ​​using statistical methods and past data, and standardizes the data format. Specifically, this process is performed using the Python Pandas library.

[0917] 2. The server analyzes the emotion data using an emotion engine to quantify the user's emotional state. For example, it uses the Google Cloud Natural Language API to extract an emotion score from the text data.

[0918] Data analysis

[0919] 1. The server analyzes the preprocessed health and emotion data using a generative AI model. Specifically, it uses a neural network model with TensorFlow to classify the dietary data by nutrient and evaluate calorie intake and nutritional balance. For example, it calculates the calories and nutrients of "toast and scrambled eggs."

[0920] 2. The server evaluates the calorie consumption and exercise intensity based on the exercise data, and evaluates the sleep duration and quality based on the sleep data. These evaluation results are combined with the emotional data to analyze the user's overall health status. Specifically, the server evaluates heart rate and step count using the SciKit-Learn library.

[0921] Health plan generation

[0922] 1. Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[0923] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[0924] 2. The server sends the generated health plan to the terminal.

[0925] Feedback and Support

[0926] 1. The device notifies the user of the received health plan and displays specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0927] 2. The user acts according to the health plan and enters their daily progress into the application, for example, "I ate less calories at dinner today."

[0928] 3. The device organizes the progress data and new emotion data and sends them to the server.

[0929] 4. The server analyzes the new progress and emotion data to evaluate the progress of the goal and areas for improvement, generating feedback such as, "You're making good progress toward your goal," or "You'd be even more effective if you reduced the calories in your dinner a little more."

[0930] 5. The server sends the generated feedback to the device.

[0931] Specific examples

[0932] 1. A user enters into a smartphone application: "I had yogurt and fruit for breakfast today. My emotional state is very good." The application also syncs exercise and sleep data from a fitness tracker.

[0933] 2. The device organizes the data and sends it to the server.

[0934] 3. The server analyzes the data, including the total daily calorie intake, calories burned, and emotional state, and generates a health plan. For example, "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[0935] 4. The server sends the generated health plan to the terminal.

[0936] 5. The device displays notifications and instructions to the user, such as advice like "Try this recipe today."

[0937] 6. The user acts according to the health plan and enters their progress into the app. For example, "I ate a low-calorie dinner today and I feel good."

[0938] 7. The device organizes the new data and sends it to the server.

[0939] 8. The server analyzes the new data and generates feedback, such as "You're on track to reach your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more."

[0940] In this way, the entire system manages users' health and emotional data in an integrated manner, and provides individually optimized health plans and feedback, thereby supporting users in maintaining and improving their health.

[0941] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0942] Step 1:

[0943] The user opens a dedicated smartphone application and manually inputs the details of their daily meals, for example, "I had toast and scrambled eggs for breakfast," and their emotional state for that day, for example, "I feel very energetic today."

[0944] Input: User's daily diet and emotional state

[0945] Output: Food and emotion data stored on the user's smartphone

[0946] Step 2:

[0947] The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise duration) and sleep data (sleep duration, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches) using Bluetooth and Wi-Fi.

[0948] Input: User's dietary data, emotional data, exercise data, sleep data

[0949] Output: Integrated dataset on smartphone

[0950] Step 3:

[0951] The device integrates all data into a single data package and sends it to the server. Specifically, it creates the data in JSON format and sends it to the server using a REST API.

[0952] Input: Integrated dataset

[0953] Output: Data package sent to the server

[0954] Step 4:

[0955] The server analyzes the received data package and performs preprocessing on the data. Specifically, it uses the Python Pandas library to impute missing values ​​and standardize the data format. For example, it imputes missing sleep data with the average value from the past.

[0956] Input: Data package sent to the server

[0957] Output: Preprocessed dataset

[0958] Step 5:

[0959] The server analyzes the emotion data using an emotion engine (e.g., Google Cloud Natural Language API) and quantifies the emotional state. Specifically, it quantifies the input "very energetic" with a positive score.

[0960] Input: Preprocessed dataset

[0961] Output: Quantified emotion data

[0962] Step 6:

[0963] The server uses a generative AI model (e.g., a neural network model using TensorFlow) to analyze the preprocessed health and emotion data. Specifically, it categorizes the dietary data by nutrient and evaluates calorie intake and nutritional balance.

[0964] Input: Preprocessed health data, quantified emotion data

[0965] Output: Analysis results (nutritional balance, calories burned, quality of sleep, etc.)

[0966] Step 7:

[0967] Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[0968] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[0969] Input: Analysis results

[0970] Output: Customized health plan

[0971] Step 8:

[0972] The server sends the generated health plan to the device. Specifically, it creates the data in JSON format and sends it to the device using a REST API.

[0973] Enter: Customized Health Plan

[0974] Output: Health plan sent to the device

[0975] Step 9:

[0976] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[0977] Input: Received Health Plan

[0978] Output: User notification and instructions for action

[0979] Step 10:

[0980] The user acts according to the health plan and inputs their daily progress into the application, for example, "I had a low-calorie dinner today."

[0981] Input: User progress data

[0982] Output: Progress data saved on the device

[0983] Step 11:

[0984] The device organizes the new progress data and emotion data and sends it to the server. Specifically, the newly collected data is again integrated in JSON format and sent via a REST API.

[0985] Input: New progress and emotion data

[0986] Output: Data package sent to the server

[0987] Step 12:

[0988] The server analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as, "You're on track with your goal," or "You'd be better off if you reduced the calories in your dinner a little more."

[0989] Input: New progress and emotion data

[0990] Output: Evaluation results and feedback

[0991] Step 13:

[0992] The server sends the evaluation results and feedback to the device. Specifically, the feedback is formatted in JSON and sent to the device using a REST API.

[0993] Input: Evaluation results and feedback

[0994] Output: Feedback sent to the terminal

[0995] Step 14:

[0996] The device will then notify the user of the received feedback and provide instructions and suggestions for the next steps, such as "You're on track to reach your goal" or "You'll be even more effective if you cut back on the calories at dinner."

[0997] Input: Feedback received

[0998] Output: Notification to the user and next action instructions

[0999] Through these steps, users can obtain the optimal health plan based on their emotional state that day, and receive continuous improvement and support.

[1000] (Application example 2)

[1001] 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."

[1002] Many conventional health management systems track a user's diet, exercise, and sleep data and provide a health plan. However, these systems do not take emotional states into account, limiting the effectiveness of personalized health plans. Furthermore, the content provided is uniform, lacking a means to provide personalized content that addresses the user's individual health status and emotions. As a result, users lose motivation to continue following their health plan. This invention aims to solve this problem by proposing a system that integrates a user's individual health data and emotional data to provide an optimal health plan and personalized health and wellness-related content.

[1003] 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 collecting health data from the user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data and generating an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, and means for providing personalized health and wellness-related content based on the health plan. This enables the user to obtain an optimal health plan and personalized content according to their emotional state and health condition on that day, thereby increasing their motivation to continuously implement the health plan.

[1004] "Health Data" refers to information about a user's diet, exercise, sleep, and other health conditions.

[1005] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze. Specifically, this includes imputing missing values, standardizing data, and standardizing formats.

[1006] "Health Plan" refers to specific guidelines and advice generated based on a user's individual health and emotional data, including exercise regimes, meal plans, sleep schedules, etc.

[1007] "Personalized Content" means personalized health and wellness related information, videos, audio, articles, etc. that are delivered to you based on your individual health and emotional state.

[1008] "Generative AI model" refers to the artificial intelligence algorithms used to analyze collected data and generate health plans and content.

[1009] "Feedback" refers to evaluating the progress of the user's health plan and providing suggestions for improvement or further advice.

[1010] "Emotion data" refers to information that indicates the user's emotional state using numerical values ​​or categories. Specifically, it includes emotional states such as "energetic," "tired easily," and "high stress."

[1011] "Individualization" refers to providing optimal information and plans according to each user's different needs and circumstances.

[1012] This invention relates to a system that collects individual user health and emotional data and provides health plans and personalized health and wellness-related content based on that data. The following describes the processing of the program that realizes this system.

[1013] Data collection

[1014] Users manually input their daily diet and emotional state using a dedicated application on their smartphone or head-mounted display. For example, they can enter information such as "I had yogurt and fruit for breakfast" or "I feel very energetic today." Additionally, exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) are automatically synchronized using a fitness tracker.

[1015] Data Preprocessing

[1016] The server receives the collected data and performs preprocessing. Specifically, it fills in missing values ​​and standardizes the format. It then uses an emotion engine to analyze the user's emotion data and convert it into numerical values ​​and categories.

[1017] Data analysis and health plan generation

[1018] The server analyzes the preprocessed health and emotion data using a generative AI model. Based on the analysis results, it generates a customized health plan for each user. This health plan includes specific guidelines and advice. For example, it suggests things like "walking for 30 minutes three times a week," "eating less than 1,500 calories a day," and "going to bed at 10 p.m. every night."

[1019] Content Recommendation

[1020] Based on the generated health plan, the server provides users with personalized health and wellness content, including health-related videos, audio, and articles, which users can view and interact with through a dedicated application.

[1021] Feedback and Support

[1022] The user carries out actions according to the health plan and enters their progress and emotional state into a dedicated application. For example, they might enter information such as, "I ate less calories at dinner today, and I'm feeling good." The server analyzes the new data collected and evaluates their progress and areas for improvement. Based on this, it provides feedback to the user. For example, it may provide specific advice such as, "You're on track to reach your goal," or "You'd be even more effective if you reduced the calories at dinner a little more."

[1023] Examples of concrete examples and prompts

[1024] For example, if a user inputs "I had yogurt and fruit for breakfast today. I feel very energetic," and synchronizes exercise data (7,000 steps, 45 minutes of exercise, average heart rate 70 BPM) and sleep data (7 hours of sleep, good quality of sleep) from a fitness tracker, the server will generate a health plan based on this data and recommend appropriate content.

[1025] An example of a prompt sentence for input to a generative AI model is as follows:

[1026] User's dietary data: yogurt and fruit

[1027] User's emotional state: Very energetic

[1028] Exercise data: 7000 steps, exercise time 45 minutes, average heart rate 70 BPM

[1029] Sleep data: 7 hours of sleep, good quality

[1030] Use this data to generate an optimal health plan and personalized content to support its implementation.

[1031] In this way, users can obtain the optimal health plan and personalized content based on their emotional and health state on that day, which increases their motivation to continue implementing the health plan and enables effective health management.

[1032] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1033] Step 1:

[1034] Device: Using a dedicated application on a smartphone or head-mounted display, the user manually inputs their daily diet and emotional state. Examples of input data include "I had yogurt and fruit for breakfast" and "I feel very energetic today." In addition, the wearable device automatically synchronizes exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality). All of this health-related information is included in the input data.

[1035] Input: Food data, Emotion data, Exercise data, Sleep data

[1036] Output: Integrated health data package

[1037] Step 2:

[1038] Terminal: Sends collected health data to the server using a secure and reliable communication protocol and uploads the data package to the server.

[1039] Input: Integrated Health Data Package

[1040] Output: Sending the data package to the server

[1041] Step 3:

[1042] Server: Preprocesses the received data package. If there is missing or incomplete data, it is filled in using statistical methods or past data. Next, the data format is standardized and an emotion engine is used to convert emotion data into numerical values ​​or categories. This results in a consistent dataset.

[1043] Input: Integrated Health Data Package

[1044] Output: Preprocessed dataset

[1045] Step 4:

[1046] Server: The preprocessed data is input into the generative AI model and analyzed. Specifically, nutritional value and calories are evaluated from dietary data, calories burned and exercise intensity from exercise data, and sleep quality and duration from sleep data. The model integrates this data and analyzes overall health status.

[1047] Input: Preprocessed dataset

[1048] Output: Analysis results

[1049] Step 5:

[1050] Server: Based on the analysis results, an individual health plan is generated. The generated health plan includes specific guidelines and advice. For example, a customized plan may be created, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[1051] Input: Analysis results

[1052] Output: Health Plan

[1053] Step 6:

[1054] Server: Based on the generated health plan, retrieves and provides personalized health and wellness-related content to the user. Content includes health-related videos, audio, articles, etc. The server selects appropriate content and sends it to the device.

[1055] Enter: Health Plan

[1056] Output: personalized content

[1057] Step 7:

[1058] Device: Informs the user of their health plan and personalized content, allowing them to take specific courses of action or view the content provided.

[1059] Input: Health plans, personalized content

[1060] Output: Notification to terminal

[1061] Step 8:

[1062] User: Takes actions according to the health plan and inputs their progress and emotional state into a dedicated application. For example, they receive feedback such as, "I ate less calories at dinner today. I'm feeling good."

[1063] Input: User results and feedback

[1064] Output: Updated progress data

[1065] Step 9:

[1066] Device: Sends newly collected progress and emotion data to the server, where it is stored for the next analysis.

[1067] Input: Updated progress data

[1068] Output: Sending progress data to the server

[1069] Step 10:

[1070] Server: Analyzes the latest progress data and evaluates the degree of goal achievement and areas for improvement. For example, it generates feedback such as "You are making good progress toward your goal" or "You would be more effective if you reduced the calories in your dinner a little more" and sends it to the device.

[1071] Input: Latest progress data

[1072] Output: Evaluation results and feedback

[1073] In this way, specific data processing and actions are performed at each step, allowing users to be provided with the optimal health plan and personalized content based on their emotional and health state on that day, enabling them to continuously implement their health plan.

[1074] 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.

[1075] 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.

[1076] 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.

[1077] [Third embodiment]

[1078] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1079] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1080] 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).

[1081] 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.

[1082] 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.

[1083] 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).

[1084] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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.

[1089] 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."

[1090] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[1091] Program processing (natural language explanation)

[1092] Data collection

[1093] 1. User: Enters daily meal information through a smartphone application, providing detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[1094] 2. Device: The application stores the entered data and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[1095] 3. Terminal: Consolidates all data into one package and sends it to the server.

[1096] Data Preprocessing

[1097] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data.

[1098] 2. Server: Standardizes the data format and converts it into a form suitable for analysis.

[1099] Data analysis

[1100] 1. Server: Analyzes the user's health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc.

[1101] 2. Server: Evaluates calories burned and exercise intensity based on exercise data.

[1102] 3. Server: Based on sleep data, evaluates sleep duration and quality and assesses overall health.

[1103] Health plan generation

[1104] 1. Server: Based on the results of data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it generates a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[1105] 2. Server: Sends the generated health plan to the terminal.

[1106] Feedback and Support

[1107] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[1108] 2. User: Carries out the actions according to the plan and enters progress into the application.

[1109] 3. Terminal: Collects new data from the user and sends it to the server.

[1110] 4. Server: Analyzes new data and assesses progress toward goals and areas for improvement.

[1111] 5. Server: Generates feedback and sends it to the device. For example, it provides feedback to the user such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[1112] Specific examples

[1113] Example 1: User trying to lose weight

[1114] 1. User: Opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[1115] 2. Terminal: Organizes the entered data and sends it to the server.

[1116] 3. Server: Based on the received data, calculates the total daily calorie intake and calories burned and performs analysis based on the user's weight loss goal.

[1117] 4. Server: Based on the analysis results, a specific health plan is generated, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed by 10 p.m.", and sent to the device.

[1118] 5. Terminal: Notifies the user and displays specific instructions for action.

[1119] 6. User: Follows the plan and enters progress into the app.

[1120] 7. Terminal: Organizes new data and sends it to the server.

[1121] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[1122] In this way, users can get the best health plan based on real data and get continuous improvement and support.

[1123] The processing flow will be explained below.

[1124] Step 1:

[1125] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, enters "I had toast and scrambled eggs for breakfast." Also, enters data for lunch and dinner in the same way.

[1126] Step 2:

[1127] Device: Stores the entered food data and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[1128] Step 3:

[1129] Device: All collected data (diet, exercise, sleep) is organized into a single data package and sent to the server.

[1130] Step 4:

[1131] Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[1132] Step 5:

[1133] Server: Analyzes pre-processed health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance.

[1134] Step 6:

[1135] Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined to analyze overall health status.

[1136] Step 7:

[1137] Server: Based on the analysis results, a customized health plan is generated for each user. For example, a specific health plan such as "30 minutes of aerobic exercise three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated.

[1138] Step 8:

[1139] Server: Sends the generated health plan to the device.

[1140] Step 9:

[1141] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1142] Step 10:

[1143] User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[1144] Step 11:

[1145] Device: Organizes newly collected progress data and sends it to the server.

[1146] Step 12:

[1147] Server: Analyzes new progress data and evaluates goal achievement and areas for improvement, generating feedback such as "You're on track to achieve your goal" or "You could be even more effective if you cut back on the calories at dinner."

[1148] Step 13:

[1149] Server: Sends feedback to the device.

[1150] Step 14:

[1151] Device: Provides feedback to the user, suggests next steps, and provides advice to help maintain motivation.

[1152] Through these steps, users can continuously manage their health status and act in accordance with an optimal health plan.

[1153] Example 1

[1154] 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."

[1155] Health management is an important issue in modern society. However, many people find it difficult to properly collect and analyze their own health data and develop effective health plans. Furthermore, many health management systems on the market lack the ability to comprehensively analyze individual data and provide feedback, making it difficult for users to achieve optimal health management. This invention aims to provide a system that collects and analyzes individual users' health data and provides customized health plans and continuous feedback.

[1156] 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.

[1157] In this invention, the server includes a means for collecting health data from users, a means for pre-processing the health data transmitted to the server, and a means for analyzing the pre-processed data to generate an individual health plan, thereby enabling the health data of each individual user to be appropriately collected and analyzed and a customized health plan to be provided.

[1158] "Health data" refers to information necessary for assessing a user's health status, such as diet, exercise, and sleep information.

[1159] "Server" refers to the central management system that processes data received from users, generates health plans, and provides feedback.

[1160] "Preprocessing" refers to the data preparation work required before data analysis, such as imputing missing values ​​and standardizing the format of received health data.

[1161] "Health Plan" refers to a plan that includes specific diet, exercise, and sleep instructions customized based on the user's health status.

[1162] "Feedback" refers to evaluations and advice provided based on a user's actions and progress.

[1163] "Generative AI models" refer to artificial intelligence algorithms and models used to analyze data and generate health plans.

[1164] "Tracking" refers to recording a user's activities and status and collecting data on an ongoing basis.

[1165] "Data Package" means all health data collected from a user in one format.

[1166] The system of this invention is an AI system that collects and analyzes individual health data of users and provides optimal health plans. This system is capable of evaluating individual health conditions based on the user's diet, exercise, and sleep data, generating customized health plans, and providing feedback.

[1167] Hardware and Software

[1168] The system is implemented using the following hardware and software:

[1169] Smartphone (user device)

[1170] Wearable devices (e.g., Fitbit, Apple Watch)

[1171] Server (cloud server)

[1172] Smartphone application (health management app)

[1173] Python libraries for running generative AI models (e.g., TensorFlow, PyTorch)

[1174] Program Implementation

[1175] The program for this system is executed as follows:

[1176] Data collection

[1177] Users input their daily meal plans through a smartphone application. For example, they can provide detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." Furthermore, the device connects to a wearable device and automatically synchronizes exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality).

[1178] All data is packaged in JSON format and sent securely to the server over HTTPS. Specifically, the device makes an API request and sends the data to the server via a POST request.

[1179] Data Preprocessing

[1180] The server analyzes the received data package and performs preprocessing on the data. For example, if there are missing values, it fills them in using statistical methods or past data. It also standardizes the data format and stores it in a unified format in a table in the database. Specifically, it parses the data and executes a script to convert it into a unified format (e.g., unifying the timestamp format).

[1181] Data analysis

[1182] The server uses the generative AI model to analyze the user's health data. For example, it categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc. It also evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. This allows for an assessment of the user's overall health.

[1183] Health plan generation

[1184] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[1185] Feedback and Support

[1186] The device notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Plan to go to the gym tomorrow." The user carries out the actions according to the plan and enters their progress into the application. The new data is organized and sent to the server, which analyzes it, evaluates the progress of goal achievement and areas for improvement, and generates feedback and sends it to the device.

[1187] Specific examples

[1188] Example 1: User trying to lose weight

[1189] 1. A user opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[1190] 2. The terminal organizes the entered data and sends it to the server.

[1191] 3. Based on the received data, the server calculates the total daily calorie intake and calories burned and analyzes it based on the user's weight loss goal.

[1192] 4. Based on the analysis results, the server generates a specific health plan such as "walk for 30 minutes three times a week," "eat no more than 1,500 calories a day," and "go to bed by 10 p.m." and sends it to the device.

[1193] 5. The device notifies the user and displays specific instructions for action.

[1194] 6. The user acts according to the plan and enters their progress into the app.

[1195] 7. The device organizes the new data and sends it to the server.

[1196] 8. The server analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[1197] Using this system, users can obtain the optimal health plan based on their individual health condition and receive ongoing support and feedback.

[1198] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1199] Step 1:

[1200] Data collection

[1201] Users manually enter their daily dietary information using a smartphone application, providing detailed dietary information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner."

[1202] Input: User's meal information (text format).

[1203] How it works: The user enters specific meal details into the app's input form.

[1204] Output: The entered meal information is saved in the app's database.

[1205] The device works with wearable devices (e.g., Fitbit, Apple Watch) and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality).

[1206] Input: Exercise and sleep data from wearable devices.

[1207] How it works: The app uses the wearable device API to retrieve data.

[1208] Output: The acquired data is saved in the app's database.

[1209] The device then compiles all the data into a single package in JSON format and sends it securely to the server using HTTPS.

[1210] Input: Integrated health data (diet, exercise, sleep) converted to JSON format.

[1211] How it works: The device makes an API request and sends data to the server in a POST request.

[1212] Output: JSON formatted data is sent to the server.

[1213] Step 2:

[1214] Data Preprocessing

[1215] The server analyzes the received data package and performs preprocessing on the data, for example, imputing missing values ​​using statistical methods or past data.

[1216] Input: Health data package in JSON format sent to the server.

[1217] How it works: A server-side script validates the data (e.g., checks for blanks) and imputes missing values.

[1218] Output: Data with missing values ​​imputed and passing validation.

[1219] The server standardizes the data format and stores it in a uniform format in tables within the database.

[1220] Input: Health data that has passed validation.

[1221] What it does: Runs a script that parses the data and converts it to a unified format (e.g. unified timestamp format).

[1222] Output: The data converted into a unified format is saved in the database.

[1223] Step 3:

[1224] Data analysis

[1225] The server analyzes the user's health data using a generative AI model, inputting dietary data into the model, classifying it by nutrient, and evaluating calorie intake, protein, fat, carbohydrates, etc.

[1226] Input: Health data converted into a unified format.

[1227] How it works: Food data is input into the AI ​​model, which then classifies and evaluates each nutrient.

[1228] Output: Classification and evaluation results for each nutrient.

[1229] The server evaluates exercise intensity and calories burned based on the exercise data.

[1230] Input: Motion data converted into a unified format.

[1231] Operation: Obtains exercise data from the database and calculates calories burned using calculation logic.

[1232] Output: Evaluation results of exercise intensity and calories burned.

[1233] The server evaluates sleep duration and quality based on sleep data, and assesses overall health.

[1234] Input: Sleep data converted into a unified format.

[1235] How it works: Sleep data is fed into the AI ​​model, and the output is interpreted using evaluation logic.

[1236] Output: Sleep duration and quality assessment, overall health status.

[1237] Step 4:

[1238] Health plan generation

[1239] Based on the data analysis results, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it provides a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[1240] Input: Data analysis results.

[1241] What it does: Analyzes the output of the AI ​​model and runs a script to set specific values ​​(e.g., calorie limit).

[1242] Output: A specific health plan for each user.

[1243] The server sends the generated health plan to the terminal in JSON format.

[1244] Input: Generated health plan.

[1245] Operation: Generates a health plan as an API response and sends it to the device. Ensures secure communication using HTTPS.

[1246] Output: Health plan sent to the device.

[1247] Step 5:

[1248] Feedback and Support

[1249] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[1250] Input: Health plan received from server.

[1251] What it does: Sends a push notification to the user using the notification system and displays details in the app.

[1252] Output: Specific instructions for action displayed to the user.

[1253] The user performs actions according to the plan and enters their progress into the application.

[1254] Input: User behavior progress data.

[1255] How it works: The user fills in a form within the app with progress information and submits it.

[1256] Output: Behavioral progress data stored within the app.

[1257] The terminal organizes new data from the user and sends it to the server.

[1258] Input: Progress data.

[1259] Behavior: The entered data is stored in an internal database and sent back to the server.

[1260] Output: Progress data sent to the server.

[1261] The server analyzes the new data and assesses progress toward achieving goals and areas for improvement.

[1262] Input: Newly received progress data.

[1263] What it does: Feeds new data back into the AI ​​model, running the logic to calculate goal achievement.

[1264] Output: Evaluation of goal achievement and identification of areas for improvement.

[1265] The server generates feedback based on the evaluation results and sends it to the device, providing specific feedback such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[1266] Input: Evaluation results and improvements.

[1267] Behavior: Runs a script that generates a feedback message and sends it to the device as an API response.

[1268] Output: Feedback message sent to the terminal.

[1269] (Application example 1)

[1270] 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."

[1271] Properly assessing individual users' health status and providing customized health plans are important in modern health management. However, current systems struggle to generate and provide effective health plans for users due to incomplete collection of health data and incomprehensive analysis. Furthermore, they lack the means to provide feedback based on progress data and continuously support health management. This makes it difficult for users to effectively achieve their health goals.

[1272] 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.

[1273] In this invention, the server includes means for collecting health data from a user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data using a generative AI model to generate an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, means for transmitting data to the server as an integrated package, and means for collecting dietary information, exercise data, and sleep data from the user and evaluating the individual's health condition based on the data. This makes it possible to comprehensively collect and analyze various health data entered by the user and provide a customized health plan tailored to the individual's health condition and continuous feedback.

[1274] A "user" is an individual who uses the system to provide health data.

[1275] "Health data" refers to health-related information such as a user's dietary information, exercise data, and sleep data.

[1276] "Server" means a computer system that collects, pre-processes, and analyzes health data, and generates and provides health plans.

[1277] "Preprocessing" refers to processing collected health data such as filling in missing values ​​and standardizing the data.

[1278] A "generative AI model" is an artificial intelligence model that evaluates a user's health status based on health data and generates a customized health plan.

[1279] "Health Plan" refers to specific behavioral guidelines generated based on a user's individual health status.

[1280] "Progress data" refers to data resulting from a user's actions in accordance with a health plan.

[1281] "Feedback" refers to evaluations and suggestions for improvement provided to users based on new progress data.

[1282] "Packaging" refers to the integration of multiple collected health data into a single dataset.

[1283] A "smartphone" is a portable device for inputting or displaying a user's health data.

[1284] A "wearable device" is a device worn by a user to automatically collect exercise and sleep data.

[1285] "Dietary information" is data relating to the types and amounts of food consumed by the user.

[1286] "Exercise data" refers to data such as the amount of exercise, exercise time, and heart rate of the user.

[1287] "Sleep data" refers to data relating to the user's sleep time and sleep quality.

[1288] "Tracking" refers to the continuous monitoring and recording of a user's diet, exercise, and sleep data.

[1289] An "action plan" is a plan that provides specific guidelines for the actions a user must take to achieve their health goals.

[1290] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[1291] Hardware and software used

[1292] This system is composed of a smartphone, a wearable device, and a server. The smartphone is used as a means for users to input daily dietary data and receive health plans and feedback. The wearable device is used as a means for automatically collecting exercise and sleep data. The server plays a central role in analyzing the collected data and generating and providing health plans.

[1293] Data collection

[1294] The smartphone application allows users to input their daily dietary information, such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." In addition, exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality) are automatically synchronized from the wearable device. All data is integrated into a single package and sent to the server.

[1295] Data Preprocessing

[1296] The server analyzes the received data package and performs pre-processing such as imputing and standardizing missing values. For example, if there are missing values, they are imputed using statistical methods or historical data.

[1297] Data analysis

[1298] The server uses the generative AI model to analyze the user's health data. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality. The overall health status is evaluated based on the analysis results.

[1299] Health plan generation

[1300] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, improved sleep) and generates a specific action plan. A specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[1301] Feedback and Support

[1302] The server collects new data as needed and evaluates the user's progress. For example, based on the newly collected data, it generates feedback such as "You're steadily moving towards your goal" or "Your dinner is a little high in calories, so please improve it." The smartphone app notifies the user and displays specific instructions and suggestions for action.

[1303] Specific prompt sentences

[1304] Here is an example of what the user might enter:

[1305] text

[1306] User ID: 12345

[1307] Please enter the following data today:

[1308] Breakfast: Yogurt and banana

[1309] Lunch: Greek salad

[1310] Dinner: Stir-fried chicken and vegetables

[1311] Exercise: Sync your fitness tracker data

[1312] Sleep: Sync your sleep tracker data

[1313] The AI ​​system will analyze your health condition and notify you of the results.

[1314] Through this system, users can obtain an optimal health plan based on actual data and effectively achieve their health goals with ongoing support.

[1315] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1316] Step 1:

[1317] Users enter their daily meal information into a smartphone application, recording detailed meal details such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[1318] Input: Meal details (text data)

[1319] Output: Food data recorded on a smartphone

[1320] Step 2:

[1321] The device automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[1322] Input: Sensor data from a wearable device

[1323] Output: Exercise and sleep data recorded on a smartphone

[1324] Step 3:

[1325] The device consolidates all data (food, exercise, and sleep data) into a single package and sends it to the server, where it is packaged in a standard format such as JSON.

[1326] Input: Food data, exercise data, sleep data

[1327] Output: Consolidated data package sent to the server

[1328] Step 4:

[1329] The server analyzes the received data package and performs preprocessing such as imputing missing values ​​and standardizing the data. For example, if there are missing values, they are imputed using statistical methods or past data.

[1330] Input: Integrated Data Package

[1331] Output: Preprocessed data

[1332] Step 5:

[1333] The server analyzes the preprocessed data using a generative AI model. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality.

[1334] Input: Preprocessed data

[1335] Output: Various health indicators and analysis results

[1336] Step 6:

[1337] The server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) based on the analysis results and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[1338] Input: Various health indicators and analysis results

[1339] Output: Specific health plan

[1340] Step 7:

[1341] The device will notify the user of the generated health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[1342] Input: Specific Health Plan

[1343] Output: Instructions and suggestions for action communicated to the user

[1344] Step 8:

[1345] As users follow their health plan and enter their progress into a smartphone application, new data is collected and sent to a server.

[1346] Input: User progress data (text data, sensor data)

[1347] Output: Progress data sent to the server

[1348] Step 9:

[1349] The server analyzes the new progress data, assesses the degree of goal achievement and areas for improvement, and then reanalyzes it using a generative AI model to generate feedback such as "You're on track" or "Your dinner is on the high side, so please improve it."

[1350] Input: New progress data

[1351] Output: Feedback and evaluation results

[1352] Step 10:

[1353] The device receives the feedback and notifies the user, who can then review their health plan based on the feedback and reflect it in their next actions.

[1354] Input: Feedback and evaluation results

[1355] Output: Feedback given to the user

[1356] Through this series of processing steps, users will receive an optimal health plan based on their individual data, and will receive continuous feedback and support to achieve their health goals.

[1357] 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.

[1358] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. This system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on this data. Furthermore, it is possible to generate a customized health plan and provide feedback on progress.

[1359] Program processing (natural language explanation)

[1360] Data collection

[1361] 1. User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user might enter "I had toast and scrambled eggs for breakfast." The user also enters data for lunch and dinner in the same way. The user also enters their emotional state for the day through the application. For example, the user might enter "I feel very energetic today."

[1362] 2. Device: The application stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[1363] 3. Terminal: Consolidates all data into one data package and sends it to the server.

[1364] Data Preprocessing

[1365] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or historical data, and standardizing the data format.

[1366] 2. Server: Using the emotion engine, analyze the user's emotion data and quantify their emotional state.

[1367] Data analysis

[1368] 1. Server: Analyzes pre-processed health and emotion data using generative AI models. For example, categorize dietary data by nutrient and evaluate calorie intake and nutritional balance.

[1369] 2. Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined with emotional data to analyze overall health status.

[1370] Health plan generation

[1371] 1. Server: Based on the results of data analysis, it generates a customized health plan for each user. It takes into account emotional data and provides a specific action plan with appropriate feedback and encouraging messages. For example, it generates a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[1372] 2. Server: Sends the generated health plan to the terminal.

[1373] Feedback and Support

[1374] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1375] 2. User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[1376] 3. Terminal: Organizes the newly collected progress data and emotion data and sends them to the server.

[1377] 4. Server: Analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[1378] 5. Server: Sends feedback to the device.

[1379] Specific examples

[1380] 1. User: Through a smartphone application, the user inputs, "I had yogurt and fruit for breakfast today. I feel very energetic." The application also automatically syncs exercise and sleep data from a fitness tracker.

[1381] 2. Terminal: Organizes the entered data and sends it to the server.

[1382] 3. Server: Based on the received data, analyzes the total daily calorie intake, calories burned, and emotional state, and generates a health plan based on the user's weight loss goals.

[1383] 4. Server: Based on the analysis results, a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[1384] 5. Device: Notifies the user and displays specific instructions for action. Provides advice tailored to the user's emotional state, such as "Try this recipe today."

[1385] 6. User: Follows the health plan and enters progress and emotional state into the app. For example, "I ate a low-calorie dinner today and I feel good."

[1386] 7. Terminal: Organizes new data and sends it to the server.

[1387] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[1388] In this way, users can get the optimal health plan according to their emotional state on that day, and receive continuous improvement and support.

[1389] The processing flow will be explained below.

[1390] Step 1:

[1391] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user enters, "I had oatmeal and a banana for breakfast." The user also enters the user's emotional state for that day through the application. For example, the user enters, "I feel very tired today."

[1392] Step 2:

[1393] Device: Stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[1394] Step 3:

[1395] Terminal: Organizes all data into a single data package and sends it to the server.

[1396] Step 4:

[1397] Server: Analyzes the received data package and performs preprocessing of the data, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[1398] Step 5:

[1399] Server: Using the emotion engine, analyzes the user's emotion data and quantifies their emotional state. In this process, each emotion is converted into a numerical value, which can be used for calculations.

[1400] Step 6:

[1401] Server: Analyzes preprocessed health and emotion data using a generative AI model. For example, it categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance. It also evaluates calories burned and exercise intensity based on exercise data, and sleep duration and quality based on sleep data.

[1402] Step 7:

[1403] Server: Integrates the assessment results and emotional data to analyze the overall health status, deriving specific insights such as, "Your calorie intake is high, but your emotional state is fatigued, so light exercise is recommended."

[1404] Step 8:

[1405] Server: Based on the analysis results, a customized health plan is generated for each user. Emotional data is also taken into consideration, providing a specific action plan with appropriate feedback and encouraging messages. For example, a specific health plan is generated, such as "Today you feel tired, so we suggest doing some light stretching" or "Tomorrow, reduce your calorie intake a little."

[1406] Step 9:

[1407] Server: Sends the generated health plan to the device.

[1408] Step 10:

[1409] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Do 30 minutes of relaxing yoga today."

[1410] Step 11:

[1411] User: Takes actions according to the health plan and enters their daily progress and emotional state into the application. For example, they might enter, "This time, I ate a lighter dinner to match my emotional state."

[1412] Step 12:

[1413] Terminal: Organizes newly collected progress data and emotion data and sends it to the server.

[1414] Step 13:

[1415] Server: Analyzes new progress and emotional data to assess goal achievement and areas for improvement. For example, it generates feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[1416] Step 14:

[1417] Server: Sends feedback to the device.

[1418] Step 15:

[1419] On-device: Provides feedback to users, suggests next steps, and provides advice to help them stay motivated, such as "If you keep going at this pace, you'll soon reach your goal weight" or "Reminder: Make sure you go to bed by 9 o'clock tonight."

[1420] Through these steps, users can continuously manage their health and act according to an optimal health plan that also takes into account their emotional state.

[1421] Example 2

[1422] 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."

[1423] In modern society, there is a demand for efficient management of people's health status and the provision of individually optimized health plans. However, conventional systems have difficulty integrating and analyzing a user's health and emotional data to provide feedback tailored to their individual health status. It is also difficult to generate a customized plan that takes into account the user's emotional state. In particular, there is a lack of systems that can collect and analyze health and emotional data separately and provide comprehensive health management, making it difficult to provide consistent health management.

[1424] 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.

[1425] In this invention, the server includes means for collecting health data and emotional data from a user, means for analyzing and quantifying the emotional data, and means for analyzing the preprocessed health data and emotional data using a generative AI model, thereby enabling the server to comprehensively analyze the user's health data and emotional data, generate a health plan optimized for each individual user, and provide feedback.

[1426] A "user" is an individual who utilizes the system to provide their health and emotional data.

[1427] "Health data" refers to information about a user's daily diet, exercise, and sleep.

[1428] "Emotion data" is information that indicates the user's emotional state, and is input as text or numerical values.

[1429] A "wearable device" is a device that automatically collects a user's exercise and sleep data. Examples include fitness trackers and smartwatches.

[1430] A "data package" is a consolidated form of all collected data that is sent to the server.

[1431] "Preprocessing" is the process of analyzing the data package sent to the server, filling in missing values, and standardizing the data format.

[1432] An "emotion engine" is a technology that analyzes emotional data and quantifies emotional states from text data.

[1433] A "generative AI model" is an artificial intelligence model that performs analysis using preprocessed health data and emotion data.

[1434] A "health plan" is a plan for maintaining and improving health that is customized for each individual user and created based on the results of data analysis.

[1435] "Feedback" refers to evaluations and advice provided to users based on progress data and analysis results.

[1436] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. The system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on that data. It is also capable of generating a customized health plan and providing feedback on progress.

[1437] Data collection

[1438] 1. The user opens a dedicated smartphone application and manually enters the details of their daily meals. For example, they might enter, "I had toast and scrambled eggs for breakfast." They also enter their emotional state. For example, they might record, "I feel very energetic today."

[1439] 2. The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches).

[1440] 3. The device aggregates all data into a single data package and sends it to the server, specifically via a REST API using JSON format.

[1441] Data Preprocessing

[1442] 1. The server analyzes the received data package, imputes missing values ​​using statistical methods and past data, and standardizes the data format. Specifically, this process is performed using the Python Pandas library.

[1443] 2. The server analyzes the emotion data using an emotion engine to quantify the user's emotional state. For example, it uses the Google Cloud Natural Language API to extract an emotion score from the text data.

[1444] Data analysis

[1445] 1. The server analyzes the preprocessed health and emotion data using a generative AI model. Specifically, it uses a neural network model with TensorFlow to classify the dietary data by nutrient and evaluate calorie intake and nutritional balance. For example, it calculates the calories and nutrients of "toast and scrambled eggs."

[1446] 2. The server evaluates the calorie consumption and exercise intensity based on the exercise data, and evaluates the sleep duration and quality based on the sleep data. These evaluation results are combined with the emotional data to analyze the user's overall health status. Specifically, the server evaluates heart rate and step count using the SciKit-Learn library.

[1447] Health plan generation

[1448] 1. Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[1449] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[1450] 2. The server sends the generated health plan to the terminal.

[1451] Feedback and Support

[1452] 1. The device notifies the user of the received health plan and displays specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1453] 2. The user acts according to the health plan and enters their daily progress into the application, for example, "I ate less calories at dinner today."

[1454] 3. The device organizes the progress data and new emotion data and sends them to the server.

[1455] 4. The server analyzes the new progress and emotion data to evaluate the progress of the goal and areas for improvement, generating feedback such as, "You're making good progress toward your goal," or "You'd be even more effective if you reduced the calories in your dinner a little more."

[1456] 5. The server sends the generated feedback to the device.

[1457] Specific examples

[1458] 1. A user enters into a smartphone application: "I had yogurt and fruit for breakfast today. My emotional state is very good." The application also syncs exercise and sleep data from a fitness tracker.

[1459] 2. The device organizes the data and sends it to the server.

[1460] 3. The server analyzes the data, including the total daily calorie intake, calories burned, and emotional state, and generates a health plan. For example, "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[1461] 4. The server sends the generated health plan to the terminal.

[1462] 5. The device displays notifications and instructions to the user, such as advice like "Try this recipe today."

[1463] 6. The user acts according to the health plan and enters their progress into the app. For example, "I ate a low-calorie dinner today and I feel good."

[1464] 7. The device organizes the new data and sends it to the server.

[1465] 8. The server analyzes the new data and generates feedback, such as "You're on track to reach your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more."

[1466] In this way, the entire system manages users' health and emotional data in an integrated manner, and provides individually optimized health plans and feedback, thereby supporting users in maintaining and improving their health.

[1467] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1468] Step 1:

[1469] The user opens a dedicated smartphone application and manually inputs the details of their daily meals, for example, "I had toast and scrambled eggs for breakfast," and their emotional state for that day, for example, "I feel very energetic today."

[1470] Input: User's daily diet and emotional state

[1471] Output: Food and emotion data stored on the user's smartphone

[1472] Step 2:

[1473] The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise duration) and sleep data (sleep duration, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches) using Bluetooth and Wi-Fi.

[1474] Input: User's dietary data, emotional data, exercise data, sleep data

[1475] Output: Integrated dataset on smartphone

[1476] Step 3:

[1477] The device integrates all data into a single data package and sends it to the server. Specifically, it creates the data in JSON format and sends it to the server using a REST API.

[1478] Input: Integrated dataset

[1479] Output: Data package sent to the server

[1480] Step 4:

[1481] The server analyzes the received data package and performs preprocessing on the data. Specifically, it uses the Python Pandas library to impute missing values ​​and standardize the data format. For example, it imputes missing sleep data with the average value from the past.

[1482] Input: Data package sent to the server

[1483] Output: Preprocessed dataset

[1484] Step 5:

[1485] The server analyzes the emotion data using an emotion engine (e.g., Google Cloud Natural Language API) and quantifies the emotional state. Specifically, it quantifies the input "very energetic" with a positive score.

[1486] Input: Preprocessed dataset

[1487] Output: Quantified emotion data

[1488] Step 6:

[1489] The server uses a generative AI model (e.g., a neural network model using TensorFlow) to analyze the preprocessed health and emotion data. Specifically, it categorizes the dietary data by nutrient and evaluates calorie intake and nutritional balance.

[1490] Input: Preprocessed health data, quantified emotion data

[1491] Output: Analysis results (nutritional balance, calories burned, quality of sleep, etc.)

[1492] Step 7:

[1493] Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[1494] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[1495] Input: Analysis results

[1496] Output: Customized health plan

[1497] Step 8:

[1498] The server sends the generated health plan to the device. Specifically, it creates the data in JSON format and sends it to the device using a REST API.

[1499] Enter: Customized Health Plan

[1500] Output: Health plan sent to the device

[1501] Step 9:

[1502] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1503] Input: Received Health Plan

[1504] Output: User notification and instructions for action

[1505] Step 10:

[1506] The user acts according to the health plan and inputs their daily progress into the application, for example, "I had a low-calorie dinner today."

[1507] Input: User progress data

[1508] Output: Progress data saved on the device

[1509] Step 11:

[1510] The device organizes the new progress data and emotion data and sends it to the server. Specifically, the newly collected data is again integrated in JSON format and sent via a REST API.

[1511] Input: New progress and emotion data

[1512] Output: Data package sent to the server

[1513] Step 12:

[1514] The server analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as, "You're on track with your goal," or "You'd be better off if you reduced the calories in your dinner a little more."

[1515] Input: New progress and emotion data

[1516] Output: Evaluation results and feedback

[1517] Step 13:

[1518] The server sends the evaluation results and feedback to the device. Specifically, the feedback is formatted in JSON and sent to the device using a REST API.

[1519] Input: Evaluation results and feedback

[1520] Output: Feedback sent to the terminal

[1521] Step 14:

[1522] The device will then notify the user of the received feedback and provide instructions and suggestions for the next steps, such as "You're on track to reach your goal" or "You'll be even more effective if you cut back on the calories at dinner."

[1523] Input: Feedback received

[1524] Output: Notification to the user and next action instructions

[1525] Through these steps, users can obtain the optimal health plan based on their emotional state that day, and receive continuous improvement and support.

[1526] (Application example 2)

[1527] 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."

[1528] Many conventional health management systems track a user's diet, exercise, and sleep data and provide a health plan. However, these systems do not take emotional states into account, limiting the effectiveness of personalized health plans. Furthermore, the content provided is uniform, lacking a means to provide personalized content that addresses the user's individual health status and emotions. As a result, users lose motivation to continue following their health plan. This invention aims to solve this problem by proposing a system that integrates a user's individual health data and emotional data to provide an optimal health plan and personalized health and wellness-related content.

[1529] 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 collecting health data from the user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data and generating an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, and means for providing personalized health and wellness-related content based on the health plan. This enables the user to obtain an optimal health plan and personalized content according to their emotional state and health condition on that day, thereby increasing their motivation to continuously implement the health plan.

[1530] "Health Data" refers to information about a user's diet, exercise, sleep, and other health conditions.

[1531] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze. Specifically, this includes imputing missing values, standardizing data, and standardizing formats.

[1532] "Health Plan" refers to specific guidelines and advice generated based on a user's individual health and emotional data, including exercise regimes, meal plans, sleep schedules, etc.

[1533] "Personalized Content" means personalized health and wellness related information, videos, audio, articles, etc. that are delivered to you based on your individual health and emotional state.

[1534] "Generative AI model" refers to the artificial intelligence algorithms used to analyze collected data and generate health plans and content.

[1535] "Feedback" refers to evaluating the progress of the user's health plan and providing suggestions for improvement or further advice.

[1536] "Emotion data" refers to information that indicates the user's emotional state using numerical values ​​or categories. Specifically, it includes emotional states such as "energetic," "tired easily," and "high stress."

[1537] "Individualization" refers to providing optimal information and plans according to each user's different needs and circumstances.

[1538] This invention relates to a system that collects individual user health and emotional data and provides health plans and personalized health and wellness-related content based on that data. The following describes the processing of the program that realizes this system.

[1539] Data collection

[1540] Users manually input their daily diet and emotional state using a dedicated application on their smartphone or head-mounted display. For example, they can enter information such as "I had yogurt and fruit for breakfast" or "I feel very energetic today." Additionally, exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) are automatically synchronized using a fitness tracker.

[1541] Data Preprocessing

[1542] The server receives the collected data and performs preprocessing. Specifically, it fills in missing values ​​and standardizes the format. It then uses an emotion engine to analyze the user's emotion data and convert it into numerical values ​​and categories.

[1543] Data analysis and health plan generation

[1544] The server analyzes the preprocessed health and emotion data using a generative AI model. Based on the analysis results, it generates a customized health plan for each user. This health plan includes specific guidelines and advice. For example, it suggests things like "walking for 30 minutes three times a week," "eating less than 1,500 calories a day," and "going to bed at 10 p.m. every night."

[1545] Content Recommendation

[1546] Based on the generated health plan, the server provides users with personalized health and wellness content, including health-related videos, audio, and articles, which users can view and interact with through a dedicated application.

[1547] Feedback and Support

[1548] The user carries out actions according to the health plan and enters their progress and emotional state into a dedicated application. For example, they might enter information such as, "I ate less calories at dinner today, and I'm feeling good." The server analyzes the new data collected and evaluates their progress and areas for improvement. Based on this, it provides feedback to the user. For example, it may provide specific advice such as, "You're on track to reach your goal," or "You'd be even more effective if you reduced the calories at dinner a little more."

[1549] Examples of concrete examples and prompts

[1550] For example, if a user inputs "I had yogurt and fruit for breakfast today. I feel very energetic," and synchronizes exercise data (7,000 steps, 45 minutes of exercise, average heart rate 70 BPM) and sleep data (7 hours of sleep, good quality of sleep) from a fitness tracker, the server will generate a health plan based on this data and recommend appropriate content.

[1551] An example of a prompt sentence for input to a generative AI model is as follows:

[1552] User's dietary data: yogurt and fruit

[1553] User's emotional state: Very energetic

[1554] Exercise data: 7000 steps, exercise time 45 minutes, average heart rate 70 BPM

[1555] Sleep data: 7 hours of sleep, good quality

[1556] Use this data to generate an optimal health plan and personalized content to support its implementation.

[1557] In this way, users can obtain the optimal health plan and personalized content based on their emotional and health state on that day, which increases their motivation to continue implementing the health plan and enables effective health management.

[1558] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1559] Step 1:

[1560] Device: Using a dedicated application on a smartphone or head-mounted display, the user manually inputs their daily diet and emotional state. Examples of input data include "I had yogurt and fruit for breakfast" and "I feel very energetic today." In addition, the wearable device automatically synchronizes exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality). All of this health-related information is included in the input data.

[1561] Input: Food data, Emotion data, Exercise data, Sleep data

[1562] Output: Integrated health data package

[1563] Step 2:

[1564] Terminal: Sends collected health data to the server using a secure and reliable communication protocol and uploads the data package to the server.

[1565] Input: Integrated Health Data Package

[1566] Output: Sending the data package to the server

[1567] Step 3:

[1568] Server: Preprocesses the received data package. If there is missing or incomplete data, it is filled in using statistical methods or past data. Next, the data format is standardized and an emotion engine is used to convert emotion data into numerical values ​​or categories. This results in a consistent dataset.

[1569] Input: Integrated Health Data Package

[1570] Output: Preprocessed dataset

[1571] Step 4:

[1572] Server: The preprocessed data is input into the generative AI model and analyzed. Specifically, nutritional value and calories are evaluated from dietary data, calories burned and exercise intensity from exercise data, and sleep quality and duration from sleep data. The model integrates this data and analyzes overall health status.

[1573] Input: Preprocessed dataset

[1574] Output: Analysis results

[1575] Step 5:

[1576] Server: Based on the analysis results, an individual health plan is generated. The generated health plan includes specific guidelines and advice. For example, a customized plan may be created, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[1577] Input: Analysis results

[1578] Output: Health Plan

[1579] Step 6:

[1580] Server: Based on the generated health plan, retrieves and provides personalized health and wellness-related content to the user. Content includes health-related videos, audio, articles, etc. The server selects appropriate content and sends it to the device.

[1581] Enter: Health Plan

[1582] Output: personalized content

[1583] Step 7:

[1584] Device: Informs the user of their health plan and personalized content, allowing them to take specific courses of action or view the content provided.

[1585] Input: Health plans, personalized content

[1586] Output: Notification to terminal

[1587] Step 8:

[1588] User: Takes actions according to the health plan and inputs their progress and emotional state into a dedicated application. For example, they receive feedback such as, "I ate less calories at dinner today. I'm feeling good."

[1589] Input: User results and feedback

[1590] Output: Updated progress data

[1591] Step 9:

[1592] Device: Sends newly collected progress and emotion data to the server, where it is stored for the next analysis.

[1593] Input: Updated progress data

[1594] Output: Sending progress data to the server

[1595] Step 10:

[1596] Server: Analyzes the latest progress data and evaluates the degree of goal achievement and areas for improvement. For example, it generates feedback such as "You are making good progress toward your goal" or "You would be more effective if you reduced the calories in your dinner a little more" and sends it to the device.

[1597] Input: Latest progress data

[1598] Output: Evaluation results and feedback

[1599] In this way, specific data processing and actions are performed at each step, allowing users to be provided with the optimal health plan and personalized content based on their emotional and health state on that day, enabling them to continuously implement their health plan.

[1600] 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.

[1601] 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.

[1602] 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.

[1603] [Fourth embodiment]

[1604] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1605] 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.

[1606] 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).

[1607] 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.

[1608] 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.

[1609] 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).

[1610] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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.

[1615] 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.

[1616] 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."

[1617] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[1618] Program processing (natural language explanation)

[1619] Data collection

[1620] 1. User: Enters daily meal information through a smartphone application, providing detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[1621] 2. Device: The application stores the entered data and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[1622] 3. Terminal: Consolidates all data into one package and sends it to the server.

[1623] Data Preprocessing

[1624] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data.

[1625] 2. Server: Standardizes the data format and converts it into a form suitable for analysis.

[1626] Data analysis

[1627] 1. Server: Analyzes the user's health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc.

[1628] 2. Server: Evaluates calories burned and exercise intensity based on exercise data.

[1629] 3. Server: Based on sleep data, evaluates sleep duration and quality and assesses overall health.

[1630] Health plan generation

[1631] 1. Server: Based on the results of data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it generates a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[1632] 2. Server: Sends the generated health plan to the terminal.

[1633] Feedback and Support

[1634] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[1635] 2. User: Carries out the actions according to the plan and enters progress into the application.

[1636] 3. Terminal: Collects new data from the user and sends it to the server.

[1637] 4. Server: Analyzes new data and assesses progress toward goals and areas for improvement.

[1638] 5. Server: Generates feedback and sends it to the device. For example, it provides feedback to the user such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[1639] Specific examples

[1640] Example 1: User trying to lose weight

[1641] 1. User: Opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[1642] 2. Terminal: Organizes the entered data and sends it to the server.

[1643] 3. Server: Based on the received data, calculates the total daily calorie intake and calories burned and performs analysis based on the user's weight loss goal.

[1644] 4. Server: Based on the analysis results, a specific health plan is generated, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed by 10 p.m.", and sent to the device.

[1645] 5. Terminal: Notifies the user and displays specific instructions for action.

[1646] 6. User: Follows the plan and enters progress into the app.

[1647] 7. Terminal: Organizes new data and sends it to the server.

[1648] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[1649] In this way, users can get the best health plan based on real data and get continuous improvement and support.

[1650] The processing flow will be explained below.

[1651] Step 1:

[1652] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, enters "I had toast and scrambled eggs for breakfast." Also, enters data for lunch and dinner in the same way.

[1653] Step 2:

[1654] Device: Stores the entered food data and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[1655] Step 3:

[1656] Device: All collected data (diet, exercise, sleep) is organized into a single data package and sent to the server.

[1657] Step 4:

[1658] Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[1659] Step 5:

[1660] Server: Analyzes pre-processed health data using a generative AI model. For example, categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance.

[1661] Step 6:

[1662] Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined to analyze overall health status.

[1663] Step 7:

[1664] Server: Based on the analysis results, a customized health plan is generated for each user. For example, a specific health plan such as "30 minutes of aerobic exercise three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated.

[1665] Step 8:

[1666] Server: Sends the generated health plan to the device.

[1667] Step 9:

[1668] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1669] Step 10:

[1670] User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[1671] Step 11:

[1672] Device: Organizes newly collected progress data and sends it to the server.

[1673] Step 12:

[1674] Server: Analyzes new progress data and evaluates goal achievement and areas for improvement, generating feedback such as "You're on track to achieve your goal" or "You could be even more effective if you cut back on the calories at dinner."

[1675] Step 13:

[1676] Server: Sends feedback to the device.

[1677] Step 14:

[1678] Device: Provides feedback to the user, suggests next steps, and provides advice to help maintain motivation.

[1679] Through these steps, users can continuously manage their health status and act in accordance with an optimal health plan.

[1680] Example 1

[1681] 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."

[1682] Health management is an important issue in modern society. However, many people find it difficult to properly collect and analyze their own health data and develop effective health plans. Furthermore, many health management systems on the market lack the ability to comprehensively analyze individual data and provide feedback, making it difficult for users to achieve optimal health management. This invention aims to provide a system that collects and analyzes individual users' health data and provides customized health plans and continuous feedback.

[1683] 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.

[1684] In this invention, the server includes a means for collecting health data from users, a means for pre-processing the health data transmitted to the server, and a means for analyzing the pre-processed data to generate an individual health plan, thereby enabling the health data of each individual user to be appropriately collected and analyzed and a customized health plan to be provided.

[1685] "Health data" refers to information necessary for assessing a user's health status, such as diet, exercise, and sleep information.

[1686] "Server" refers to the central management system that processes data received from users, generates health plans, and provides feedback.

[1687] "Preprocessing" refers to the data preparation work required before data analysis, such as imputing missing values ​​and standardizing the format of received health data.

[1688] "Health Plan" refers to a plan that includes specific diet, exercise, and sleep instructions customized based on the user's health status.

[1689] "Feedback" refers to evaluations and advice provided based on a user's actions and progress.

[1690] "Generative AI models" refer to artificial intelligence algorithms and models used to analyze data and generate health plans.

[1691] "Tracking" refers to recording a user's activities and status and collecting data on an ongoing basis.

[1692] "Data Package" means all health data collected from a user in one format.

[1693] The system of this invention is an AI system that collects and analyzes individual health data of users and provides optimal health plans. This system is capable of evaluating individual health conditions based on the user's diet, exercise, and sleep data, generating customized health plans, and providing feedback.

[1694] Hardware and Software

[1695] The system is implemented using the following hardware and software:

[1696] Smartphone (user device)

[1697] Wearable devices (e.g., Fitbit, Apple Watch)

[1698] Server (cloud server)

[1699] Smartphone application (health management app)

[1700] Python libraries for running generative AI models (e.g., TensorFlow, PyTorch)

[1701] Program Implementation

[1702] The program for this system is executed as follows:

[1703] Data collection

[1704] Users input their daily meal plans through a smartphone application. For example, they can provide detailed meal information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." Furthermore, the device connects to a wearable device and automatically synchronizes exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality).

[1705] All data is packaged in JSON format and sent securely to the server over HTTPS. Specifically, the device makes an API request and sends the data to the server via a POST request.

[1706] Data Preprocessing

[1707] The server analyzes the received data package and performs preprocessing on the data. For example, if there are missing values, it fills them in using statistical methods or past data. It also standardizes the data format and stores it in a unified format in a table in the database. Specifically, it parses the data and executes a script to convert it into a unified format (e.g., unifying the timestamp format).

[1708] Data analysis

[1709] The server uses the generative AI model to analyze the user's health data. For example, it categorizes dietary data by nutrient and evaluates calorie intake, protein, fat, carbohydrates, etc. It also evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. This allows for an assessment of the user's overall health.

[1710] Health plan generation

[1711] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[1712] Feedback and Support

[1713] The device notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Plan to go to the gym tomorrow." The user carries out the actions according to the plan and enters their progress into the application. The new data is organized and sent to the server, which analyzes it, evaluates the progress of goal achievement and areas for improvement, and generates feedback and sends it to the device.

[1714] Specific examples

[1715] Example 1: User trying to lose weight

[1716] 1. A user opens the app on their smartphone, enters "fruit and yogurt" as their breakfast, and automatically syncs exercise and sleep data from their fitness tracker.

[1717] 2. The terminal organizes the entered data and sends it to the server.

[1718] 3. Based on the received data, the server calculates the total daily calorie intake and calories burned and analyzes it based on the user's weight loss goal.

[1719] 4. Based on the analysis results, the server generates a specific health plan such as "walk for 30 minutes three times a week," "eat no more than 1,500 calories a day," and "go to bed by 10 p.m." and sends it to the device.

[1720] 5. The device notifies the user and displays specific instructions for action.

[1721] 6. The user acts according to the plan and enters their progress into the app.

[1722] 7. The device organizes the new data and sends it to the server.

[1723] 8. The server analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[1724] Using this system, users can obtain the optimal health plan based on their individual health condition and receive ongoing support and feedback.

[1725] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1726] Step 1:

[1727] Data collection

[1728] Users manually enter their daily dietary information using a smartphone application, providing detailed dietary information such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner."

[1729] Input: User's meal information (text format).

[1730] How it works: The user enters specific meal details into the app's input form.

[1731] Output: The entered meal information is saved in the app's database.

[1732] The device works with wearable devices (e.g., Fitbit, Apple Watch) and automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality).

[1733] Input: Exercise and sleep data from wearable devices.

[1734] How it works: The app uses the wearable device API to retrieve data.

[1735] Output: The acquired data is saved in the app's database.

[1736] The device then compiles all the data into a single package in JSON format and sends it securely to the server using HTTPS.

[1737] Input: Integrated health data (diet, exercise, sleep) converted to JSON format.

[1738] How it works: The device makes an API request and sends data to the server in a POST request.

[1739] Output: JSON formatted data is sent to the server.

[1740] Step 2:

[1741] Data Preprocessing

[1742] The server analyzes the received data package and performs preprocessing on the data, for example, imputing missing values ​​using statistical methods or past data.

[1743] Input: Health data package in JSON format sent to the server.

[1744] How it works: A server-side script validates the data (e.g., checks for blanks) and imputes missing values.

[1745] Output: Data with missing values ​​imputed and passing validation.

[1746] The server standardizes the data format and stores it in a uniform format in tables within the database.

[1747] Input: Health data that has passed validation.

[1748] What it does: Runs a script that parses the data and converts it to a unified format (e.g. unified timestamp format).

[1749] Output: The data converted into a unified format is saved in the database.

[1750] Step 3:

[1751] Data analysis

[1752] The server analyzes the user's health data using a generative AI model, inputting dietary data into the model, classifying it by nutrient, and evaluating calorie intake, protein, fat, carbohydrates, etc.

[1753] Input: Health data converted into a unified format.

[1754] How it works: Food data is input into the AI ​​model, which then classifies and evaluates each nutrient.

[1755] Output: Classification and evaluation results for each nutrient.

[1756] The server evaluates exercise intensity and calories burned based on the exercise data.

[1757] Input: Motion data converted into a unified format.

[1758] Operation: Obtains exercise data from the database and calculates calories burned using calculation logic.

[1759] Output: Evaluation results of exercise intensity and calories burned.

[1760] The server evaluates sleep duration and quality based on sleep data, and assesses overall health.

[1761] Input: Sleep data converted into a unified format.

[1762] How it works: Sleep data is fed into the AI ​​model, and the output is interpreted using evaluation logic.

[1763] Output: Sleep duration and quality assessment, overall health status.

[1764] Step 4:

[1765] Health plan generation

[1766] Based on the data analysis results, the server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) and generates a specific action plan. For example, it provides a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night."

[1767] Input: Data analysis results.

[1768] What it does: Analyzes the output of the AI ​​model and runs a script to set specific values ​​(e.g., calorie limit).

[1769] Output: A specific health plan for each user.

[1770] The server sends the generated health plan to the terminal in JSON format.

[1771] Input: Generated health plan.

[1772] Operation: Generates a health plan as an API response and sends it to the device. Ensures secure communication using HTTPS.

[1773] Output: Health plan sent to the device.

[1774] Step 5:

[1775] Feedback and Support

[1776] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[1777] Input: Health plan received from server.

[1778] What it does: Sends a push notification to the user using the notification system and displays details in the app.

[1779] Output: Specific instructions for action displayed to the user.

[1780] The user performs actions according to the plan and enters their progress into the application.

[1781] Input: User behavior progress data.

[1782] How it works: The user fills in a form within the app with progress information and submits it.

[1783] Output: Behavioral progress data stored within the app.

[1784] The terminal organizes new data from the user and sends it to the server.

[1785] Input: Progress data.

[1786] Behavior: The entered data is stored in an internal database and sent back to the server.

[1787] Output: Progress data sent to the server.

[1788] The server analyzes the new data and assesses progress toward achieving goals and areas for improvement.

[1789] Input: Newly received progress data.

[1790] What it does: Feeds new data back into the AI ​​model, running the logic to calculate goal achievement.

[1791] Output: Evaluation of goal achievement and identification of areas for improvement.

[1792] The server generates feedback based on the evaluation results and sends it to the device, providing specific feedback such as "You're doing well" or "Your dinner is too high in calories, so please improve it."

[1793] Input: Evaluation results and improvements.

[1794] Behavior: Runs a script that generates a feedback message and sends it to the device as an API response.

[1795] Output: Feedback message sent to the terminal.

[1796] (Application example 1)

[1797] 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."

[1798] Properly assessing individual users' health status and providing customized health plans are important in modern health management. However, current systems struggle to generate and provide effective health plans for users due to incomplete collection of health data and incomprehensive analysis. Furthermore, they lack the means to provide feedback based on progress data and continuously support health management. This makes it difficult for users to effectively achieve their health goals.

[1799] 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.

[1800] In this invention, the server includes means for collecting health data from a user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data using a generative AI model to generate an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, means for transmitting data to the server as an integrated package, and means for collecting dietary information, exercise data, and sleep data from the user and evaluating the individual's health condition based on the data. This makes it possible to comprehensively collect and analyze various health data entered by the user and provide a customized health plan tailored to the individual's health condition and continuous feedback.

[1801] A "user" is an individual who uses the system to provide health data.

[1802] "Health data" refers to health-related information such as a user's dietary information, exercise data, and sleep data.

[1803] "Server" means a computer system that collects, pre-processes, and analyzes health data, and generates and provides health plans.

[1804] "Preprocessing" refers to processing collected health data such as filling in missing values ​​and standardizing the data.

[1805] A "generative AI model" is an artificial intelligence model that evaluates a user's health status based on health data and generates a customized health plan.

[1806] "Health Plan" refers to specific behavioral guidelines generated based on a user's individual health status.

[1807] "Progress data" refers to data resulting from a user's actions in accordance with a health plan.

[1808] "Feedback" refers to evaluations and suggestions for improvement provided to users based on new progress data.

[1809] "Packaging" refers to the integration of multiple collected health data into a single dataset.

[1810] A "smartphone" is a portable device for inputting or displaying a user's health data.

[1811] A "wearable device" is a device worn by a user to automatically collect exercise and sleep data.

[1812] "Dietary information" is data relating to the types and amounts of food consumed by the user.

[1813] "Exercise data" refers to data such as the amount of exercise, exercise time, and heart rate of the user.

[1814] "Sleep data" refers to data relating to the user's sleep time and sleep quality.

[1815] "Tracking" refers to the continuous monitoring and recording of a user's diet, exercise, and sleep data.

[1816] An "action plan" is a plan that provides specific guidelines for the actions a user must take to achieve their health goals.

[1817] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan. This system evaluates the individual health condition based on the user's diet, exercise, and sleep data, generates a customized health plan, and provides feedback.

[1818] Hardware and software used

[1819] This system is composed of a smartphone, a wearable device, and a server. The smartphone is used as a means for users to input daily dietary data and receive health plans and feedback. The wearable device is used as a means for automatically collecting exercise and sleep data. The server plays a central role in analyzing the collected data and generating and providing health plans.

[1820] Data collection

[1821] The smartphone application allows users to input their daily dietary information, such as "toast and scrambled eggs for breakfast, chicken salad for lunch, and steak and vegetables for dinner." In addition, exercise data (number of steps, heart rate, and exercise time) and sleep data (sleep time and quality) are automatically synchronized from the wearable device. All data is integrated into a single package and sent to the server.

[1822] Data Preprocessing

[1823] The server analyzes the received data package and performs pre-processing such as imputing and standardizing missing values. For example, if there are missing values, they are imputed using statistical methods or historical data.

[1824] Data analysis

[1825] The server uses the generative AI model to analyze the user's health data. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality. The overall health status is evaluated based on the analysis results.

[1826] Health plan generation

[1827] Based on the results of the data analysis, the server sets health goals for each user (e.g., weight loss, muscle gain, improved sleep) and generates a specific action plan. A specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[1828] Feedback and Support

[1829] The server collects new data as needed and evaluates the user's progress. For example, based on the newly collected data, it generates feedback such as "You're steadily moving towards your goal" or "Your dinner is a little high in calories, so please improve it." The smartphone app notifies the user and displays specific instructions and suggestions for action.

[1830] Specific prompt sentences

[1831] Here is an example of what the user might enter:

[1832] text

[1833] User ID: 12345

[1834] Please enter the following data today:

[1835] Breakfast: Yogurt and banana

[1836] Lunch: Greek salad

[1837] Dinner: Stir-fried chicken and vegetables

[1838] Exercise: Sync your fitness tracker data

[1839] Sleep: Sync your sleep tracker data

[1840] The AI ​​system will analyze your health condition and notify you of the results.

[1841] Through this system, users can obtain an optimal health plan based on actual data and effectively achieve their health goals with ongoing support.

[1842] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1843] Step 1:

[1844] Users enter their daily meal information into a smartphone application, recording detailed meal details such as "toast and scrambled eggs for breakfast, chicken salad for lunch, steak and vegetables for dinner."

[1845] Input: Meal details (text data)

[1846] Output: Food data recorded on a smartphone

[1847] Step 2:

[1848] The device automatically syncs exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from the wearable device.

[1849] Input: Sensor data from a wearable device

[1850] Output: Exercise and sleep data recorded on a smartphone

[1851] Step 3:

[1852] The device consolidates all data (food, exercise, and sleep data) into a single package and sends it to the server, where it is packaged in a standard format such as JSON.

[1853] Input: Food data, exercise data, sleep data

[1854] Output: Consolidated data package sent to the server

[1855] Step 4:

[1856] The server analyzes the received data package and performs preprocessing such as imputing missing values ​​and standardizing the data. For example, if there are missing values, they are imputed using statistical methods or past data.

[1857] Input: Integrated Data Package

[1858] Output: Preprocessed data

[1859] Step 5:

[1860] The server analyzes the preprocessed data using a generative AI model. Dietary data is categorized by nutrient and evaluated for calorie intake, protein, fat, carbohydrates, etc. Exercise data is evaluated for calories burned and exercise intensity, and sleep data is evaluated for sleep duration and quality.

[1861] Input: Preprocessed data

[1862] Output: Various health indicators and analysis results

[1863] Step 6:

[1864] The server sets health goals for each user (e.g., weight loss, muscle gain, sleep improvement) based on the analysis results and generates a specific action plan. For example, a specific health plan such as "eat less than 1,500 calories a day," "do 30 minutes of aerobic exercise three times a week," and "go to bed at 10 p.m. every night" is generated and sent to the user's smartphone.

[1865] Input: Various health indicators and analysis results

[1866] Output: Specific health plan

[1867] Step 7:

[1868] The device will notify the user of the generated health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Make plans to go to the gym tomorrow."

[1869] Input: Specific Health Plan

[1870] Output: Instructions and suggestions for action communicated to the user

[1871] Step 8:

[1872] As users follow their health plan and enter their progress into a smartphone application, new data is collected and sent to a server.

[1873] Input: User progress data (text data, sensor data)

[1874] Output: Progress data sent to the server

[1875] Step 9:

[1876] The server analyzes the new progress data, assesses the degree of goal achievement and areas for improvement, and then reanalyzes it using a generative AI model to generate feedback such as "You're on track" or "Your dinner is on the high side, so please improve it."

[1877] Input: New progress data

[1878] Output: Feedback and evaluation results

[1879] Step 10:

[1880] The device receives the feedback and notifies the user, who can then review their health plan based on the feedback and reflect it in their next actions.

[1881] Input: Feedback and evaluation results

[1882] Output: Feedback given to the user

[1883] Through this series of processing steps, users will receive an optimal health plan based on their individual data, and will receive continuous feedback and support to achieve their health goals.

[1884] 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.

[1885] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. This system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on this data. Furthermore, it is possible to generate a customized health plan and provide feedback on progress.

[1886] Program processing (natural language explanation)

[1887] Data collection

[1888] 1. User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user might enter "I had toast and scrambled eggs for breakfast." The user also enters data for lunch and dinner in the same way. The user also enters their emotional state for the day through the application. For example, the user might enter "I feel very energetic today."

[1889] 2. Device: The application stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[1890] 3. Terminal: Consolidates all data into one data package and sends it to the server.

[1891] Data Preprocessing

[1892] 1. Server: Analyzes the received data package and performs data preprocessing, for example, imputing missing values ​​using statistical methods or historical data, and standardizing the data format.

[1893] 2. Server: Using the emotion engine, analyze the user's emotion data and quantify their emotional state.

[1894] Data analysis

[1895] 1. Server: Analyzes pre-processed health and emotion data using generative AI models. For example, categorize dietary data by nutrient and evaluate calorie intake and nutritional balance.

[1896] 2. Server: Evaluates calories burned and exercise intensity based on exercise data, and evaluates sleep duration and quality based on sleep data. These evaluation results are combined with emotional data to analyze overall health status.

[1897] Health plan generation

[1898] 1. Server: Based on the results of data analysis, it generates a customized health plan for each user. It takes into account emotional data and provides a specific action plan with appropriate feedback and encouraging messages. For example, it generates a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[1899] 2. Server: Sends the generated health plan to the terminal.

[1900] Feedback and Support

[1901] 1. Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1902] 2. User: Takes action according to the health plan and enters daily progress into the application. For example, "I ate less calories at dinner today."

[1903] 3. Terminal: Organizes the newly collected progress data and emotion data and sends them to the server.

[1904] 4. Server: Analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[1905] 5. Server: Sends feedback to the device.

[1906] Specific examples

[1907] 1. User: Through a smartphone application, the user inputs, "I had yogurt and fruit for breakfast today. I feel very energetic." The application also automatically syncs exercise and sleep data from a fitness tracker.

[1908] 2. Terminal: Organizes the entered data and sends it to the server.

[1909] 3. Server: Based on the received data, analyzes the total daily calorie intake, calories burned, and emotional state, and generates a health plan based on the user's weight loss goals.

[1910] 4. Server: Based on the analysis results, a specific health plan such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night" is generated and sent to the device.

[1911] 5. Device: Notifies the user and displays specific instructions for action. Provides advice tailored to the user's emotional state, such as "Try this recipe today."

[1912] 6. User: Follows the health plan and enters progress and emotional state into the app. For example, "I ate a low-calorie dinner today and I feel good."

[1913] 7. Terminal: Organizes new data and sends it to the server.

[1914] 8. Server: Analyzes the data and generates feedback such as "You're making good progress towards your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more," and sends it to the device.

[1915] In this way, users can get the optimal health plan according to their emotional state on that day, and receive continuous improvement and support.

[1916] The processing flow will be explained below.

[1917] Step 1:

[1918] User: Opens a dedicated smartphone application and manually enters the details of daily meals. For example, the user enters, "I had oatmeal and a banana for breakfast." The user also enters the user's emotional state for that day through the application. For example, the user enters, "I feel very tired today."

[1919] Step 2:

[1920] Device: Stores the entered food, exercise, sleep, and emotional data, and automatically synchronizes exercise data (steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers).

[1921] Step 3:

[1922] Terminal: Organizes all data into a single data package and sends it to the server.

[1923] Step 4:

[1924] Server: Analyzes the received data package and performs preprocessing of the data, for example, imputing missing values ​​using statistical methods or past data, and standardizing the data format.

[1925] Step 5:

[1926] Server: Using the emotion engine, analyzes the user's emotion data and quantifies their emotional state. In this process, each emotion is converted into a numerical value, which can be used for calculations.

[1927] Step 6:

[1928] Server: Analyzes preprocessed health and emotion data using a generative AI model. For example, it categorizes dietary data by nutrient and evaluates calorie intake and nutritional balance. It also evaluates calories burned and exercise intensity based on exercise data, and sleep duration and quality based on sleep data.

[1929] Step 7:

[1930] Server: Integrates the assessment results and emotional data to analyze the overall health status, deriving specific insights such as, "Your calorie intake is high, but your emotional state is fatigued, so light exercise is recommended."

[1931] Step 8:

[1932] Server: Based on the analysis results, a customized health plan is generated for each user. Emotional data is also taken into consideration, providing a specific action plan with appropriate feedback and encouraging messages. For example, a specific health plan is generated, such as "Today you feel tired, so we suggest doing some light stretching" or "Tomorrow, reduce your calorie intake a little."

[1933] Step 9:

[1934] Server: Sends the generated health plan to the device.

[1935] Step 10:

[1936] Device: Notifies the user of the received health plan and displays specific instructions and suggestions for action. For example, it provides advice such as "Try this recipe today" or "Do 30 minutes of relaxing yoga today."

[1937] Step 11:

[1938] User: Takes actions according to the health plan and enters their daily progress and emotional state into the application. For example, they might enter, "This time, I ate a lighter dinner to match my emotional state."

[1939] Step 12:

[1940] Terminal: Organizes newly collected progress data and emotion data and sends it to the server.

[1941] Step 13:

[1942] Server: Analyzes new progress and emotional data to assess goal achievement and areas for improvement. For example, it generates feedback such as "You're on track with your goal" or "You'd be better off if you reduced the calories in your dinner a bit."

[1943] Step 14:

[1944] Server: Sends feedback to the device.

[1945] Step 15:

[1946] On-device: Provides feedback to users, suggests next steps, and provides advice to help them stay motivated, such as "If you keep going at this pace, you'll soon reach your goal weight" or "Reminder: Make sure you go to bed by 9 o'clock tonight."

[1947] Through these steps, users can continuously manage their health and act according to an optimal health plan that also takes into account their emotional state.

[1948] Example 2

[1949] 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."

[1950] In modern society, there is a demand for efficient management of people's health status and the provision of individually optimized health plans. However, conventional systems have difficulty integrating and analyzing a user's health and emotional data to provide feedback tailored to their individual health status. It is also difficult to generate a customized plan that takes into account the user's emotional state. In particular, there is a lack of systems that can collect and analyze health and emotional data separately and provide comprehensive health management, making it difficult to provide consistent health management.

[1951] 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.

[1952] In this invention, the server includes means for collecting health data and emotional data from a user, means for analyzing and quantifying the emotional data, and means for analyzing the preprocessed health data and emotional data using a generative AI model, thereby enabling the server to comprehensively analyze the user's health data and emotional data, generate a health plan optimized for each individual user, and provide feedback.

[1953] A "user" is an individual who utilizes the system to provide their health and emotional data.

[1954] "Health data" refers to information about a user's daily diet, exercise, and sleep.

[1955] "Emotion data" is information that indicates the user's emotional state, and is input as text or numerical values.

[1956] A "wearable device" is a device that automatically collects a user's exercise and sleep data. Examples include fitness trackers and smartwatches.

[1957] A "data package" is a consolidated form of all collected data that is sent to the server.

[1958] "Preprocessing" is the process of analyzing the data package sent to the server, filling in missing values, and standardizing the data format.

[1959] An "emotion engine" is a technology that analyzes emotional data and quantifies emotional states from text data.

[1960] A "generative AI model" is an artificial intelligence model that performs analysis using preprocessed health data and emotion data.

[1961] A "health plan" is a plan for maintaining and improving health that is customized for each individual user and created based on the results of data analysis.

[1962] "Feedback" refers to evaluations and advice provided to users based on progress data and analysis results.

[1963] This invention relates to an AI system that collects and analyzes individual user health data and provides an optimal health plan that includes emotional information. The system uses an emotion engine to collect emotional data, in addition to diet, exercise, and sleep data, and evaluates the user's health based on that data. It is also capable of generating a customized health plan and providing feedback on progress.

[1964] Data collection

[1965] 1. The user opens a dedicated smartphone application and manually enters the details of their daily meals. For example, they might enter, "I had toast and scrambled eggs for breakfast." They also enter their emotional state. For example, they might record, "I feel very energetic today."

[1966] 2. The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise time) and sleep data (sleep time, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches).

[1967] 3. The device aggregates all data into a single data package and sends it to the server, specifically via a REST API using JSON format.

[1968] Data Preprocessing

[1969] 1. The server analyzes the received data package, imputes missing values ​​using statistical methods and past data, and standardizes the data format. Specifically, this process is performed using the Python Pandas library.

[1970] 2. The server analyzes the emotion data using an emotion engine to quantify the user's emotional state. For example, it uses the Google Cloud Natural Language API to extract an emotion score from the text data.

[1971] Data analysis

[1972] 1. The server analyzes the preprocessed health and emotion data using a generative AI model. Specifically, it uses a neural network model with TensorFlow to classify the dietary data by nutrient and evaluate calorie intake and nutritional balance. For example, it calculates the calories and nutrients of "toast and scrambled eggs."

[1973] 2. The server evaluates the calorie consumption and exercise intensity based on the exercise data, and evaluates the sleep duration and quality based on the sleep data. These evaluation results are combined with the emotional data to analyze the user's overall health status. Specifically, the server evaluates heart rate and step count using the SciKit-Learn library.

[1974] Health plan generation

[1975] 1. Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[1976] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[1977] 2. The server sends the generated health plan to the terminal.

[1978] Feedback and Support

[1979] 1. The device notifies the user of the received health plan and displays specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[1980] 2. The user acts according to the health plan and enters their daily progress into the application, for example, "I ate less calories at dinner today."

[1981] 3. The device organizes the progress data and new emotion data and sends them to the server.

[1982] 4. The server analyzes the new progress and emotion data to evaluate the progress of the goal and areas for improvement, generating feedback such as, "You're making good progress toward your goal," or "You'd be even more effective if you reduced the calories in your dinner a little more."

[1983] 5. The server sends the generated feedback to the device.

[1984] Specific examples

[1985] 1. A user enters into a smartphone application: "I had yogurt and fruit for breakfast today. My emotional state is very good." The application also syncs exercise and sleep data from a fitness tracker.

[1986] 2. The device organizes the data and sends it to the server.

[1987] 3. The server analyzes the data, including the total daily calorie intake, calories burned, and emotional state, and generates a health plan. For example, "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[1988] 4. The server sends the generated health plan to the terminal.

[1989] 5. The device displays notifications and instructions to the user, such as advice like "Try this recipe today."

[1990] 6. The user acts according to the health plan and enters their progress into the app. For example, "I ate a low-calorie dinner today and I feel good."

[1991] 7. The device organizes the new data and sends it to the server.

[1992] 8. The server analyzes the new data and generates feedback, such as "You're on track to reach your goal" or "You'd be even more effective if you reduced the calories in your dinner a little more."

[1993] In this way, the entire system manages users' health and emotional data in an integrated manner, and provides individually optimized health plans and feedback, thereby supporting users in maintaining and improving their health.

[1994] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1995] Step 1:

[1996] The user opens a dedicated smartphone application and manually inputs the details of their daily meals, for example, "I had toast and scrambled eggs for breakfast," and their emotional state for that day, for example, "I feel very energetic today."

[1997] Input: User's daily diet and emotional state

[1998] Output: Food and emotion data stored on the user's smartphone

[1999] Step 2:

[2000] The device stores the dietary and emotional data entered into the application and automatically synchronizes exercise data (step count, heart rate, exercise duration) and sleep data (sleep duration, sleep quality) from wearable devices (e.g., fitness trackers and smartwatches) using Bluetooth and Wi-Fi.

[2001] Input: User's dietary data, emotional data, exercise data, sleep data

[2002] Output: Integrated dataset on smartphone

[2003] Step 3:

[2004] The device integrates all data into a single data package and sends it to the server. Specifically, it creates the data in JSON format and sends it to the server using a REST API.

[2005] Input: Integrated dataset

[2006] Output: Data package sent to the server

[2007] Step 4:

[2008] The server analyzes the received data package and performs preprocessing on the data. Specifically, it uses the Python Pandas library to impute missing values ​​and standardize the data format. For example, it imputes missing sleep data with the average value from the past.

[2009] Input: Data package sent to the server

[2010] Output: Preprocessed dataset

[2011] Step 5:

[2012] The server analyzes the emotion data using an emotion engine (e.g., Google Cloud Natural Language API) and quantifies the emotional state. Specifically, it quantifies the input "very energetic" with a positive score.

[2013] Input: Preprocessed dataset

[2014] Output: Quantified emotion data

[2015] Step 6:

[2016] The server uses a generative AI model (e.g., a neural network model using TensorFlow) to analyze the preprocessed health and emotion data. Specifically, it categorizes the dietary data by nutrient and evaluates calorie intake and nutritional balance.

[2017] Input: Preprocessed health data, quantified emotion data

[2018] Output: Analysis results (nutritional balance, calories burned, quality of sleep, etc.)

[2019] Step 7:

[2020] Based on the data analysis results, the server generates a customized health plan for each user, including feedback and encouragement messages that take emotional data into account.

[2021] Examples: "Walk for 30 minutes three times a week," "Eat less than 1500 calories a day," "Go to bed at 10pm every night."

[2022] Input: Analysis results

[2023] Output: Customized health plan

[2024] Step 8:

[2025] The server sends the generated health plan to the device. Specifically, it creates the data in JSON format and sends it to the device using a REST API.

[2026] Enter: Customized Health Plan

[2027] Output: Health plan sent to the device

[2028] Step 9:

[2029] The device will notify the user of the received health plan and display specific instructions and suggestions for action, such as "Try this recipe today" or "Go for a 30-minute jog tomorrow."

[2030] Input: Received Health Plan

[2031] Output: User notification and instructions for action

[2032] Step 10:

[2033] The user acts according to the health plan and inputs their daily progress into the application, for example, "I had a low-calorie dinner today."

[2034] Input: User progress data

[2035] Output: Progress data saved on the device

[2036] Step 11:

[2037] The device organizes the new progress data and emotion data and sends it to the server. Specifically, the newly collected data is again integrated in JSON format and sent via a REST API.

[2038] Input: New progress and emotion data

[2039] Output: Data package sent to the server

[2040] Step 12:

[2041] The server analyzes the new progress and emotion data to assess goal achievement and areas for improvement, generating feedback such as, "You're on track with your goal," or "You'd be better off if you reduced the calories in your dinner a little more."

[2042] Input: New progress and emotion data

[2043] Output: Evaluation results and feedback

[2044] Step 13:

[2045] The server sends the evaluation results and feedback to the device. Specifically, the feedback is formatted in JSON and sent to the device using a REST API.

[2046] Input: Evaluation results and feedback

[2047] Output: Feedback sent to the terminal

[2048] Step 14:

[2049] The device will then notify the user of the received feedback and provide instructions and suggestions for the next steps, such as "You're on track to reach your goal" or "You'll be even more effective if you cut back on the calories at dinner."

[2050] Input: Feedback received

[2051] Output: Notification to the user and next action instructions

[2052] Through these steps, users can obtain the optimal health plan based on their emotional state that day, and receive continuous improvement and support.

[2053] (Application example 2)

[2054] 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."

[2055] Many conventional health management systems track a user's diet, exercise, and sleep data and provide a health plan. However, these systems do not take emotional states into account, limiting the effectiveness of personalized health plans. Furthermore, the content provided is uniform, lacking a means to provide personalized content that addresses the user's individual health status and emotions. As a result, users lose motivation to continue following their health plan. This invention aims to solve this problem by proposing a system that integrates a user's individual health data and emotional data to provide an optimal health plan and personalized health and wellness-related content.

[2056] 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 collecting health data from the user, means for pre-processing the health data transmitted to the server, means for analyzing the pre-processed data and generating an individual health plan, means for providing the generated health plan to the user, means for collecting progress data and providing feedback, and means for providing personalized health and wellness-related content based on the health plan. This enables the user to obtain an optimal health plan and personalized content according to their emotional state and health condition on that day, thereby increasing their motivation to continuously implement the health plan.

[2057] "Health Data" refers to information about a user's diet, exercise, sleep, and other health conditions.

[2058] "Preprocessing" refers to the process of preparing collected data in a format that is easy to analyze. Specifically, this includes imputing missing values, standardizing data, and standardizing formats.

[2059] "Health Plan" refers to specific guidelines and advice generated based on a user's individual health and emotional data, including exercise regimes, meal plans, sleep schedules, etc.

[2060] "Personalized Content" means personalized health and wellness related information, videos, audio, articles, etc. that are delivered to you based on your individual health and emotional state.

[2061] "Generative AI model" refers to the artificial intelligence algorithms used to analyze collected data and generate health plans and content.

[2062] "Feedback" refers to evaluating the progress of the user's health plan and providing suggestions for improvement or further advice.

[2063] "Emotion data" refers to information that indicates the user's emotional state using numerical values ​​or categories. Specifically, it includes emotional states such as "energetic," "tired easily," and "high stress."

[2064] "Individualization" refers to providing optimal information and plans according to each user's different needs and circumstances.

[2065] This invention relates to a system that collects individual user health and emotional data and provides health plans and personalized health and wellness-related content based on that data. The following describes the processing of the program that realizes this system.

[2066] Data collection

[2067] Users manually input their daily diet and emotional state using a dedicated application on their smartphone or head-mounted display. For example, they can enter information such as "I had yogurt and fruit for breakfast" or "I feel very energetic today." Additionally, exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality) are automatically synchronized using a fitness tracker.

[2068] Data Preprocessing

[2069] The server receives the collected data and performs preprocessing. Specifically, it fills in missing values ​​and standardizes the format. It then uses an emotion engine to analyze the user's emotion data and convert it into numerical values ​​and categories.

[2070] Data analysis and health plan generation

[2071] The server analyzes the preprocessed health and emotion data using a generative AI model. Based on the analysis results, it generates a customized health plan for each user. This health plan includes specific guidelines and advice. For example, it suggests things like "walking for 30 minutes three times a week," "eating less than 1,500 calories a day," and "going to bed at 10 p.m. every night."

[2072] Content Recommendation

[2073] Based on the generated health plan, the server provides users with personalized health and wellness content, including health-related videos, audio, and articles, which users can view and interact with through a dedicated application.

[2074] Feedback and Support

[2075] The user carries out actions according to the health plan and enters their progress and emotional state into a dedicated application. For example, they might enter information such as, "I ate less calories at dinner today, and I'm feeling good." The server analyzes the new data collected and evaluates their progress and areas for improvement. Based on this, it provides feedback to the user. For example, it may provide specific advice such as, "You're on track to reach your goal," or "You'd be even more effective if you reduced the calories at dinner a little more."

[2076] Examples of concrete examples and prompts

[2077] For example, if a user inputs "I had yogurt and fruit for breakfast today. I feel very energetic," and synchronizes exercise data (7,000 steps, 45 minutes of exercise, average heart rate 70 BPM) and sleep data (7 hours of sleep, good quality of sleep) from a fitness tracker, the server will generate a health plan based on this data and recommend appropriate content.

[2078] An example of a prompt sentence for input to a generative AI model is as follows:

[2079] User's dietary data: yogurt and fruit

[2080] User's emotional state: Very energetic

[2081] Exercise data: 7000 steps, exercise time 45 minutes, average heart rate 70 BPM

[2082] Sleep data: 7 hours of sleep, good quality

[2083] Use this data to generate an optimal health plan and personalized content to support its implementation.

[2084] In this way, users can obtain the optimal health plan and personalized content based on their emotional and health state on that day, which increases their motivation to continue implementing the health plan and enables effective health management.

[2085] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2086] Step 1:

[2087] Device: Using a dedicated application on a smartphone or head-mounted display, the user manually inputs their daily diet and emotional state. Examples of input data include "I had yogurt and fruit for breakfast" and "I feel very energetic today." In addition, the wearable device automatically synchronizes exercise data (number of steps, heart rate, exercise time) and sleep data (sleep time, sleep quality). All of this health-related information is included in the input data.

[2088] Input: Food data, Emotion data, Exercise data, Sleep data

[2089] Output: Integrated health data package

[2090] Step 2:

[2091] Terminal: Sends collected health data to the server using a secure and reliable communication protocol and uploads the data package to the server.

[2092] Input: Integrated Health Data Package

[2093] Output: Sending the data package to the server

[2094] Step 3:

[2095] Server: Preprocesses the received data package. If there is missing or incomplete data, it is filled in using statistical methods or past data. Next, the data format is standardized and an emotion engine is used to convert emotion data into numerical values ​​or categories. This results in a consistent dataset.

[2096] Input: Integrated Health Data Package

[2097] Output: Preprocessed dataset

[2098] Step 4:

[2099] Server: The preprocessed data is input into the generative AI model and analyzed. Specifically, nutritional value and calories are evaluated from dietary data, calories burned and exercise intensity from exercise data, and sleep quality and duration from sleep data. The model integrates this data and analyzes overall health status.

[2100] Input: Preprocessed dataset

[2101] Output: Analysis results

[2102] Step 5:

[2103] Server: Based on the analysis results, an individual health plan is generated. The generated health plan includes specific guidelines and advice. For example, a customized plan may be created, such as "walk for 30 minutes three times a week," "eat less than 1,500 calories a day," and "go to bed at 10 p.m. every night."

[2104] Input: Analysis results

[2105] Output: Health Plan

[2106] Step 6:

[2107] Server: Based on the generated health plan, retrieves and provides personalized health and wellness-related content to the user. Content includes health-related videos, audio, articles, etc. The server selects appropriate content and sends it to the device.

[2108] Enter: Health Plan

[2109] Output: personalized content

[2110] Step 7:

[2111] Device: Informs the user of their health plan and personalized content, allowing them to take specific courses of action or view the content provided.

[2112] Input: Health plans, personalized content

[2113] Output: Notification to terminal

[2114] Step 8:

[2115] User: Takes actions according to the health plan and inputs their progress and emotional state into a dedicated application. For example, they receive feedback such as, "I ate less calories at dinner today. I'm feeling good."

[2116] Input: User results and feedback

[2117] Output: Updated progress data

[2118] Step 9:

[2119] Device: Sends newly collected progress and emotion data to the server, where it is stored for the next analysis.

[2120] Input: Updated progress data

[2121] Output: Sending progress data to the server

[2122] Step 10:

[2123] Server: Analyzes the latest progress data and evaluates the degree of goal achievement and areas for improvement. For example, it generates feedback such as "You are making good progress toward your goal" or "You would be more effective if you reduced the calories in your dinner a little more" and sends it to the device.

[2124] Input: Latest progress data

[2125] Output: Evaluation results and feedback

[2126] In this way, specific data processing and actions are performed at each step, allowing users to be provided with the optimal health plan and personalized content based on their emotional and health state on that day, enabling them to continuously implement their health plan.

[2127] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2128] 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.

[2129] 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 ...

Claims

1. means for collecting health data from a user; means for pre-processing the health data transmitted to the server; means for analyzing the pre-processed data to generate an individualized health plan; means for providing the generated health plan to the user; a means of collecting progress data and providing feedback; A system including:

2. The system of claim 1 further comprising means for tracking dietary, exercise, and sleep data.

3. The system of claim 1 , further comprising means for performing data analysis using the generative AI model.

Images