System

Abstract

A system is provided.SOLUTION: A system including means for collecting data from a device that monitors biological information of a user, means for transmitting the data to a server, means for storing and preprocessing the data in the server, means for analyzing the preprocessed data to identify a lifestyle of the user, means for generating individual health advice for each user by using a generated AI based on an analysis result, and means for transmitting and notifying the health advice to a terminal of the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Many people today are at risk of health problems due to irregular lifestyles, inappropriate diets, and lack of exercise. Existing health management systems have difficulty providing detailed and specific advice tailored to individual users. There is a need to improve this situation and provide an effective system that makes it easier for users to manage their own health. [Means for solving the problem]

[0005] The present invention provides a system including means for collecting data from a device that monitors a user's biological information, means for transmitting the data to a server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating individual health advice for each user using a generation AI based on the analysis results, and means for transmitting and notifying the user of the health advice to a terminal of the user. This allows the user to receive specific health advice based on their own data and improve their lifestyle habits.

[0006] "User" refers to an individual who uses the system to manage their own health.

[0007] "Biometric information" refers to data about the human body, such as heart rate, number of steps, sleep time, and calories burned.

[0008] "Monitoring device" refers to a device that collects and records a user's biometric information in real time.

[0009] "Data" refers to information, including biometric information, obtained from a monitoring device and transmitted to a server.

[0010] "Server" refers to a central processing unit that receives, stores, pre-processes, analyzes data, generates and transmits health advice.

[0011] "Preprocessing" refers to the operation of performing necessary interpolation or filtering on received data.

[0012] "Missing value imputation" refers to the process of estimating appropriate values ​​from the preceding and following data when some data is missing.

[0013] "Outlier filtering" refers to the act of identifying and ignoring abnormal data that deviates from normal patterns.

[0014] "Analysis" refers to the calculations and statistical operations used to identify a user's lifestyle habits based on pre-processed data.

[0015] "Generative AI" refers to artificial intelligence that creates individually tailored health advice based on analysis results.

[0016] "Health Advice" means specific recommendations for users to maintain or improve their health.

[0017] "Notification" refers to the action of notifying the user of the generated health advice on their terminal.

[0018] "Terminal" refers to a device used by a user, such as a smartphone or tablet, that receives notifications from a server.

[0019] "Lifestyle habits" refers to a user's daily behavioral patterns such as activities, sleep, and meals. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] The present invention relates to a monitoring device that monitors a user's biometric information, and a system that transmits the collected data to a server, preprocesses and analyzes it, and uses generative AI to provide personalized health advice.

[0042] Program processing

[0043] Data collection

[0044] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and also transmits this data to the server at the timing of data transfer.

[0045] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[0046] Data storage

[0047] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[0048] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[0049] Data Preprocessing

[0050] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[0051] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[0052] Lifestyle analysis

[0053] The server analyzes the pre-processed data, which identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0054] For example, the system calculates a user's average number of steps and sleep time from a week's data and evaluates their exercise habits and sleep quality.

[0055] Generating health advice

[0056] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results as input and creates optimal advice for each user.

[0057] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day."

[0058] Advice Delivery

[0059] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[0060] The user checks the advice in the notification sent to the device. For example, they may receive a notification saying, "You haven't been exercising enough today, so aim for another 2,000 steps." This system allows users to know the specific steps they need to take to improve their lifestyle habits.

[0061] In this way, the present invention is a system that supports a user's own health management by providing individually optimized health advice based on the user's biological information.

[0062] The processing flow will be explained below.

[0063] Step 1: Data collection

[0064] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[0065] Step 2: Data Transfer

[0066] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[0067] Step 3: Receiving and storing data

[0068] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[0069] Step 4: Preprocessing the data

[0070] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[0071] Step 5: Lifestyle analysis

[0072] The server uses the preprocessed data to analyze the user's lifestyle. The analysis algorithm receives the data as input and derives the user's exercise patterns, average heart rate, sleep patterns, etc. For example, daily step count data can be compiled to evaluate exercise habits.

[0073] Step 6: Generate health advice

[0074] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis data as input and creates optimal advice for each user. For example, based on data from the past week, it generates specific advice such as "We recommend walking 30 minutes every day."

[0075] Step 7: Distributing Advice

[0076] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[0077] Step 8: Receive and review advice

[0078] The user receives a notification on their device and can confirm the advice. If the user taps the notification, they can open the app and view detailed advice. For example, they can confirm and follow advice such as "You haven't been exercising enough today, so aim for another 2,000 steps."

[0079] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[0080] Example 1

[0081] 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."

[0082] In modern society, many people recognize the importance of health management, but finding specific ways to improve their lifestyle habits is difficult. Furthermore, providing optimal health advice to individual users requires accurate preprocessing and analysis of collected biometric data. However, there is a lack of efficient means for processing biometric data that contains outliers and missing values. This makes it difficult to provide specific, individually optimized health advice.

[0083] 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.

[0084] In this invention, the server includes means for collecting data from a device that monitors a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating individual health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, and means for the monitoring device to collect and transmit data at regular intervals. This makes it possible to accurately collect the user's biological information, perform pre-processing, and analyze the lifestyle habits, and then provide the user with individually optimized health advice.

[0085] "User's biological information" is data that indicates the health condition of each individual user in their daily life, such as heart rate, number of steps, sleep time, and calories burned.

[0086] A "monitoring device" is a device used to collect biometric information from a user, and includes wearable devices and smartphones.

[0087] A "server" is a computer system that receives, stores, pre-processes, and analyzes data sent from a terminal.

[0088] "Storing data" refers to recording information received from a terminal in a specific storage device or database.

[0089] "Preprocessing" refers to processing performed on collected biometric information data, and includes error correction, missing value completion, and outlier filtering.

[0090] "Data analysis" refers to the use of pre-processed data to perform calculations and evaluations to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0091] "Generative AI" refers to an AI model that uses artificial intelligence technology to generate personalized health advice for each user based on specific input data.

[0092] "Health advice" refers to specific instructions or recommendations for improving the user's health, derived from the analysis results by the generative AI.

[0093] The "notification system" is a system for transmitting the generated health advice to the user's terminal and notifying the user.

[0094] An "interval" is a set time interval or frequency at which data is collected or transmitted.

[0095] The present invention is a system for monitoring a user's biological information, and a specific implementation method will be described here. Specific names of the hardware and software used and examples of prompt sentences will also be clearly stated.

[0096] This system includes a monitoring device (terminal), a server for data processing and storage, and a generative AI model for providing advice to users. The user wears a monitoring device that collects biometric information from daily life, such as heart rate, number of steps, sleep time, and calories burned. This device can be a wearable device or a smartphone, for example.

[0097] Program processing

[0098] Data collection

[0099] The device continuously monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. This data is stored in local storage at regular intervals. For example, data is collected every second and sent to the server every hour.

[0100] Data storage

[0101] The server receives the data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery. Each piece of data is assigned a timestamp and a user ID, which allows the data to be organized for each user.

[0102] Data Preprocessing

[0103] The server performs error correction, missing value completion, and outlier filtering on the received data, often using scripting languages ​​such as Python or R. Once preprocessing is complete, the data is stored back in the database.

[0104] Lifestyle analysis

[0105] The server analyzes the preprocessed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns using distributed processing frameworks such as Spark and Hadoop.

[0106] Generating health advice

[0107] The server generates personalized health advice using a generative AI model (e.g., GPT-4 (registered trademark)) based on the analysis results. It also generates prompt sentences for inputting the analysis results and inputs them into the generative AI.

[0108] Example prompt sentence:

[0109] User ID: 12345

[0110] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[0111] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[0112] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[0113] Use this data to generate personalized health improvement advice for users.

[0114] Advice Delivery

[0115] The server sends the generated health advice to the user's device. The advice is notified to the user using a notification system such as Firebase Cloud Messaging or Amazon SNS. The user can check the notification received on their device and improve their lifestyle based on the advice.

[0116] Specific examples

[0117] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server stores the data using RDS and preprocesses it with a Python script. The resulting prompt is then fed to the generative AI model, which then generates advice for the user, such as "We recommend walking 30 minutes daily."

[0118] In this way, this system accurately collects the user's biometric information, performs preprocessing, analyzes lifestyle habits, and provides individually optimized health advice to the user, thereby supporting the user's health management.

[0119] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0120] Step 1:

[0121] Data collection

[0122] The device continuously monitors the user's biometric information, such as heart rate, steps taken, sleep time, and calories burned, and stores the data in local storage at regular intervals (e.g., every second).

[0123] Specific operation: Acquires data from the heart rate sensor and accelerometer and stores it in local storage.

[0124] Input: Real-time biometric data of the user

[0125] Output: Biometric data stored in local storage

[0126] Step 2:

[0127] Data transmission

[0128] After a certain period of time has elapsed (for example, every hour), the terminal transmits the biometric information data accumulated in the local storage to the server.

[0129] Specific operation: Data is divided into packets and sent to a server over the Internet.

[0130] Input: Biometric data stored in local storage

[0131] Output: Biometric data sent to the server

[0132] Step 3:

[0133] Data storage

[0134] The server receives the biometric data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery.

[0135] Specific operation: Receive data, assign a timestamp and user ID to each data, and save it in the database.

[0136] Input: Biometric data sent from the device

[0137] Output: Aligned biometric data stored in a database

[0138] Step 4:

[0139] Data Preprocessing

[0140] The server performs error correction, missing value completion, and outlier filtering on the received data using Python and R scripts.

[0141] Specific operations: Detect and remove outliers, impute missing values, and perform noise reduction.

[0142] Input: Biometric data stored in a database

[0143] Output: Clean biometric data after preprocessing

[0144] Step 5:

[0145] Lifestyle analysis

[0146] The server analyzes the pre-processed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns, using distributed processing frameworks such as Spark and Hadoop.

[0147] Specific operation: Aggregate one week's worth of data and calculate average values ​​and trends.

[0148] Input: Clean, pre-processed biometric data

[0149] Output: Analysis results (user's lifestyle data)

[0150] Step 6:

[0151] Generating health advice

[0152] The server uses a generative AI model (e.g., GPT-4) to generate personalized health advice for each user based on the analysis results.

[0153] Specific operation: The analysis results are input into the generation AI as a prompt sentence, and a response is obtained from the AI.

[0154] Input: Analysis results (user's lifestyle data)

[0155] Output: Generated personalized health advice

[0156] Step 7:

[0157] Advice Delivery

[0158] The server sends the generated health advice to the user's device using a notification system such as Firebase Cloud Messaging or Amazon SNS.

[0159] Specific operation: A notification message is constructed and sent to the device. The user receives it and uses it to improve their lifestyle habits.

[0160] Input: Generated personalized health advice

[0161] Output: Health advice notification delivered to the user's device

[0162] Example prompt sentence:

[0163] User ID: 12345

[0164] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[0165] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[0166] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[0167] Use this data to generate personalized health improvement advice for users.

[0168]

[0169] (Application example 1)

[0170] 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."

[0171] Conventional health management systems only collect users' biometric information and provide health advice based on the analysis results. However, they do not consider recommending specific products based on the user's health status or providing related discounts or campaign information. As a result, there is a lack of means to encourage users to make practical and economical improvements. This problem remains unsolved due to a lack of incentives to motivate users and encourage behavioral change.

[0172] 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.

[0173] In this invention, the server includes means for collecting data from devices that monitor a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating personalized health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, means for recommending products based on the generated health advice according to the user's health condition, and means for generating discount and campaign information based on the health condition. This makes it easier for users to purchase specific products and services based on their health condition, thereby increasing their motivation to improve their health.

[0174] "User's biological information" is data that indicates the user's health condition, such as heart rate, number of steps, sleep time, and calories burned.

[0175] A "monitoring device" is a device for collecting biometric information from a user. Examples include smartwatches and fitness trackers.

[0176] A "server" is a computer system for storing, preprocessing, and analyzing collected biometric information.

[0177] "Storage" means recording collected data for future reference.

[0178] "Preprocessing" refers to the process of correcting errors in biometric information data, complementing missing values, and filtering outliers.

[0179] "Analysis" refers to identifying a user's lifestyle and health status using preprocessed data.

[0180] "Generative AI" is a technology that uses artificial intelligence to generate useful information and advice from specific input data.

[0181] "Health advice" refers to specific instructions or recommendations based on the analysis results aimed at improving the user's lifestyle habits.

[0182] A "terminal" is a device through which a user receives health advice. Examples include smartphones and tablets.

[0183] "Product recommendation" refers to recommending specific products to encourage purchase based on the user's health status.

[0184] "Discount and campaign information" is information about special offers and price reductions that are intended to increase the user's purchasing motivation.

[0185] This invention is a system that collects data from devices that monitor a user's biometric information, transmits the data to a server, stores it, preprocesses it, and analyzes it. Furthermore, it uses generative AI to provide personalized health advice, and generates and provides product recommendations and discount information based on the user's health status, thereby supporting the user's health management and purchasing behavior.

[0186] System Configuration

[0187] The system consists of the following main components:

[0188] 1. Monitoring devices: Devices such as smartwatches and fitness trackers collect biometric information such as a user's heart rate, steps taken, sleep time, and calories burned.

[0189] 2. Server:

[0190] Data storage: The biometric data sent from the monitoring device is stored in a database such as Amazon RDS.

[0191] Preprocessing: Use AWS (registered trademark) Lambda to perform error correction, missing value imputation, and outlier filtering.

[0192] Data analysis: Use Amazon SageMaker to analyze data and identify user habits and health conditions.

[0193] Generative AI: Using generative AI models such as GPT-4, personalized health advice is generated based on the analysis results.

[0194] 3. Mobile Applications: Applications developed on iOS and ANDROID platforms (e.g., Xcode, Android Studio) inform users of health advice, product recommendations, and discount information.

[0195] Program processing

[0196] 1. Data collection and transmission: The monitoring device collects the user's biometric information in real time and transmits the data to the server at regular intervals. This data is marked with a timestamp and user ID.

[0197] 2. Data storage and preprocessing: The server stores the data in a database and then uses AWS Lambda to preprocess the data, specifically imputing missing data and filtering outliers.

[0198] 3. Data analysis and generation: Using Amazon SageMaker, the preprocessed data is analyzed to identify the user's lifestyle habits and health status. A generative AI (e.g., GPT-4) generates personalized health advice based on the analysis results.

[0199] 4. Advice Delivery: The generated health advice, product recommendations, and discount information are sent to the user via the mobile application. For example, specific advice such as "You haven't been exercising enough today, so aim for 2,000 more steps" is provided.

[0200] 5. Product recommendations based on health status: Generative AI recommends appropriate products (e.g., health foods and fitness products) based on the user's health status.

[0201] 6. Discount and campaign information: Generate discount codes and campaign information linked to the user's health status and provide it to the user.

[0202] Examples of concrete examples and prompts

[0203] For example, if the user's biometric information is "heart rate: 70 bpm, number of steps: 8,000, sleep time: 7 hours, calories burned: 2,500 kcal," the following prompt sentence is input to the generation AI:

[0204] Based on the user's health data (heart rate: 70 bpm, number of steps: 8000 steps, sleep time: 7 hours, calories burned: 2500 kcal), recommend healthy foods and exercise equipment, and generate discount and campaign information applicable to their purchase.

[0205] This will enable the realization of a system that provides users with specific advice and recommended products tailored to their health, as well as economic incentives, leading to the maintenance of their health and behavioral changes.

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

[0207] Step 1:

[0208] The monitoring device (terminal) collects biometric information such as the user's heart rate, number of steps, sleep time, and calories burned in real time. This data is temporarily stored in the terminal's local storage at regular intervals (e.g., every hour). The terminal then transmits the data to a server. The input is the user's biometric information, and the output is a data file sent to the server.

[0209] Step 2:

[0210] The server receives the biometric data sent from the device and records it in a database. The data is assigned a timestamp and user ID and is organized by user. The input is the biometric data sent from the device, and the output is the data stored in the database.

[0211] Step 3:

[0212] The server preprocesses the incoming data. It uses AWS Lambda to impute missing data and filter outliers. This processing improves the accuracy of the data. The input is the stored biometric data, and the output is the preprocessed data.

[0213] Step 4:

[0214] The server analyzes the preprocessed data. Amazon SageMaker is used to identify the user's lifestyle and health status (for example, average heart rate, total number of steps, sleep patterns, etc.). The input is the preprocessed data, and the output is the analysis results. Specifically, the server analyzes the data and extracts trends.

[0215] Step 5:

[0216] The generative AI (for example, GPT-4) generates individual health advice based on the analysis results. Specific advice is generated based on the analysis results, which are input as a prompt. The input is the analysis results, and the output is the generated health advice. Specifically, the prompt is input into the generative AI model, and the result is received as text.

[0217] Step 6:

[0218] The server sends the generated health advice to the user's device. The user's device receives a notification through the application and can check the advice. The input is the generated health advice, and the output is the notification to the user's device. Specifically, the server pushes the advice through the notification system.

[0219] Step 7:

[0220] The server recommends suitable products to the user based on the generated health advice. These recommendations include products according to the user's health condition (e.g., health foods and fitness products). The input is the generated health advice, and the output is a list of recommended products. Specifically, the server selects suitable products from a database and creates a list.

[0221] Step 8:

[0222] The server generates discount and campaign information based on the user's health status. It uses a generative AI model to create optimal discount codes and campaign information. The input is the user's health information and analysis results, and the output is discount and campaign information. Specifically, the server works in conjunction with the sales promotion system to generate applicable promotions.

[0223] Step 9:

[0224] The server sends the generated discount and campaign information to the user's terminal. The user's terminal can receive and use this information through an application. The input is the generated discount and campaign information, and the output is a notification to the user's terminal. In concrete terms, the server distributes the information via the campaign management system.

[0225] 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.

[0226] This invention combines a monitoring device that monitors a user's biometric information, a system that transmits the data to a server, and provides individually optimized health advice using preprocessing, analysis, and generation AI, with an emotion engine that recognizes the user's emotions.

[0227] Program processing

[0228] Data collection

[0229] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and then transmits it to the server at the data transfer timing.

[0230] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[0231] Data storage

[0232] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[0233] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[0234] Data Preprocessing

[0235] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[0236] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[0237] Emotion recognition

[0238] The server recognizes the user's emotions based on the pre-processed data using an emotion engine, which analyzes the user's short-term and long-term emotional state from their biometric and activity data.

[0239] For example, the possibility that the user is feeling stressed can be estimated based on fluctuations in heart rate and activity patterns.

[0240] Lifestyle analysis

[0241] The server then comprehensively analyzes the pre-processed data, including the results of the emotion engine analysis, to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information.

[0242] For example, the system can calculate a user's average number of steps and sleep time from a week's data to evaluate their exercise habits and sleep quality, and identify stress levels and emotional fluctuation patterns from emotional data.

[0243] Generating health advice

[0244] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results and emotional data as input and creates optimal advice for each user.

[0245] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day." If it detects signs of stress, it will provide advice such as "We recommend deep breathing exercises to help you relax."

[0246] Advice Delivery

[0247] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[0248] Users can view the advice by receiving a notification on their device, or by tapping the notification, they can open the app and view the detailed advice.

[0249] For example, you can receive notifications such as "You haven't been exercising enough today, so aim for 2,000 more steps" or "Try meditating for 5 minutes to relax."

[0250] In this way, the present invention provides multifaceted support for the user's health management by providing individually optimized health advice based on the user's biometric information and emotional data.

[0251] The processing flow will be explained below.

[0252] Step 1: Data collection

[0253] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[0254] Step 2: Data Transfer

[0255] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[0256] Step 3: Receiving and storing data

[0257] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[0258] Step 4: Preprocessing the data

[0259] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[0260] Step 5: Recognize emotions

[0261] The server uses an emotion engine to recognize the user's emotions based on the preprocessed data. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it estimates the possibility that the user is feeling stressed based on fluctuations in their heart rate and activity patterns.

[0262] Step 6: Lifestyle analysis

[0263] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[0264] Step 7: Generate health advice

[0265] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis results and emotional data as input and creates optimal advice for each user. For example, if it determines that a user is not getting enough exercise, it generates specific advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, it also provides advice such as "We recommend deep breathing exercises to relax."

[0266] Step 8: Distributing Advice

[0267] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[0268] Step 9: Receive and review advice

[0269] Users receive a notification on their device and can check the advice. By tapping the notification, they can open the app and view detailed advice. For example, they can receive a notification such as "Today you haven't been exercising enough, so aim for 2,000 more steps" or "Try 5 minutes of meditation to relax."

[0270] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[0271] Example 2

[0272] 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."

[0273] The problem that this invention aims to solve is to efficiently and accurately collect a user's biometric information and provide individually optimized health advice based on that data. In particular, it is necessary to generate health advice that takes into account the user's emotional state and support comprehensive health management in daily life. It is also necessary to appropriately handle quality issues such as missing data and outliers, and to achieve high-precision data analysis.

[0274] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a preprocessing means for correcting data errors, complementing missing values, and filtering outliers, a means for recognizing a user's emotions through an emotion engine using the preprocessed data, a means for identifying the user's lifestyle habits by analyzing the preprocessed data and emotion data, a means for generating individual health advice for each user using a generation AI based on the analysis results and emotion data, and a means for transmitting the health advice to the user's terminal and notifying the user. This makes it possible to provide individually optimized health advice with high accuracy based on the user's biometric information and emotion data.

[0275] "User's biometric information" refers to physical data from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned.

[0276] "Monitoring device" refers to a terminal used to constantly monitor and collect a user's biometric information.

[0277] "Server" refers to a computer system for storing, pre-processing, and analyzing data transmitted from monitoring devices.

[0278] "Preprocessing" refers to the process of correcting errors in the collected raw data, filling in missing values, and filtering outliers.

[0279] "Emotion engine" refers to a function that uses biometric and activity data to analyze and recognize a user's emotional state.

[0280] "Generative AI" refers to artificial intelligence that automatically generates optimal health advice for each user based on analysis results and emotional data.

[0281] "Health advice" refers to specific advice aimed at improving lifestyle habits and promoting health, generated based on the user's biometric information and emotional data.

[0282] "Missing value imputation" refers to the process of filling in missing data with other valid data.

[0283] "Outlier filtering" refers to the process of removing values ​​in the data that are deemed to be clearly inaccurate, such as abnormally high or low values.

[0284] "Database" refers to a system within the server for organizing and storing received and pre-processed data.

[0285] "Notification system" refers to a function for sending health advice to a user's terminal and notifying the user.

[0286] This invention is a system for monitoring and collecting a user's biometric information and providing individually optimized health advice to the user. Specifically, the system uses data acquired by a monitoring device, preprocesses and analyzes the data, and provides advice using generative AI.

[0287] Hardware and Software Configuration

[0288] Monitoring Devices:

[0289] Devices (e.g. fitness trackers, smartwatches) contain sensors such as:

[0290] Heart rate sensor

[0291] Acceleration sensor

[0292] Gyroscope

[0293] This allows the system to constantly monitor and collect biometric information such as the user's heart rate, number of steps taken, sleep time, and calories burned.

[0294] server:

[0295] The following hardware and software are used for data storage, preprocessing, and analysis:

[0296] Database server (e.g., MySQL (registered trademark), MongoDB)

[0297] Data analysis tools (e.g., Scikit-learn, TENSORFLOW (registered trademark))

[0298] Emotion engine (e.g., Microsoft® Azure® Emotion API)

[0299] Generative AI models (e.g., OpenAI® GPT-4)

[0300] Communication modules (e.g. REST API servers)

[0301] Processing Flow

[0302] First, the device collects the user's biometric information in real time. For example, a heart rate sensor measures the heart rate every second, and an acceleration sensor counts the number of steps. This data is accumulated in local storage at regular intervals (for example, every hour).

[0303] Next, the device transmits the collected data to the server via wireless communication (Bluetooth or Wi-Fi). When the transmitted data is received by the server, it is first stored in a database.

[0304] The server preprocesses the received raw data, which includes error correction, missing value imputation, and outlier filtering. The preprocessed data is then stored in the database again.

[0305] The server then uses an emotion engine to recognize the user's emotions based on the pre-processed data, analyzing the short-term and long-term emotional states to obtain emotion data.

[0306] The server comprehensively analyzes the pre-processed data and emotional data to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc. Based on the results of this analysis, a generative AI model is run to generate personalized health advice for each user.

[0307] The generated health advice is sent to the user's device via the notification system. The user can then check the notification displayed on the device and view the detailed advice in the app.

[0308] Examples and prompts

[0309] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server then preprocesses the data and recognizes their emotional state, determining that the user is experiencing moderate stress.

[0310] At this point, the database contains preprocessed data and emotion data. The server analyzes this data and inputs the following prompt to the generative AI model:

[0311] Generate health advice based on the user's biometric and emotional data. Use the following data:

[0312] Heart rate: 70 bpm

[0313] Daily steps: 8,000

[0314] Stress level: Moderate

[0315] Sleep time: 6 hours

[0316] Based on this prompt, the generative AI model generates health advice such as, "Based on your recent data, your daily exercise volume is appropriate, but your sleep time is somewhat insufficient. Try to get at least seven hours of sleep each night. Also, you appear to be at a moderate level of stress, so try incorporating deep breathing exercises to help you relax."

[0317] As a result, the present invention provides individually optimized health advice based on the user's biometric information and emotional data, and provides comprehensive support for the user's health management.

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

[0319] Step 1: Data collection

[0320] Devices (e.g., fitness trackers, smartwatches) use sensors to collect biometric information such as a user's heart rate, number of steps, sleep time, and calories burned in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer counts the number of steps, and the gyroscope detects the user's movements and estimates sleep time.

[0321] Input: The user's actual biometric data

[0322] Output: Measured biological information data (heart rate, steps, sleep time, calories burned)

[0323] Step 2: Sending data

[0324] The device accumulates the collected data in local storage at regular intervals (for example, every hour), and then transmits it to the server via wireless communication (Bluetooth or Wi-Fi). The data is packetized and sent to the server using a secure communication protocol (for example, HTTPS).

[0325] Input: Biometric data stored in local storage

[0326] Output: Biometric data sent to the server

[0327] Step 3: Save your data

[0328] The server receives the data sent from the device, temporarily stores it in memory, and then saves it in a database (e.g., MySQL or MongoDB). The data is assigned a timestamp and user ID and organized appropriately.

[0329] Input: Received biometric data

[0330] Output: Biometric data stored in a database

[0331] Step 4: Preprocessing the data

[0332] The server preprocesses the stored data. This preprocessing includes correcting errors in the data, imputing missing values, and filtering outliers. The preprocessed data is then saved back into the database. Specifically, the raw data is read from the database, and a Python script cleans the data using the Pandas library.

[0333] Input: Biometric data stored in a database

[0334] Output: Preprocessed biometric data

[0335] Step 5: Recognize emotions

[0336] The server analyzes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API) based on the preprocessed data. It sends the input data to the API and obtains the emotion recognition results, which are then stored in a database.

[0337] Input: Preprocessed biometric data

[0338] Output: Emotion data obtained from the emotion engine

[0339] Step 6: Lifestyle analysis

[0340] The server uses data analysis tools (e.g., Scikit-learn, TensorFlow) to comprehensively analyze the preprocessed data and emotion data, thereby identifying the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0341] Input: Preprocessed biometric and emotion data

[0342] Output: Analyzed lifestyle data

[0343] Step 7: Generate health advice

[0344] The server generates health advice using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results and emotion data. The generative AI model receives specific prompts as input and generates optimal advice.

[0345] Example prompt:

[0346] Generate health advice based on the user's biometric and emotional data. Use the following data:

[0347] Heart rate: 70 bpm

[0348] Daily steps: 8,000

[0349] Stress level: Moderate

[0350] Sleep time: 6 hours

[0351] Input: Analysis results and emotion data

[0352] Output: Generated health advice

[0353] Step 8: Distributing Advice

[0354] The server sends the generated health advice to the user's device using a notification system (e.g., Firebase Cloud Messaging). The user receives a notification displayed on the device and can view detailed advice in the app.

[0355] Input: Generated health advice

[0356] Output: Notification sent to the user's device

[0357] (Application example 2)

[0358] 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."

[0359] Conventional health advice systems provide certain health advice based on a user's biometric information, but because they do not take the user's emotional state into account, it is difficult to provide individual dietary and health advice tailored to the user's actual needs. This also limits the effectiveness of the advice provided, resulting in a low effectiveness in managing the user's health.

[0360] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0361] In this invention, the server includes means for identifying the user's biometric information and emotional data, means for generating personalized health and dietary advice using a generation AI based on the analysis results and emotional data, and means for transmitting and notifying the generated health and dietary advice to the user's terminal. This allows for the provision of personalized dietary and health advice based on the user's actual health and emotional state, making it possible to more effectively manage the user's health.

[0362] - "Biometric information" refers to data that indicates the user's physical condition, such as the user's heart rate, number of steps taken, and calories burned.

[0363] A "device" is a device for monitoring a user's biometric information and collecting data.

[0364] "Server" means a device or system that receives collected data and performs storage, pre-processing, analysis, and generative AI.

[0365] "Preprocessing" refers to the process of correcting or removing errors, missing values, and outliers from collected data and converting it into a format suitable for analysis.

[0366] "Analysis" is the process of identifying a user's lifestyle habits and emotions based on preprocessed data.

[0367] "Emotion data" is data relating to the emotional state of the user analyzed from biometric information and activity data.

[0368] "Generative AI" is an artificial intelligence technology that generates individual health and dietary advice for each user based on analysis results and emotional data.

[0369] "Health advice" is specific instructions or suggestions related to a user's exercise, diet, and rest.

[0370] "Sending" is the process of delivering the generated advice from the server to the user's terminal.

[0371] "Notifications" is a feature that notifies users of advice and reminders displayed on the device.

[0372] The present invention is a system that monitors a user's biological information and provides personalized health and dietary advice based on the acquired data. The system consists of a monitoring device, a server, a food delivery application, and a user terminal.

[0373] First, the user wears a monitoring device. This device collects biometric information such as heart rate, number of steps, and calories burned in real time. This data is stored in local storage at regular intervals and sent to the server as appropriate. For example, if a user walks 8,000 steps in a day and their average heart rate is 70 bpm, this data will be collected and sent to the server every hour.

[0374] The server receives the data sent from the device and stores it in a database. The received data is appended with a timestamp and user ID, and the data is organized for each user. Daily exercise data and heart rate data are organized by each user's ID and stored in the database.

[0375] Data preprocessing involves error correction, missing value completion, and outlier filtering. For example, if heart rate data is missing, it is completed based on valid data before and after, and abnormally high heart rate data is excluded. The preprocessed data is then resaved.

[0376] The server then uses the preprocessed data to recognize the user's emotions using an emotion engine. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it can estimate the user's likelihood of feeling stressed based on fluctuations in their heart rate and activity patterns.

[0377] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[0378] Based on the analysis results and emotion data, the generative AI generates optimal health and dietary advice for each user. The generative AI model is built using TensorFlow and inputs the analysis results and emotion data as prompts. The generated advice includes specific exercise, diet, and rest recommendations.

[0379] For example, if a user is judged to be lacking in exercise, the system will generate advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, the system will provide advice such as "We recommend deep breathing exercises to help you relax." Furthermore, a system built into a food delivery application will recommend menus containing ingredients that have a relaxing effect to users who are feeling stressed.

[0380] The generated health and diet advice is sent to the user's device and delivered to them through a notification system, where they can tap on the notification to view the detailed advice.

[0381] The following are examples of specific prompt sentences:

[0382] Prompt Sentence Examples

[0383] Input data:

[0384] Heart rate: 72 bpm

[0385] Steps: 5,000 steps

[0386] Calories burned: 350 kcal

[0387] Emotional state: Stress level 0.7

[0388] Generation advice:

[0389] Your heart rate is in the normal range, but you may not be getting enough exercise. Your stress levels are high, so we recommend a dinner that includes foods that have a relaxing effect (e.g., bananas and nuts). You should also set a goal to walk a little more each day. For example, aim for 7,000 steps tomorrow.

[0390] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0391] Step 1:

[0392] The monitoring device collects the user's biometric information. The input is data such as heart rate, steps, and calories burned. The device monitors this data in real time and stores it in local storage. The output is the collected biometric data.

[0393] Step 2:

[0394] The monitoring device transmits biometric data to the server at regular intervals. The input is the biometric data stored in the local storage. The data is transmitted from the device to the server. The output is the biometric data transmitted to the server.

[0395] Step 3:

[0396] The server receives the transmitted biometric data and stores it in a database. The input is the biometric data sent from the device. The data is stored in the database and organized by timestamp and user ID. The output is organized and stored biometric data.

[0397] Step 4:

[0398] The server preprocesses the received data. Preprocessing includes missing value imputation, outlier filtering, and error correction. The input is biometric data stored in a database. For example, if heart rate data is missing, it is imputed based on previous and subsequent data, and abnormally high heart rate data is excluded. The output is the preprocessed biometric data.

[0399] Step 5:

[0400] The server analyzes the user's emotions using an emotion engine based on the preprocessed data. The input is preprocessed biometric data. The emotion engine estimates the user's stress level and emotional state from fluctuations in heart rate and activity patterns. The output is analyzed emotion data.

[0401] Step 6:

[0402] The server comprehensively analyzes the preprocessed data and emotional data. The input is the preprocessed biometric data and emotional data. The data analysis identifies the user's lifestyle habits, exercise patterns, stress level, etc. The output is the analysis results.

[0403] Step 7:

[0404] The server uses generative AI to generate personalized health and diet advice based on the analysis results and emotional data. The input is the analysis results and emotional data. The generative AI model (e.g., TensorFlow) uses the analysis results and emotional data to generate advice. For example, advice such as "30 minutes of walking daily is recommended" may be generated for lack of exercise, or "a dinner containing ingredients with a relaxing effect is recommended" for high stress levels. The output is the generated health and diet advice.

[0405] Step 8:

[0406] The server sends the generated health and diet advice to the user's device and notifies them. The input is the generated health and diet advice. The advice is sent to the device and delivered to the user through the notification system. When the user receives the notification, they can tap it to view the detailed advice. The output is the advice and notification displayed on the user's device.

[0407] This process allows users to receive personalized health and dietary advice based on their biometrics and emotional state.

[0408] 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.

[0409] 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.

[0410] 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.

[0411] [Second embodiment]

[0412] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0413] 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.

[0414] 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).

[0415] 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.

[0416] 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.

[0417] 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).

[0418] 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.

[0419] 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.

[0420] 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.

[0421] 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.

[0422] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0423] 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."

[0424] The present invention relates to a monitoring device that monitors a user's biometric information, and a system that transmits the collected data to a server, preprocesses and analyzes it, and uses generative AI to provide personalized health advice.

[0425] Program processing

[0426] Data collection

[0427] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and also transmits this data to the server at the timing of data transfer.

[0428] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[0429] Data storage

[0430] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[0431] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[0432] Data Preprocessing

[0433] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[0434] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[0435] Lifestyle analysis

[0436] The server analyzes the pre-processed data, which identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0437] For example, the system calculates a user's average number of steps and sleep time from a week's data and evaluates their exercise habits and sleep quality.

[0438] Generating health advice

[0439] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results as input and creates optimal advice for each user.

[0440] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day."

[0441] Advice Delivery

[0442] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[0443] The user checks the advice in the notification sent to the device. For example, they may receive a notification saying, "You haven't been exercising enough today, so aim for another 2,000 steps." This system allows users to know the specific steps they need to take to improve their lifestyle habits.

[0444] In this way, the present invention is a system that supports a user's own health management by providing individually optimized health advice based on the user's biological information.

[0445] The processing flow will be explained below.

[0446] Step 1: Data collection

[0447] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[0448] Step 2: Data Transfer

[0449] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[0450] Step 3: Receiving and storing data

[0451] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[0452] Step 4: Preprocessing the data

[0453] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[0454] Step 5: Lifestyle analysis

[0455] The server uses the preprocessed data to analyze the user's lifestyle. The analysis algorithm receives the data as input and derives the user's exercise patterns, average heart rate, sleep patterns, etc. For example, daily step count data can be compiled to evaluate exercise habits.

[0456] Step 6: Generate health advice

[0457] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis data as input and creates optimal advice for each user. For example, based on data from the past week, it generates specific advice such as "We recommend walking 30 minutes every day."

[0458] Step 7: Distributing Advice

[0459] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[0460] Step 8: Receive and review advice

[0461] The user receives a notification on their device and can confirm the advice. If the user taps the notification, they can open the app and view detailed advice. For example, they can confirm and follow advice such as "You haven't been exercising enough today, so aim for another 2,000 steps."

[0462] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[0463] Example 1

[0464] 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."

[0465] In modern society, many people recognize the importance of health management, but finding specific ways to improve their lifestyle habits is difficult. Furthermore, providing optimal health advice to individual users requires accurate preprocessing and analysis of collected biometric data. However, there is a lack of efficient means for processing biometric data that contains outliers and missing values. This makes it difficult to provide specific, individually optimized health advice.

[0466] 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.

[0467] In this invention, the server includes means for collecting data from a device that monitors a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating individual health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, and means for the monitoring device to collect and transmit data at regular intervals. This makes it possible to accurately collect the user's biological information, perform pre-processing, and analyze the lifestyle habits, and then provide the user with individually optimized health advice.

[0468] "User's biological information" is data that indicates the health condition of each individual user in their daily life, such as heart rate, number of steps, sleep time, and calories burned.

[0469] A "monitoring device" is a device used to collect biometric information from a user, and includes wearable devices and smartphones.

[0470] A "server" is a computer system that receives, stores, pre-processes, and analyzes data sent from a terminal.

[0471] "Storing data" refers to recording information received from a terminal in a specific storage device or database.

[0472] "Preprocessing" refers to processing performed on collected biometric information data, and includes error correction, missing value completion, and outlier filtering.

[0473] "Data analysis" refers to the use of pre-processed data to perform calculations and evaluations to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0474] "Generative AI" refers to an AI model that uses artificial intelligence technology to generate personalized health advice for each user based on specific input data.

[0475] "Health advice" refers to specific instructions or recommendations for improving the user's health, derived from the analysis results by the generative AI.

[0476] The "notification system" is a system for transmitting the generated health advice to the user's terminal and notifying the user.

[0477] An "interval" is a set time interval or frequency at which data is collected or transmitted.

[0478] The present invention is a system for monitoring a user's biological information, and a specific implementation method will be described here. Specific names of the hardware and software used and examples of prompt sentences will also be clearly stated.

[0479] This system includes a monitoring device (terminal), a server for data processing and storage, and a generative AI model for providing advice to users. The user wears a monitoring device that collects biometric information from daily life, such as heart rate, number of steps, sleep time, and calories burned. This device can be a wearable device or a smartphone, for example.

[0480] Program processing

[0481] Data collection

[0482] The device continuously monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. This data is stored in local storage at regular intervals. For example, data is collected every second and sent to the server every hour.

[0483] Data storage

[0484] The server receives the data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery. Each piece of data is assigned a timestamp and a user ID, which allows the data to be organized for each user.

[0485] Data Preprocessing

[0486] The server performs error correction, missing value completion, and outlier filtering on the received data, often using scripting languages ​​such as Python or R. Once preprocessing is complete, the data is stored back in the database.

[0487] Lifestyle analysis

[0488] The server analyzes the preprocessed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns using distributed processing frameworks such as Spark and Hadoop.

[0489] Generating health advice

[0490] The server generates personalized health advice using a generative AI model (e.g., GPT-4) based on the analysis results. It also generates prompts to input the analysis results and inputs them into the generative AI.

[0491] Example prompt sentence:

[0492] User ID: 12345

[0493] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[0494] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[0495] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[0496] Use this data to generate personalized health improvement advice for users.

[0497] Advice Delivery

[0498] The server sends the generated health advice to the user's device. The advice is notified to the user using a notification system such as Firebase Cloud Messaging or Amazon SNS. The user can check the notification received on their device and improve their lifestyle based on the advice.

[0499] Specific examples

[0500] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server stores the data using RDS and preprocesses it with a Python script. The resulting prompt is then fed to the generative AI model, which then generates advice for the user, such as "We recommend walking 30 minutes daily."

[0501] In this way, this system accurately collects the user's biometric information, performs preprocessing, analyzes lifestyle habits, and provides individually optimized health advice to the user, thereby supporting the user's health management.

[0502] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0503] Step 1:

[0504] Data collection

[0505] The device continuously monitors the user's biometric information, such as heart rate, steps taken, sleep time, and calories burned, and stores the data in local storage at regular intervals (e.g., every second).

[0506] Specific operation: Acquires data from the heart rate sensor and accelerometer and stores it in local storage.

[0507] Input: Real-time biometric data of the user

[0508] Output: Biometric data stored in local storage

[0509] Step 2:

[0510] Data transmission

[0511] After a certain period of time has elapsed (for example, every hour), the terminal transmits the biometric information data accumulated in the local storage to the server.

[0512] Specific operation: Data is divided into packets and sent to a server over the Internet.

[0513] Input: Biometric data stored in local storage

[0514] Output: Biometric data sent to the server

[0515] Step 3:

[0516] Data storage

[0517] The server receives the biometric data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery.

[0518] Specific operation: Receive data, assign a timestamp and user ID to each data, and save it in the database.

[0519] Input: Biometric data sent from the device

[0520] Output: Aligned biometric data stored in a database

[0521] Step 4:

[0522] Data Preprocessing

[0523] The server performs error correction, missing value completion, and outlier filtering on the received data using Python and R scripts.

[0524] Specific operations: Detect and remove outliers, impute missing values, and perform noise reduction.

[0525] Input: Biometric data stored in a database

[0526] Output: Clean biometric data after preprocessing

[0527] Step 5:

[0528] Lifestyle analysis

[0529] The server analyzes the pre-processed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns, using distributed processing frameworks such as Spark and Hadoop.

[0530] Specific operation: Aggregate one week's worth of data and calculate average values ​​and trends.

[0531] Input: Clean, pre-processed biometric data

[0532] Output: Analysis results (user's lifestyle data)

[0533] Step 6:

[0534] Generating health advice

[0535] The server uses a generative AI model (e.g., GPT-4) to generate personalized health advice for each user based on the analysis results.

[0536] Specific operation: The analysis results are input into the generation AI as a prompt sentence, and a response is obtained from the AI.

[0537] Input: Analysis results (user's lifestyle data)

[0538] Output: Generated personalized health advice

[0539] Step 7:

[0540] Advice Delivery

[0541] The server sends the generated health advice to the user's device using a notification system such as Firebase Cloud Messaging or Amazon SNS.

[0542] Specific operation: A notification message is constructed and sent to the device. The user receives it and uses it to improve their lifestyle habits.

[0543] Input: Generated personalized health advice

[0544] Output: Health advice notification delivered to the user's device

[0545] Example prompt sentence:

[0546] User ID: 12345

[0547] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[0548] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[0549] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[0550] Use this data to generate personalized health improvement advice for users.

[0551]

[0552] (Application example 1)

[0553] 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."

[0554] Conventional health management systems only collect users' biometric information and provide health advice based on the analysis results. However, they do not consider recommending specific products based on the user's health status or providing related discounts or campaign information. As a result, there is a lack of means to encourage users to make practical and economical improvements. This problem remains unsolved due to a lack of incentives to motivate users and encourage behavioral change.

[0555] 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.

[0556] In this invention, the server includes means for collecting data from devices that monitor a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating personalized health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, means for recommending products based on the generated health advice according to the user's health condition, and means for generating discount and campaign information based on the health condition. This makes it easier for users to purchase specific products and services based on their health condition, thereby increasing their motivation to improve their health.

[0557] "User's biological information" is data that indicates the user's health condition, such as heart rate, number of steps, sleep time, and calories burned.

[0558] A "monitoring device" is a device for collecting biometric information from a user. Examples include smartwatches and fitness trackers.

[0559] A "server" is a computer system for storing, preprocessing, and analyzing collected biometric information.

[0560] "Storage" means recording collected data for future reference.

[0561] "Preprocessing" refers to the process of correcting errors in biometric information data, complementing missing values, and filtering outliers.

[0562] "Analysis" refers to identifying a user's lifestyle and health status using preprocessed data.

[0563] "Generative AI" is a technology that uses artificial intelligence to generate useful information and advice from specific input data.

[0564] "Health advice" refers to specific instructions or recommendations based on the analysis results aimed at improving the user's lifestyle habits.

[0565] A "terminal" is a device through which a user receives health advice. Examples include smartphones and tablets.

[0566] "Product recommendation" refers to recommending specific products to encourage purchase based on the user's health status.

[0567] "Discount and campaign information" is information about special offers and price reductions that are intended to increase the user's purchasing motivation.

[0568] This invention is a system that collects data from devices that monitor a user's biometric information, transmits the data to a server, stores it, preprocesses it, and analyzes it. Furthermore, it uses generative AI to provide personalized health advice, and generates and provides product recommendations and discount information based on the user's health status, thereby supporting the user's health management and purchasing behavior.

[0569] System Configuration

[0570] The system consists of the following main components:

[0571] 1. Monitoring devices: Devices such as smartwatches and fitness trackers collect biometric information such as a user's heart rate, steps taken, sleep time, and calories burned.

[0572] 2. Server:

[0573] Data storage: The biometric data sent from the monitoring device is stored in a database such as Amazon RDS.

[0574] Preprocessing: Use AWS Lambda to perform error correction, missing value imputation, and outlier filtering.

[0575] Data analysis: Use Amazon SageMaker to analyze data and identify user habits and health conditions.

[0576] Generative AI: Using generative AI models such as GPT-4, personalized health advice is generated based on the analysis results.

[0577] 3. Mobile Applications: Applications developed on iOS and Android platforms (e.g., Xcode, Android Studio) inform users of health advice, product recommendations, and discount information.

[0578] Program processing

[0579] 1. Data collection and transmission: The monitoring device collects the user's biometric information in real time and transmits the data to the server at regular intervals. This data is marked with a timestamp and user ID.

[0580] 2. Data storage and preprocessing: The server stores the data in a database and then uses AWS Lambda to preprocess the data, specifically imputing missing data and filtering outliers.

[0581] 3. Data analysis and generation: Using Amazon SageMaker, the preprocessed data is analyzed to identify the user's lifestyle habits and health status. A generative AI (e.g., GPT-4) generates personalized health advice based on the analysis results.

[0582] 4. Advice Delivery: The generated health advice, product recommendations, and discount information are sent to the user via the mobile application. For example, specific advice such as "You haven't been exercising enough today, so aim for 2,000 more steps" is provided.

[0583] 5. Product recommendations based on health status: Generative AI recommends appropriate products (e.g., health foods and fitness products) based on the user's health status.

[0584] 6. Discount and campaign information: Generate discount codes and campaign information linked to the user's health status and provide it to the user.

[0585] Examples of concrete examples and prompts

[0586] For example, if the user's biometric information is "heart rate: 70 bpm, number of steps: 8,000, sleep time: 7 hours, calories burned: 2,500 kcal," the following prompt sentence is input to the generation AI:

[0587] Based on the user's health data (heart rate: 70 bpm, number of steps: 8000 steps, sleep time: 7 hours, calories burned: 2500 kcal), recommend healthy foods and exercise equipment, and generate discount and campaign information applicable to their purchase.

[0588] This will enable the realization of a system that provides users with specific advice and recommended products tailored to their health, as well as economic incentives, leading to the maintenance of their health and behavioral changes.

[0589] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0590] Step 1:

[0591] The monitoring device (terminal) collects biometric information such as the user's heart rate, number of steps, sleep time, and calories burned in real time. This data is temporarily stored in the terminal's local storage at regular intervals (e.g., every hour). The terminal then transmits the data to a server. The input is the user's biometric information, and the output is a data file sent to the server.

[0592] Step 2:

[0593] The server receives the biometric data sent from the device and records it in a database. The data is assigned a timestamp and user ID and is organized by user. The input is the biometric data sent from the device, and the output is the data stored in the database.

[0594] Step 3:

[0595] The server preprocesses the incoming data. It uses AWS Lambda to impute missing data and filter outliers. This processing improves the accuracy of the data. The input is the stored biometric data, and the output is the preprocessed data.

[0596] Step 4:

[0597] The server analyzes the preprocessed data. Amazon SageMaker is used to identify the user's lifestyle and health status (for example, average heart rate, total number of steps, sleep patterns, etc.). The input is the preprocessed data, and the output is the analysis results. Specifically, the server analyzes the data and extracts trends.

[0598] Step 5:

[0599] The generative AI (for example, GPT-4) generates individual health advice based on the analysis results. Specific advice is generated based on the analysis results, which are input as a prompt. The input is the analysis results, and the output is the generated health advice. Specifically, the prompt is input into the generative AI model, and the result is received as text.

[0600] Step 6:

[0601] The server sends the generated health advice to the user's device. The user's device receives a notification through the application and can check the advice. The input is the generated health advice, and the output is the notification to the user's device. Specifically, the server pushes the advice through the notification system.

[0602] Step 7:

[0603] The server recommends suitable products to the user based on the generated health advice. These recommendations include products according to the user's health condition (e.g., health foods and fitness products). The input is the generated health advice, and the output is a list of recommended products. Specifically, the server selects suitable products from a database and creates a list.

[0604] Step 8:

[0605] The server generates discount and campaign information based on the user's health status. It uses a generative AI model to create optimal discount codes and campaign information. The input is the user's health information and analysis results, and the output is discount and campaign information. Specifically, the server works in conjunction with the sales promotion system to generate applicable promotions.

[0606] Step 9:

[0607] The server sends the generated discount and campaign information to the user's terminal. The user's terminal can receive and use this information through an application. The input is the generated discount and campaign information, and the output is a notification to the user's terminal. In concrete terms, the server distributes the information via the campaign management system.

[0608] 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.

[0609] This invention combines a monitoring device that monitors a user's biometric information, a system that transmits the data to a server, and provides individually optimized health advice using preprocessing, analysis, and generation AI, with an emotion engine that recognizes the user's emotions.

[0610] Program processing

[0611] Data collection

[0612] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and then transmits it to the server at the data transfer timing.

[0613] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[0614] Data storage

[0615] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[0616] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[0617] Data Preprocessing

[0618] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[0619] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[0620] Emotion recognition

[0621] The server recognizes the user's emotions based on the pre-processed data using an emotion engine, which analyzes the user's short-term and long-term emotional state from their biometric and activity data.

[0622] For example, the possibility that the user is feeling stressed can be estimated based on fluctuations in heart rate and activity patterns.

[0623] Lifestyle analysis

[0624] The server then comprehensively analyzes the pre-processed data, including the results of the emotion engine analysis, to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information.

[0625] For example, the system can calculate a user's average number of steps and sleep time from a week's data to evaluate their exercise habits and sleep quality, and identify stress levels and emotional fluctuation patterns from emotional data.

[0626] Generating health advice

[0627] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results and emotional data as input and creates optimal advice for each user.

[0628] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day." If it detects signs of stress, it will provide advice such as "We recommend deep breathing exercises to help you relax."

[0629] Advice Delivery

[0630] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[0631] Users can view the advice by receiving a notification on their device, or by tapping the notification, they can open the app and view the detailed advice.

[0632] For example, you can receive notifications such as "You haven't been exercising enough today, so aim for 2,000 more steps" or "Try meditating for 5 minutes to relax."

[0633] In this way, the present invention provides multifaceted support for the user's health management by providing individually optimized health advice based on the user's biometric information and emotional data.

[0634] The processing flow will be explained below.

[0635] Step 1: Data collection

[0636] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[0637] Step 2: Data Transfer

[0638] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[0639] Step 3: Receiving and storing data

[0640] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[0641] Step 4: Preprocessing the data

[0642] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[0643] Step 5: Recognize emotions

[0644] The server uses an emotion engine to recognize the user's emotions based on the preprocessed data. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it estimates the possibility that the user is feeling stressed based on fluctuations in their heart rate and activity patterns.

[0645] Step 6: Lifestyle analysis

[0646] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[0647] Step 7: Generate health advice

[0648] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis results and emotional data as input and creates optimal advice for each user. For example, if it determines that a user is not getting enough exercise, it generates specific advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, it also provides advice such as "We recommend deep breathing exercises to relax."

[0649] Step 8: Distributing Advice

[0650] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[0651] Step 9: Receive and review advice

[0652] Users receive a notification on their device and can check the advice. By tapping the notification, they can open the app and view detailed advice. For example, they can receive a notification such as "Today you haven't been exercising enough, so aim for 2,000 more steps" or "Try 5 minutes of meditation to relax."

[0653] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[0654] Example 2

[0655] 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."

[0656] The problem that this invention aims to solve is to efficiently and accurately collect a user's biometric information and provide individually optimized health advice based on that data. In particular, it is necessary to generate health advice that takes into account the user's emotional state and support comprehensive health management in daily life. It is also necessary to appropriately handle quality issues such as missing data and outliers, and to achieve high-precision data analysis.

[0657] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a preprocessing means for correcting data errors, complementing missing values, and filtering outliers, a means for recognizing a user's emotions through an emotion engine using the preprocessed data, a means for identifying the user's lifestyle habits by analyzing the preprocessed data and emotion data, a means for generating individual health advice for each user using a generation AI based on the analysis results and emotion data, and a means for transmitting the health advice to the user's terminal and notifying the user. This makes it possible to provide individually optimized health advice with high accuracy based on the user's biometric information and emotion data.

[0658] "User's biometric information" refers to physical data from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned.

[0659] "Monitoring device" refers to a terminal used to constantly monitor and collect a user's biometric information.

[0660] "Server" refers to a computer system for storing, pre-processing, and analyzing data transmitted from monitoring devices.

[0661] "Preprocessing" refers to the process of correcting errors in the collected raw data, filling in missing values, and filtering outliers.

[0662] "Emotion engine" refers to a function that uses biometric and activity data to analyze and recognize a user's emotional state.

[0663] "Generative AI" refers to artificial intelligence that automatically generates optimal health advice for each user based on analysis results and emotional data.

[0664] "Health advice" refers to specific advice aimed at improving lifestyle habits and promoting health, generated based on the user's biometric information and emotional data.

[0665] "Missing value imputation" refers to the process of filling in missing data with other valid data.

[0666] "Outlier filtering" refers to the process of removing values ​​in the data that are deemed to be clearly inaccurate, such as abnormally high or low values.

[0667] "Database" refers to a system within the server for organizing and storing received and pre-processed data.

[0668] "Notification system" refers to a function for sending health advice to a user's terminal and notifying the user.

[0669] This invention is a system for monitoring and collecting a user's biometric information and providing individually optimized health advice to the user. Specifically, the system uses data acquired by a monitoring device, preprocesses and analyzes the data, and provides advice using generative AI.

[0670] Hardware and Software Configuration

[0671] Monitoring Devices:

[0672] Devices (e.g. fitness trackers, smartwatches) contain sensors such as:

[0673] Heart rate sensor

[0674] Acceleration sensor

[0675] Gyroscope

[0676] This allows the system to constantly monitor and collect biometric information such as the user's heart rate, number of steps taken, sleep time, and calories burned.

[0677] server:

[0678] The following hardware and software are used for data storage, preprocessing, and analysis:

[0679] Database servers (e.g. MySQL, MongoDB)

[0680] Data analysis tools (e.g., Scikit-learn, TensorFlow)

[0681] Emotion engine (e.g. Microsoft Azure Emotion API)

[0682] Generative AI models (e.g., OpenAI GPT-4)

[0683] Communication modules (e.g. REST API servers)

[0684] Processing Flow

[0685] First, the device collects the user's biometric information in real time. For example, a heart rate sensor measures the heart rate every second, and an acceleration sensor counts the number of steps. This data is accumulated in local storage at regular intervals (for example, every hour).

[0686] Next, the device transmits the collected data to the server via wireless communication (Bluetooth or Wi-Fi). When the transmitted data is received by the server, it is first stored in a database.

[0687] The server preprocesses the received raw data, which includes error correction, missing value imputation, and outlier filtering. The preprocessed data is then stored in the database again.

[0688] The server then uses an emotion engine to recognize the user's emotions based on the pre-processed data, analyzing the short-term and long-term emotional states to obtain emotion data.

[0689] The server comprehensively analyzes the pre-processed data and emotional data to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc. Based on the results of this analysis, a generative AI model is run to generate personalized health advice for each user.

[0690] The generated health advice is sent to the user's device via the notification system. The user can then check the notification displayed on the device and view the detailed advice in the app.

[0691] Examples and prompts

[0692] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server then preprocesses the data and recognizes their emotional state, determining that the user is experiencing moderate stress.

[0693] At this point, the database contains preprocessed data and emotion data. The server analyzes this data and inputs the following prompt to the generative AI model:

[0694] Generate health advice based on the user's biometric and emotional data. Use the following data:

[0695] Heart rate: 70 bpm

[0696] Daily steps: 8,000

[0697] Stress level: Moderate

[0698] Sleep time: 6 hours

[0699] Based on this prompt, the generative AI model generates health advice such as, "Based on your recent data, your daily exercise volume is appropriate, but your sleep time is somewhat insufficient. Try to get at least seven hours of sleep each night. Also, you appear to be at a moderate level of stress, so try incorporating deep breathing exercises to help you relax."

[0700] As a result, the present invention provides individually optimized health advice based on the user's biometric information and emotional data, and provides comprehensive support for the user's health management.

[0701] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0702] Step 1: Data collection

[0703] Devices (e.g., fitness trackers, smartwatches) use sensors to collect biometric information such as a user's heart rate, number of steps, sleep time, and calories burned in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer counts the number of steps, and the gyroscope detects the user's movements and estimates sleep time.

[0704] Input: The user's actual biometric data

[0705] Output: Measured biological information data (heart rate, steps, sleep time, calories burned)

[0706] Step 2: Sending data

[0707] The device accumulates the collected data in local storage at regular intervals (for example, every hour), and then transmits it to the server via wireless communication (Bluetooth or Wi-Fi). The data is packetized and sent to the server using a secure communication protocol (for example, HTTPS).

[0708] Input: Biometric data stored in local storage

[0709] Output: Biometric data sent to the server

[0710] Step 3: Save your data

[0711] The server receives the data sent from the device, temporarily stores it in memory, and then saves it in a database (e.g., MySQL or MongoDB). The data is assigned a timestamp and user ID and organized appropriately.

[0712] Input: Received biometric data

[0713] Output: Biometric data stored in a database

[0714] Step 4: Preprocessing the data

[0715] The server preprocesses the stored data. This preprocessing includes correcting errors in the data, imputing missing values, and filtering outliers. The preprocessed data is then saved back into the database. Specifically, the raw data is read from the database, and a Python script cleans the data using the Pandas library.

[0716] Input: Biometric data stored in a database

[0717] Output: Preprocessed biometric data

[0718] Step 5: Recognize emotions

[0719] The server analyzes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API) based on the preprocessed data. It sends the input data to the API and obtains the emotion recognition results, which are then stored in a database.

[0720] Input: Preprocessed biometric data

[0721] Output: Emotion data obtained from the emotion engine

[0722] Step 6: Lifestyle analysis

[0723] The server uses data analysis tools (e.g., Scikit-learn, TensorFlow) to comprehensively analyze the preprocessed data and emotion data, thereby identifying the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0724] Input: Preprocessed biometric and emotion data

[0725] Output: Analyzed lifestyle data

[0726] Step 7: Generate health advice

[0727] The server generates health advice using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results and emotion data. The generative AI model receives specific prompts as input and generates optimal advice.

[0728] Example prompt:

[0729] Generate health advice based on the user's biometric and emotional data. Use the following data:

[0730] Heart rate: 70 bpm

[0731] Daily steps: 8,000

[0732] Stress level: Moderate

[0733] Sleep time: 6 hours

[0734] Input: Analysis results and emotion data

[0735] Output: Generated health advice

[0736] Step 8: Distributing Advice

[0737] The server sends the generated health advice to the user's device using a notification system (e.g., Firebase Cloud Messaging). The user receives a notification displayed on the device and can view detailed advice in the app.

[0738] Input: Generated health advice

[0739] Output: Notification sent to the user's device

[0740] (Application example 2)

[0741] 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."

[0742] Conventional health advice systems provide certain health advice based on a user's biometric information, but because they do not take the user's emotional state into account, it is difficult to provide individual dietary and health advice tailored to the user's actual needs. This also limits the effectiveness of the advice provided, resulting in a low effectiveness in managing the user's health.

[0743] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0744] In this invention, the server includes means for identifying the user's biometric information and emotional data, means for generating personalized health and dietary advice using a generation AI based on the analysis results and emotional data, and means for transmitting and notifying the generated health and dietary advice to the user's terminal. This allows for the provision of personalized dietary and health advice based on the user's actual health and emotional state, making it possible to more effectively manage the user's health.

[0745] - "Biometric information" refers to data that indicates the user's physical condition, such as the user's heart rate, number of steps taken, and calories burned.

[0746] A "device" is a device for monitoring a user's biometric information and collecting data.

[0747] "Server" means a device or system that receives collected data and performs storage, pre-processing, analysis, and generative AI.

[0748] "Preprocessing" refers to the process of correcting or removing errors, missing values, and outliers from collected data and converting it into a format suitable for analysis.

[0749] "Analysis" is the process of identifying a user's lifestyle habits and emotions based on preprocessed data.

[0750] "Emotion data" is data relating to the emotional state of the user analyzed from biometric information and activity data.

[0751] "Generative AI" is an artificial intelligence technology that generates individual health and dietary advice for each user based on analysis results and emotional data.

[0752] "Health advice" is specific instructions or suggestions related to a user's exercise, diet, and rest.

[0753] "Sending" is the process of delivering the generated advice from the server to the user's terminal.

[0754] "Notifications" is a feature that notifies users of advice and reminders displayed on the device.

[0755] The present invention is a system that monitors a user's biological information and provides personalized health and dietary advice based on the acquired data. The system consists of a monitoring device, a server, a food delivery application, and a user terminal.

[0756] First, the user wears a monitoring device. This device collects biometric information such as heart rate, number of steps, and calories burned in real time. This data is stored in local storage at regular intervals and sent to the server as appropriate. For example, if a user walks 8,000 steps in a day and their average heart rate is 70 bpm, this data will be collected and sent to the server every hour.

[0757] The server receives the data sent from the device and stores it in a database. The received data is appended with a timestamp and user ID, and the data is organized for each user. Daily exercise data and heart rate data are organized by each user's ID and stored in the database.

[0758] Data preprocessing involves error correction, missing value completion, and outlier filtering. For example, if heart rate data is missing, it is completed based on valid data before and after, and abnormally high heart rate data is excluded. The preprocessed data is then resaved.

[0759] The server then uses the preprocessed data to recognize the user's emotions using an emotion engine. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it can estimate the user's likelihood of feeling stressed based on fluctuations in their heart rate and activity patterns.

[0760] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[0761] Based on the analysis results and emotion data, the generative AI generates optimal health and dietary advice for each user. The generative AI model is built using TensorFlow and inputs the analysis results and emotion data as prompts. The generated advice includes specific exercise, diet, and rest recommendations.

[0762] For example, if a user is judged to be lacking in exercise, the system will generate advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, the system will provide advice such as "We recommend deep breathing exercises to help you relax." Furthermore, a system built into a food delivery application will recommend menus containing ingredients that have a relaxing effect to users who are feeling stressed.

[0763] The generated health and diet advice is sent to the user's device and delivered to them through a notification system, where they can tap on the notification to view the detailed advice.

[0764] The following are examples of specific prompt sentences:

[0765] Prompt Sentence Examples

[0766] Input data:

[0767] Heart rate: 72 bpm

[0768] Steps: 5,000 steps

[0769] Calories burned: 350 kcal

[0770] Emotional state: Stress level 0.7

[0771] Generation advice:

[0772] Your heart rate is in the normal range, but you may not be getting enough exercise. Your stress levels are high, so we recommend a dinner that includes foods that have a relaxing effect (e.g., bananas and nuts). You should also set a goal to walk a little more each day. For example, aim for 7,000 steps tomorrow.

[0773] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0774] Step 1:

[0775] The monitoring device collects the user's biometric information. The input is data such as heart rate, steps, and calories burned. The device monitors this data in real time and stores it in local storage. The output is the collected biometric data.

[0776] Step 2:

[0777] The monitoring device transmits biometric data to the server at regular intervals. The input is the biometric data stored in the local storage. The data is transmitted from the device to the server. The output is the biometric data transmitted to the server.

[0778] Step 3:

[0779] The server receives the transmitted biometric data and stores it in a database. The input is the biometric data sent from the device. The data is stored in the database and organized by timestamp and user ID. The output is organized and stored biometric data.

[0780] Step 4:

[0781] The server preprocesses the received data. Preprocessing includes missing value imputation, outlier filtering, and error correction. The input is biometric data stored in a database. For example, if heart rate data is missing, it is imputed based on previous and subsequent data, and abnormally high heart rate data is excluded. The output is the preprocessed biometric data.

[0782] Step 5:

[0783] The server analyzes the user's emotions using an emotion engine based on the preprocessed data. The input is preprocessed biometric data. The emotion engine estimates the user's stress level and emotional state from fluctuations in heart rate and activity patterns. The output is analyzed emotion data.

[0784] Step 6:

[0785] The server comprehensively analyzes the preprocessed data and emotional data. The input is the preprocessed biometric data and emotional data. The data analysis identifies the user's lifestyle habits, exercise patterns, stress level, etc. The output is the analysis results.

[0786] Step 7:

[0787] The server uses generative AI to generate personalized health and diet advice based on the analysis results and emotional data. The input is the analysis results and emotional data. The generative AI model (e.g., TensorFlow) uses the analysis results and emotional data to generate advice. For example, advice such as "30 minutes of walking daily is recommended" may be generated for lack of exercise, or "a dinner containing ingredients with a relaxing effect is recommended" for high stress levels. The output is the generated health and diet advice.

[0788] Step 8:

[0789] The server sends the generated health and diet advice to the user's device and notifies them. The input is the generated health and diet advice. The advice is sent to the device and delivered to the user through the notification system. When the user receives the notification, they can tap it to view the detailed advice. The output is the advice and notification displayed on the user's device.

[0790] This process allows users to receive personalized health and dietary advice based on their biometrics and emotional state.

[0791] 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.

[0792] 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.

[0793] 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.

[0794] [Third embodiment]

[0795] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0796] 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.

[0797] 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).

[0798] 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.

[0799] 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.

[0800] 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).

[0801] 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.

[0802] 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.

[0803] 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.

[0804] 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.

[0805] 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.

[0806] 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."

[0807] The present invention relates to a monitoring device that monitors a user's biometric information, and a system that transmits the collected data to a server, preprocesses and analyzes it, and uses generative AI to provide personalized health advice.

[0808] Program processing

[0809] Data collection

[0810] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and also transmits this data to the server at the timing of data transfer.

[0811] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[0812] Data storage

[0813] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[0814] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[0815] Data Preprocessing

[0816] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[0817] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[0818] Lifestyle analysis

[0819] The server analyzes the pre-processed data, which identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0820] For example, the system calculates a user's average number of steps and sleep time from a week's data and evaluates their exercise habits and sleep quality.

[0821] Generating health advice

[0822] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results as input and creates optimal advice for each user.

[0823] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day."

[0824] Advice Delivery

[0825] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[0826] The user checks the advice in the notification sent to the device. For example, they may receive a notification saying, "You haven't been exercising enough today, so aim for another 2,000 steps." This system allows users to know the specific steps they need to take to improve their lifestyle habits.

[0827] In this way, the present invention is a system that supports a user's own health management by providing individually optimized health advice based on the user's biological information.

[0828] The processing flow will be explained below.

[0829] Step 1: Data collection

[0830] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[0831] Step 2: Data Transfer

[0832] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[0833] Step 3: Receiving and storing data

[0834] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[0835] Step 4: Preprocessing the data

[0836] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[0837] Step 5: Lifestyle analysis

[0838] The server uses the preprocessed data to analyze the user's lifestyle. The analysis algorithm receives the data as input and derives the user's exercise patterns, average heart rate, sleep patterns, etc. For example, daily step count data can be compiled to evaluate exercise habits.

[0839] Step 6: Generate health advice

[0840] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis data as input and creates optimal advice for each user. For example, based on data from the past week, it generates specific advice such as "We recommend walking 30 minutes every day."

[0841] Step 7: Distributing Advice

[0842] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[0843] Step 8: Receive and review advice

[0844] The user receives a notification on their device and can confirm the advice. If the user taps the notification, they can open the app and view detailed advice. For example, they can confirm and follow advice such as "You haven't been exercising enough today, so aim for another 2,000 steps."

[0845] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[0846] Example 1

[0847] 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."

[0848] In modern society, many people recognize the importance of health management, but finding specific ways to improve their lifestyle habits is difficult. Furthermore, providing optimal health advice to individual users requires accurate preprocessing and analysis of collected biometric data. However, there is a lack of efficient means for processing biometric data that contains outliers and missing values. This makes it difficult to provide specific, individually optimized health advice.

[0849] 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.

[0850] In this invention, the server includes means for collecting data from a device that monitors a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating individual health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, and means for the monitoring device to collect and transmit data at regular intervals. This makes it possible to accurately collect the user's biological information, perform pre-processing, and analyze the lifestyle habits, and then provide the user with individually optimized health advice.

[0851] "User's biological information" is data that indicates the health condition of each individual user in their daily life, such as heart rate, number of steps, sleep time, and calories burned.

[0852] A "monitoring device" is a device used to collect biometric information from a user, and includes wearable devices and smartphones.

[0853] A "server" is a computer system that receives, stores, pre-processes, and analyzes data sent from a terminal.

[0854] "Storing data" refers to recording information received from a terminal in a specific storage device or database.

[0855] "Preprocessing" refers to processing performed on collected biometric information data, and includes error correction, missing value completion, and outlier filtering.

[0856] "Data analysis" refers to the use of pre-processed data to perform calculations and evaluations to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[0857] "Generative AI" refers to an AI model that uses artificial intelligence technology to generate personalized health advice for each user based on specific input data.

[0858] "Health advice" refers to specific instructions or recommendations for improving the user's health, derived from the analysis results by the generative AI.

[0859] The "notification system" is a system for transmitting the generated health advice to the user's terminal and notifying the user.

[0860] An "interval" is a set time interval or frequency at which data is collected or transmitted.

[0861] The present invention is a system for monitoring a user's biological information, and a specific implementation method will be described here. Specific names of the hardware and software used and examples of prompt sentences will also be clearly stated.

[0862] This system includes a monitoring device (terminal), a server for data processing and storage, and a generative AI model for providing advice to users. The user wears a monitoring device that collects biometric information from daily life, such as heart rate, number of steps, sleep time, and calories burned. This device can be a wearable device or a smartphone, for example.

[0863] Program processing

[0864] Data collection

[0865] The device continuously monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. This data is stored in local storage at regular intervals. For example, data is collected every second and sent to the server every hour.

[0866] Data storage

[0867] The server receives the data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery. Each piece of data is assigned a timestamp and a user ID, which allows the data to be organized for each user.

[0868] Data Preprocessing

[0869] The server performs error correction, missing value completion, and outlier filtering on the received data, often using scripting languages ​​such as Python or R. Once preprocessing is complete, the data is stored back in the database.

[0870] Lifestyle analysis

[0871] The server analyzes the preprocessed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns using distributed processing frameworks such as Spark and Hadoop.

[0872] Generating health advice

[0873] The server generates personalized health advice using a generative AI model (e.g., GPT-4) based on the analysis results. It also generates prompts to input the analysis results and inputs them into the generative AI.

[0874] Example prompt sentence:

[0875] User ID: 12345

[0876] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[0877] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[0878] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[0879] Use this data to generate personalized health improvement advice for users.

[0880] Advice Delivery

[0881] The server sends the generated health advice to the user's device. The advice is notified to the user using a notification system such as Firebase Cloud Messaging or Amazon SNS. The user can check the notification received on their device and improve their lifestyle based on the advice.

[0882] Specific examples

[0883] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server stores the data using RDS and preprocesses it with a Python script. The resulting prompt is then fed to the generative AI model, which then generates advice for the user, such as "We recommend walking 30 minutes daily."

[0884] In this way, this system accurately collects the user's biometric information, performs preprocessing, analyzes lifestyle habits, and provides individually optimized health advice to the user, thereby supporting the user's health management.

[0885] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0886] Step 1:

[0887] Data collection

[0888] The device continuously monitors the user's biometric information, such as heart rate, steps taken, sleep time, and calories burned, and stores the data in local storage at regular intervals (e.g., every second).

[0889] Specific operation: Acquires data from the heart rate sensor and accelerometer and stores it in local storage.

[0890] Input: Real-time biometric data of the user

[0891] Output: Biometric data stored in local storage

[0892] Step 2:

[0893] Data transmission

[0894] After a certain period of time has elapsed (for example, every hour), the terminal transmits the biometric information data accumulated in the local storage to the server.

[0895] Specific operation: Data is divided into packets and sent to a server over the Internet.

[0896] Input: Biometric data stored in local storage

[0897] Output: Biometric data sent to the server

[0898] Step 3:

[0899] Data storage

[0900] The server receives the biometric data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery.

[0901] Specific operation: Receive data, assign a timestamp and user ID to each data, and save it in the database.

[0902] Input: Biometric data sent from the device

[0903] Output: Aligned biometric data stored in a database

[0904] Step 4:

[0905] Data Preprocessing

[0906] The server performs error correction, missing value completion, and outlier filtering on the received data using Python and R scripts.

[0907] Specific operations: Detect and remove outliers, impute missing values, and perform noise reduction.

[0908] Input: Biometric data stored in a database

[0909] Output: Clean biometric data after preprocessing

[0910] Step 5:

[0911] Lifestyle analysis

[0912] The server analyzes the pre-processed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns, using distributed processing frameworks such as Spark and Hadoop.

[0913] Specific operation: Aggregate one week's worth of data and calculate average values ​​and trends.

[0914] Input: Clean, pre-processed biometric data

[0915] Output: Analysis results (user's lifestyle data)

[0916] Step 6:

[0917] Generating health advice

[0918] The server uses a generative AI model (e.g., GPT-4) to generate personalized health advice for each user based on the analysis results.

[0919] Specific operation: The analysis results are input into the generation AI as a prompt sentence, and a response is obtained from the AI.

[0920] Input: Analysis results (user's lifestyle data)

[0921] Output: Generated personalized health advice

[0922] Step 7:

[0923] Advice Delivery

[0924] The server sends the generated health advice to the user's device using a notification system such as Firebase Cloud Messaging or Amazon SNS.

[0925] Specific operation: A notification message is constructed and sent to the device. The user receives it and uses it to improve their lifestyle habits.

[0926] Input: Generated personalized health advice

[0927] Output: Health advice notification delivered to the user's device

[0928] Example prompt sentence:

[0929] User ID: 12345

[0930] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[0931] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[0932] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[0933] Use this data to generate personalized health improvement advice for users.

[0934]

[0935] (Application example 1)

[0936] 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."

[0937] Conventional health management systems only collect users' biometric information and provide health advice based on the analysis results. However, they do not consider recommending specific products based on the user's health status or providing related discounts or campaign information. As a result, there is a lack of means to encourage users to make practical and economical improvements. This problem remains unsolved due to a lack of incentives to motivate users and encourage behavioral change.

[0938] 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.

[0939] In this invention, the server includes means for collecting data from devices that monitor a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating personalized health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, means for recommending products based on the generated health advice according to the user's health condition, and means for generating discount and campaign information based on the health condition. This makes it easier for users to purchase specific products and services based on their health condition, thereby increasing their motivation to improve their health.

[0940] "User's biological information" is data that indicates the user's health condition, such as heart rate, number of steps, sleep time, and calories burned.

[0941] A "monitoring device" is a device for collecting biometric information from a user. Examples include smartwatches and fitness trackers.

[0942] A "server" is a computer system for storing, preprocessing, and analyzing collected biometric information.

[0943] "Storage" means recording collected data for future reference.

[0944] "Preprocessing" refers to the process of correcting errors in biometric information data, complementing missing values, and filtering outliers.

[0945] "Analysis" refers to identifying a user's lifestyle and health status using preprocessed data.

[0946] "Generative AI" is a technology that uses artificial intelligence to generate useful information and advice from specific input data.

[0947] "Health advice" refers to specific instructions or recommendations based on the analysis results aimed at improving the user's lifestyle habits.

[0948] A "terminal" is a device through which a user receives health advice. Examples include smartphones and tablets.

[0949] "Product recommendation" refers to recommending specific products to encourage purchase based on the user's health status.

[0950] "Discount and campaign information" is information about special offers and price reductions that are intended to increase the user's purchasing motivation.

[0951] This invention is a system that collects data from devices that monitor a user's biometric information, transmits the data to a server, stores it, preprocesses it, and analyzes it. Furthermore, it uses generative AI to provide personalized health advice, and generates and provides product recommendations and discount information based on the user's health status, thereby supporting the user's health management and purchasing behavior.

[0952] System Configuration

[0953] The system consists of the following main components:

[0954] 1. Monitoring devices: Devices such as smartwatches and fitness trackers collect biometric information such as a user's heart rate, steps taken, sleep time, and calories burned.

[0955] 2. Server:

[0956] Data storage: The biometric data sent from the monitoring device is stored in a database such as Amazon RDS.

[0957] Preprocessing: Use AWS Lambda to perform error correction, missing value imputation, and outlier filtering.

[0958] Data analysis: Use Amazon SageMaker to analyze data and identify user habits and health conditions.

[0959] Generative AI: Using generative AI models such as GPT-4, personalized health advice is generated based on the analysis results.

[0960] 3. Mobile Applications: Applications developed on iOS and Android platforms (e.g., Xcode, Android Studio) inform users of health advice, product recommendations, and discount information.

[0961] Program processing

[0962] 1. Data collection and transmission: The monitoring device collects the user's biometric information in real time and transmits the data to the server at regular intervals. This data is marked with a timestamp and user ID.

[0963] 2. Data storage and preprocessing: The server stores the data in a database and then uses AWS Lambda to preprocess the data, specifically imputing missing data and filtering outliers.

[0964] 3. Data analysis and generation: Using Amazon SageMaker, the preprocessed data is analyzed to identify the user's lifestyle habits and health status. A generative AI (e.g., GPT-4) generates personalized health advice based on the analysis results.

[0965] 4. Advice Delivery: The generated health advice, product recommendations, and discount information are sent to the user via the mobile application. For example, specific advice such as "You haven't been exercising enough today, so aim for 2,000 more steps" is provided.

[0966] 5. Product recommendations based on health status: Generative AI recommends appropriate products (e.g., health foods and fitness products) based on the user's health status.

[0967] 6. Discount and campaign information: Generate discount codes and campaign information linked to the user's health status and provide it to the user.

[0968] Examples of concrete examples and prompts

[0969] For example, if the user's biometric information is "heart rate: 70 bpm, number of steps: 8,000, sleep time: 7 hours, calories burned: 2,500 kcal," the following prompt sentence is input to the generation AI:

[0970] Based on the user's health data (heart rate: 70 bpm, number of steps: 8000 steps, sleep time: 7 hours, calories burned: 2500 kcal), recommend healthy foods and exercise equipment, and generate discount and campaign information applicable to their purchase.

[0971] This will enable the realization of a system that provides users with specific advice and recommended products tailored to their health, as well as economic incentives, leading to the maintenance of their health and behavioral changes.

[0972] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0973] Step 1:

[0974] The monitoring device (terminal) collects biometric information such as the user's heart rate, number of steps, sleep time, and calories burned in real time. This data is temporarily stored in the terminal's local storage at regular intervals (e.g., every hour). The terminal then transmits the data to a server. The input is the user's biometric information, and the output is a data file sent to the server.

[0975] Step 2:

[0976] The server receives the biometric data sent from the device and records it in a database. The data is assigned a timestamp and user ID and is organized by user. The input is the biometric data sent from the device, and the output is the data stored in the database.

[0977] Step 3:

[0978] The server preprocesses the incoming data. It uses AWS Lambda to impute missing data and filter outliers. This processing improves the accuracy of the data. The input is the stored biometric data, and the output is the preprocessed data.

[0979] Step 4:

[0980] The server analyzes the preprocessed data. Amazon SageMaker is used to identify the user's lifestyle and health status (for example, average heart rate, total number of steps, sleep patterns, etc.). The input is the preprocessed data, and the output is the analysis results. Specifically, the server analyzes the data and extracts trends.

[0981] Step 5:

[0982] The generative AI (for example, GPT-4) generates individual health advice based on the analysis results. Specific advice is generated based on the analysis results, which are input as a prompt. The input is the analysis results, and the output is the generated health advice. Specifically, the prompt is input into the generative AI model, and the result is received as text.

[0983] Step 6:

[0984] The server sends the generated health advice to the user's device. The user's device receives a notification through the application and can check the advice. The input is the generated health advice, and the output is the notification to the user's device. Specifically, the server pushes the advice through the notification system.

[0985] Step 7:

[0986] The server recommends suitable products to the user based on the generated health advice. These recommendations include products according to the user's health condition (e.g., health foods and fitness products). The input is the generated health advice, and the output is a list of recommended products. Specifically, the server selects suitable products from a database and creates a list.

[0987] Step 8:

[0988] The server generates discount and campaign information based on the user's health status. It uses a generative AI model to create optimal discount codes and campaign information. The input is the user's health information and analysis results, and the output is discount and campaign information. Specifically, the server works in conjunction with the sales promotion system to generate applicable promotions.

[0989] Step 9:

[0990] The server sends the generated discount and campaign information to the user's terminal. The user's terminal can receive and use this information through an application. The input is the generated discount and campaign information, and the output is a notification to the user's terminal. In concrete terms, the server distributes the information via the campaign management system.

[0991] 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.

[0992] This invention combines a monitoring device that monitors a user's biometric information, a system that transmits the data to a server, and provides individually optimized health advice using preprocessing, analysis, and generation AI, with an emotion engine that recognizes the user's emotions.

[0993] Program processing

[0994] Data collection

[0995] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and then transmits it to the server at the data transfer timing.

[0996] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[0997] Data storage

[0998] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[0999] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[1000] Data Preprocessing

[1001] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[1002] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[1003] Emotion recognition

[1004] The server recognizes the user's emotions based on the pre-processed data using an emotion engine, which analyzes the user's short-term and long-term emotional state from their biometric and activity data.

[1005] For example, the possibility that the user is feeling stressed can be estimated based on fluctuations in heart rate and activity patterns.

[1006] Lifestyle analysis

[1007] The server then comprehensively analyzes the pre-processed data, including the results of the emotion engine analysis, to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information.

[1008] For example, the system can calculate a user's average number of steps and sleep time from a week's data to evaluate their exercise habits and sleep quality, and identify stress levels and emotional fluctuation patterns from emotional data.

[1009] Generating health advice

[1010] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results and emotional data as input and creates optimal advice for each user.

[1011] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day." If it detects signs of stress, it will provide advice such as "We recommend deep breathing exercises to help you relax."

[1012] Advice Delivery

[1013] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[1014] Users can view the advice by receiving a notification on their device, or by tapping the notification, they can open the app and view the detailed advice.

[1015] For example, you can receive notifications such as "You haven't been exercising enough today, so aim for 2,000 more steps" or "Try meditating for 5 minutes to relax."

[1016] In this way, the present invention provides multifaceted support for the user's health management by providing individually optimized health advice based on the user's biometric information and emotional data.

[1017] The processing flow will be explained below.

[1018] Step 1: Data collection

[1019] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[1020] Step 2: Data Transfer

[1021] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[1022] Step 3: Receiving and storing data

[1023] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[1024] Step 4: Preprocessing the data

[1025] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[1026] Step 5: Recognize emotions

[1027] The server uses an emotion engine to recognize the user's emotions based on the preprocessed data. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it estimates the possibility that the user is feeling stressed based on fluctuations in their heart rate and activity patterns.

[1028] Step 6: Lifestyle analysis

[1029] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[1030] Step 7: Generate health advice

[1031] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis results and emotional data as input and creates optimal advice for each user. For example, if it determines that a user is not getting enough exercise, it generates specific advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, it also provides advice such as "We recommend deep breathing exercises to relax."

[1032] Step 8: Distributing Advice

[1033] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[1034] Step 9: Receive and review advice

[1035] Users receive a notification on their device and can check the advice. By tapping the notification, they can open the app and view detailed advice. For example, they can receive a notification such as "Today you haven't been exercising enough, so aim for 2,000 more steps" or "Try 5 minutes of meditation to relax."

[1036] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[1037] Example 2

[1038] 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."

[1039] The problem that this invention aims to solve is to efficiently and accurately collect a user's biometric information and provide individually optimized health advice based on that data. In particular, it is necessary to generate health advice that takes into account the user's emotional state and support comprehensive health management in daily life. It is also necessary to appropriately handle quality issues such as missing data and outliers, and to achieve high-precision data analysis.

[1040] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a preprocessing means for correcting data errors, complementing missing values, and filtering outliers, a means for recognizing a user's emotions through an emotion engine using the preprocessed data, a means for identifying the user's lifestyle habits by analyzing the preprocessed data and emotion data, a means for generating individual health advice for each user using a generation AI based on the analysis results and emotion data, and a means for transmitting the health advice to the user's terminal and notifying the user. This makes it possible to provide individually optimized health advice with high accuracy based on the user's biometric information and emotion data.

[1041] "User's biometric information" refers to physical data from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned.

[1042] "Monitoring device" refers to a terminal used to constantly monitor and collect a user's biometric information.

[1043] "Server" refers to a computer system for storing, pre-processing, and analyzing data transmitted from monitoring devices.

[1044] "Preprocessing" refers to the process of correcting errors in the collected raw data, filling in missing values, and filtering outliers.

[1045] "Emotion engine" refers to a function that uses biometric and activity data to analyze and recognize a user's emotional state.

[1046] "Generative AI" refers to artificial intelligence that automatically generates optimal health advice for each user based on analysis results and emotional data.

[1047] "Health advice" refers to specific advice aimed at improving lifestyle habits and promoting health, generated based on the user's biometric information and emotional data.

[1048] "Missing value imputation" refers to the process of filling in missing data with other valid data.

[1049] "Outlier filtering" refers to the process of removing values ​​in the data that are deemed to be clearly inaccurate, such as abnormally high or low values.

[1050] "Database" refers to a system within the server for organizing and storing received and pre-processed data.

[1051] "Notification system" refers to a function for sending health advice to a user's terminal and notifying the user.

[1052] This invention is a system for monitoring and collecting a user's biometric information and providing individually optimized health advice to the user. Specifically, the system uses data acquired by a monitoring device, preprocesses and analyzes the data, and provides advice using generative AI.

[1053] Hardware and Software Configuration

[1054] Monitoring Devices:

[1055] Devices (e.g. fitness trackers, smartwatches) contain sensors such as:

[1056] Heart rate sensor

[1057] Acceleration sensor

[1058] Gyroscope

[1059] This allows the system to constantly monitor and collect biometric information such as the user's heart rate, number of steps taken, sleep time, and calories burned.

[1060] server:

[1061] The following hardware and software are used for data storage, preprocessing, and analysis:

[1062] Database servers (e.g. MySQL, MongoDB)

[1063] Data analysis tools (e.g., Scikit-learn, TensorFlow)

[1064] Emotion engine (e.g. Microsoft Azure Emotion API)

[1065] Generative AI models (e.g., OpenAI GPT-4)

[1066] Communication modules (e.g. REST API servers)

[1067] Processing Flow

[1068] First, the device collects the user's biometric information in real time. For example, a heart rate sensor measures the heart rate every second, and an acceleration sensor counts the number of steps. This data is accumulated in local storage at regular intervals (for example, every hour).

[1069] Next, the device transmits the collected data to the server via wireless communication (Bluetooth or Wi-Fi). When the transmitted data is received by the server, it is first stored in a database.

[1070] The server preprocesses the received raw data, which includes error correction, missing value imputation, and outlier filtering. The preprocessed data is then stored in the database again.

[1071] The server then uses an emotion engine to recognize the user's emotions based on the pre-processed data, analyzing the short-term and long-term emotional states to obtain emotion data.

[1072] The server comprehensively analyzes the pre-processed data and emotional data to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc. Based on the results of this analysis, a generative AI model is run to generate personalized health advice for each user.

[1073] The generated health advice is sent to the user's device via the notification system. The user can then check the notification displayed on the device and view the detailed advice in the app.

[1074] Examples and prompts

[1075] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server then preprocesses the data and recognizes their emotional state, determining that the user is experiencing moderate stress.

[1076] At this point, the database contains preprocessed data and emotion data. The server analyzes this data and inputs the following prompt to the generative AI model:

[1077] Generate health advice based on the user's biometric and emotional data. Use the following data:

[1078] Heart rate: 70 bpm

[1079] Daily steps: 8,000

[1080] Stress level: Moderate

[1081] Sleep time: 6 hours

[1082] Based on this prompt, the generative AI model generates health advice such as, "Based on your recent data, your daily exercise volume is appropriate, but your sleep time is somewhat insufficient. Try to get at least seven hours of sleep each night. Also, you appear to be at a moderate level of stress, so try incorporating deep breathing exercises to help you relax."

[1083] As a result, the present invention provides individually optimized health advice based on the user's biometric information and emotional data, and provides comprehensive support for the user's health management.

[1084] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1085] Step 1: Data collection

[1086] Devices (e.g., fitness trackers, smartwatches) use sensors to collect biometric information such as a user's heart rate, number of steps, sleep time, and calories burned in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer counts the number of steps, and the gyroscope detects the user's movements and estimates sleep time.

[1087] Input: The user's actual biometric data

[1088] Output: Measured biological information data (heart rate, steps, sleep time, calories burned)

[1089] Step 2: Sending data

[1090] The device accumulates the collected data in local storage at regular intervals (for example, every hour), and then transmits it to the server via wireless communication (Bluetooth or Wi-Fi). The data is packetized and sent to the server using a secure communication protocol (for example, HTTPS).

[1091] Input: Biometric data stored in local storage

[1092] Output: Biometric data sent to the server

[1093] Step 3: Save your data

[1094] The server receives the data sent from the device, temporarily stores it in memory, and then saves it in a database (e.g., MySQL or MongoDB). The data is assigned a timestamp and user ID and organized appropriately.

[1095] Input: Received biometric data

[1096] Output: Biometric data stored in a database

[1097] Step 4: Preprocessing the data

[1098] The server preprocesses the stored data. This preprocessing includes correcting errors in the data, imputing missing values, and filtering outliers. The preprocessed data is then saved back into the database. Specifically, the raw data is read from the database, and a Python script cleans the data using the Pandas library.

[1099] Input: Biometric data stored in a database

[1100] Output: Preprocessed biometric data

[1101] Step 5: Recognize emotions

[1102] The server analyzes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API) based on the preprocessed data. It sends the input data to the API and obtains the emotion recognition results, which are then stored in a database.

[1103] Input: Preprocessed biometric data

[1104] Output: Emotion data obtained from the emotion engine

[1105] Step 6: Lifestyle analysis

[1106] The server uses data analysis tools (e.g., Scikit-learn, TensorFlow) to comprehensively analyze the preprocessed data and emotion data, thereby identifying the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[1107] Input: Preprocessed biometric and emotion data

[1108] Output: Analyzed lifestyle data

[1109] Step 7: Generate health advice

[1110] The server generates health advice using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results and emotion data. The generative AI model receives specific prompts as input and generates optimal advice.

[1111] Example prompt:

[1112] Generate health advice based on the user's biometric and emotional data. Use the following data:

[1113] Heart rate: 70 bpm

[1114] Daily steps: 8,000

[1115] Stress level: Moderate

[1116] Sleep time: 6 hours

[1117] Input: Analysis results and emotion data

[1118] Output: Generated health advice

[1119] Step 8: Distributing Advice

[1120] The server sends the generated health advice to the user's device using a notification system (e.g., Firebase Cloud Messaging). The user receives a notification displayed on the device and can view detailed advice in the app.

[1121] Input: Generated health advice

[1122] Output: Notification sent to the user's device

[1123] (Application example 2)

[1124] 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."

[1125] Conventional health advice systems provide certain health advice based on a user's biometric information, but because they do not take the user's emotional state into account, it is difficult to provide individual dietary and health advice tailored to the user's actual needs. This also limits the effectiveness of the advice provided, resulting in a low effectiveness in managing the user's health.

[1126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1127] In this invention, the server includes means for identifying the user's biometric information and emotional data, means for generating personalized health and dietary advice using a generation AI based on the analysis results and emotional data, and means for transmitting and notifying the generated health and dietary advice to the user's terminal. This allows for the provision of personalized dietary and health advice based on the user's actual health and emotional state, making it possible to more effectively manage the user's health.

[1128] - "Biometric information" refers to data that indicates the user's physical condition, such as the user's heart rate, number of steps taken, and calories burned.

[1129] A "device" is a device for monitoring a user's biometric information and collecting data.

[1130] "Server" means a device or system that receives collected data and performs storage, pre-processing, analysis, and generative AI.

[1131] "Preprocessing" refers to the process of correcting or removing errors, missing values, and outliers from collected data and converting it into a format suitable for analysis.

[1132] "Analysis" is the process of identifying a user's lifestyle habits and emotions based on preprocessed data.

[1133] "Emotion data" is data relating to the emotional state of the user analyzed from biometric information and activity data.

[1134] "Generative AI" is an artificial intelligence technology that generates individual health and dietary advice for each user based on analysis results and emotional data.

[1135] "Health advice" is specific instructions or suggestions related to a user's exercise, diet, and rest.

[1136] "Sending" is the process of delivering the generated advice from the server to the user's terminal.

[1137] "Notifications" is a feature that notifies users of advice and reminders displayed on the device.

[1138] The present invention is a system that monitors a user's biological information and provides personalized health and dietary advice based on the acquired data. The system consists of a monitoring device, a server, a food delivery application, and a user terminal.

[1139] First, the user wears a monitoring device. This device collects biometric information such as heart rate, number of steps, and calories burned in real time. This data is stored in local storage at regular intervals and sent to the server as appropriate. For example, if a user walks 8,000 steps in a day and their average heart rate is 70 bpm, this data will be collected and sent to the server every hour.

[1140] The server receives the data sent from the device and stores it in a database. The received data is appended with a timestamp and user ID, and the data is organized for each user. Daily exercise data and heart rate data are organized by each user's ID and stored in the database.

[1141] Data preprocessing involves error correction, missing value completion, and outlier filtering. For example, if heart rate data is missing, it is completed based on valid data before and after, and abnormally high heart rate data is excluded. The preprocessed data is then resaved.

[1142] The server then uses the preprocessed data to recognize the user's emotions using an emotion engine. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it can estimate the user's likelihood of feeling stressed based on fluctuations in their heart rate and activity patterns.

[1143] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[1144] Based on the analysis results and emotion data, the generative AI generates optimal health and dietary advice for each user. The generative AI model is built using TensorFlow and inputs the analysis results and emotion data as prompts. The generated advice includes specific exercise, diet, and rest recommendations.

[1145] For example, if a user is judged to be lacking in exercise, the system will generate advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, the system will provide advice such as "We recommend deep breathing exercises to help you relax." Furthermore, a system built into a food delivery application will recommend menus containing ingredients that have a relaxing effect to users who are feeling stressed.

[1146] The generated health and diet advice is sent to the user's device and delivered to them through a notification system, where they can tap on the notification to view the detailed advice.

[1147] The following are examples of specific prompt sentences:

[1148] Prompt Sentence Examples

[1149] Input data:

[1150] Heart rate: 72 bpm

[1151] Steps: 5,000 steps

[1152] Calories burned: 350 kcal

[1153] Emotional state: Stress level 0.7

[1154] Generation advice:

[1155] Your heart rate is in the normal range, but you may not be getting enough exercise. Your stress levels are high, so we recommend a dinner that includes foods that have a relaxing effect (e.g., bananas and nuts). You should also set a goal to walk a little more each day. For example, aim for 7,000 steps tomorrow.

[1156] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1157] Step 1:

[1158] The monitoring device collects the user's biometric information. The input is data such as heart rate, steps, and calories burned. The device monitors this data in real time and stores it in local storage. The output is the collected biometric data.

[1159] Step 2:

[1160] The monitoring device transmits biometric data to the server at regular intervals. The input is the biometric data stored in the local storage. The data is transmitted from the device to the server. The output is the biometric data transmitted to the server.

[1161] Step 3:

[1162] The server receives the transmitted biometric data and stores it in a database. The input is the biometric data sent from the device. The data is stored in the database and organized by timestamp and user ID. The output is organized and stored biometric data.

[1163] Step 4:

[1164] The server preprocesses the received data. Preprocessing includes missing value imputation, outlier filtering, and error correction. The input is biometric data stored in a database. For example, if heart rate data is missing, it is imputed based on previous and subsequent data, and abnormally high heart rate data is excluded. The output is the preprocessed biometric data.

[1165] Step 5:

[1166] The server analyzes the user's emotions using an emotion engine based on the preprocessed data. The input is preprocessed biometric data. The emotion engine estimates the user's stress level and emotional state from fluctuations in heart rate and activity patterns. The output is analyzed emotion data.

[1167] Step 6:

[1168] The server comprehensively analyzes the preprocessed data and emotional data. The input is the preprocessed biometric data and emotional data. The data analysis identifies the user's lifestyle habits, exercise patterns, stress level, etc. The output is the analysis results.

[1169] Step 7:

[1170] The server uses generative AI to generate personalized health and diet advice based on the analysis results and emotional data. The input is the analysis results and emotional data. The generative AI model (e.g., TensorFlow) uses the analysis results and emotional data to generate advice. For example, advice such as "30 minutes of walking daily is recommended" may be generated for lack of exercise, or "a dinner containing ingredients with a relaxing effect is recommended" for high stress levels. The output is the generated health and diet advice.

[1171] Step 8:

[1172] The server sends the generated health and diet advice to the user's device and notifies them. The input is the generated health and diet advice. The advice is sent to the device and delivered to the user through the notification system. When the user receives the notification, they can tap it to view the detailed advice. The output is the advice and notification displayed on the user's device.

[1173] This process allows users to receive personalized health and dietary advice based on their biometrics and emotional state.

[1174] 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.

[1175] 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.

[1176] 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.

[1177] [Fourth embodiment]

[1178] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1179] 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.

[1180] 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).

[1181] 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.

[1182] 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.

[1183] 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).

[1184] 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.

[1185] 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.

[1186] 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.

[1187] 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.

[1188] 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.

[1189] 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.

[1190] 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."

[1191] The present invention relates to a monitoring device that monitors a user's biometric information, and a system that transmits the collected data to a server, preprocesses and analyzes it, and uses generative AI to provide personalized health advice.

[1192] Program processing

[1193] Data collection

[1194] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and also transmits this data to the server at the timing of data transfer.

[1195] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[1196] Data storage

[1197] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[1198] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[1199] Data Preprocessing

[1200] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[1201] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[1202] Lifestyle analysis

[1203] The server analyzes the pre-processed data, which identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[1204] For example, the system calculates a user's average number of steps and sleep time from a week's data and evaluates their exercise habits and sleep quality.

[1205] Generating health advice

[1206] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results as input and creates optimal advice for each user.

[1207] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day."

[1208] Advice Delivery

[1209] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[1210] The user checks the advice in the notification sent to the device. For example, they may receive a notification saying, "You haven't been exercising enough today, so aim for another 2,000 steps." This system allows users to know the specific steps they need to take to improve their lifestyle habits.

[1211] In this way, the present invention is a system that supports a user's own health management by providing individually optimized health advice based on the user's biological information.

[1212] The processing flow will be explained below.

[1213] Step 1: Data collection

[1214] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[1215] Step 2: Data Transfer

[1216] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[1217] Step 3: Receiving and storing data

[1218] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[1219] Step 4: Preprocessing the data

[1220] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[1221] Step 5: Lifestyle analysis

[1222] The server uses the preprocessed data to analyze the user's lifestyle. The analysis algorithm receives the data as input and derives the user's exercise patterns, average heart rate, sleep patterns, etc. For example, daily step count data can be compiled to evaluate exercise habits.

[1223] Step 6: Generate health advice

[1224] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis data as input and creates optimal advice for each user. For example, based on data from the past week, it generates specific advice such as "We recommend walking 30 minutes every day."

[1225] Step 7: Distributing Advice

[1226] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[1227] Step 8: Receive and review advice

[1228] The user receives a notification on their device and can confirm the advice. If the user taps the notification, they can open the app and view detailed advice. For example, they can confirm and follow advice such as "You haven't been exercising enough today, so aim for another 2,000 steps."

[1229] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[1230] Example 1

[1231] 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."

[1232] In modern society, many people recognize the importance of health management, but finding specific ways to improve their lifestyle habits is difficult. Furthermore, providing optimal health advice to individual users requires accurate preprocessing and analysis of collected biometric data. However, there is a lack of efficient means for processing biometric data that contains outliers and missing values. This makes it difficult to provide specific, individually optimized health advice.

[1233] 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.

[1234] In this invention, the server includes means for collecting data from a device that monitors a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating individual health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, and means for the monitoring device to collect and transmit data at regular intervals. This makes it possible to accurately collect the user's biological information, perform pre-processing, and analyze the lifestyle habits, and then provide the user with individually optimized health advice.

[1235] "User's biological information" is data that indicates the health condition of each individual user in their daily life, such as heart rate, number of steps, sleep time, and calories burned.

[1236] A "monitoring device" is a device used to collect biometric information from a user, and includes wearable devices and smartphones.

[1237] A "server" is a computer system that receives, stores, pre-processes, and analyzes data sent from a terminal.

[1238] "Storing data" refers to recording information received from a terminal in a specific storage device or database.

[1239] "Preprocessing" refers to processing performed on collected biometric information data, and includes error correction, missing value completion, and outlier filtering.

[1240] "Data analysis" refers to the use of pre-processed data to perform calculations and evaluations to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[1241] "Generative AI" refers to an AI model that uses artificial intelligence technology to generate personalized health advice for each user based on specific input data.

[1242] "Health advice" refers to specific instructions or recommendations for improving the user's health, derived from the analysis results by the generative AI.

[1243] The "notification system" is a system for transmitting the generated health advice to the user's terminal and notifying the user.

[1244] An "interval" is a set time interval or frequency at which data is collected or transmitted.

[1245] The present invention is a system for monitoring a user's biological information, and a specific implementation method will be described here. Specific names of the hardware and software used and examples of prompt sentences will also be clearly stated.

[1246] This system includes a monitoring device (terminal), a server for data processing and storage, and a generative AI model for providing advice to users. The user wears a monitoring device that collects biometric information from daily life, such as heart rate, number of steps, sleep time, and calories burned. This device can be a wearable device or a smartphone, for example.

[1247] Program processing

[1248] Data collection

[1249] The device continuously monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. This data is stored in local storage at regular intervals. For example, data is collected every second and sent to the server every hour.

[1250] Data storage

[1251] The server receives the data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery. Each piece of data is assigned a timestamp and a user ID, which allows the data to be organized for each user.

[1252] Data Preprocessing

[1253] The server performs error correction, missing value completion, and outlier filtering on the received data, often using scripting languages ​​such as Python or R. Once preprocessing is complete, the data is stored back in the database.

[1254] Lifestyle analysis

[1255] The server analyzes the preprocessed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns using distributed processing frameworks such as Spark and Hadoop.

[1256] Generating health advice

[1257] The server generates personalized health advice using a generative AI model (e.g., GPT-4) based on the analysis results. It also generates prompts to input the analysis results and inputs them into the generative AI.

[1258] Example prompt sentence:

[1259] User ID: 12345

[1260] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[1261] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[1262] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[1263] Use this data to generate personalized health improvement advice for users.

[1264] Advice Delivery

[1265] The server sends the generated health advice to the user's device. The advice is notified to the user using a notification system such as Firebase Cloud Messaging or Amazon SNS. The user can check the notification received on their device and improve their lifestyle based on the advice.

[1266] Specific examples

[1267] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server stores the data using RDS and preprocesses it with a Python script. The resulting prompt is then fed to the generative AI model, which then generates advice for the user, such as "We recommend walking 30 minutes daily."

[1268] In this way, this system accurately collects the user's biometric information, performs preprocessing, analyzes lifestyle habits, and provides individually optimized health advice to the user, thereby supporting the user's health management.

[1269] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1270] Step 1:

[1271] Data collection

[1272] The device continuously monitors the user's biometric information, such as heart rate, steps taken, sleep time, and calories burned, and stores the data in local storage at regular intervals (e.g., every second).

[1273] Specific operation: Acquires data from the heart rate sensor and accelerometer and stores it in local storage.

[1274] Input: Real-time biometric data of the user

[1275] Output: Biometric data stored in local storage

[1276] Step 2:

[1277] Data transmission

[1278] After a certain period of time has elapsed (for example, every hour), the terminal transmits the biometric information data accumulated in the local storage to the server.

[1279] Specific operation: Data is divided into packets and sent to a server over the Internet.

[1280] Input: Biometric data stored in local storage

[1281] Output: Biometric data sent to the server

[1282] Step 3:

[1283] Data storage

[1284] The server receives the biometric data sent from the device and stores it in a database such as Amazon Web Services' RDS or Google Cloud's BigQuery.

[1285] Specific operation: Receive data, assign a timestamp and user ID to each data, and save it in the database.

[1286] Input: Biometric data sent from the device

[1287] Output: Aligned biometric data stored in a database

[1288] Step 4:

[1289] Data Preprocessing

[1290] The server performs error correction, missing value completion, and outlier filtering on the received data using Python and R scripts.

[1291] Specific operations: Detect and remove outliers, impute missing values, and perform noise reduction.

[1292] Input: Biometric data stored in a database

[1293] Output: Clean biometric data after preprocessing

[1294] Step 5:

[1295] Lifestyle analysis

[1296] The server analyzes the pre-processed data to identify the user's lifestyle habits, exercise patterns, average heart rate, and sleep patterns, using distributed processing frameworks such as Spark and Hadoop.

[1297] Specific operation: Aggregate one week's worth of data and calculate average values ​​and trends.

[1298] Input: Clean, pre-processed biometric data

[1299] Output: Analysis results (user's lifestyle data)

[1300] Step 6:

[1301] Generating health advice

[1302] The server uses a generative AI model (e.g., GPT-4) to generate personalized health advice for each user based on the analysis results.

[1303] Specific operation: The analysis results are input into the generation AI as a prompt sentence, and a response is obtained from the AI.

[1304] Input: Analysis results (user's lifestyle data)

[1305] Output: Generated personalized health advice

[1306] Step 7:

[1307] Advice Delivery

[1308] The server sends the generated health advice to the user's device using a notification system such as Firebase Cloud Messaging or Amazon SNS.

[1309] Specific operation: A notification message is constructed and sent to the device. The user receives it and uses it to improve their lifestyle habits.

[1310] Input: Generated personalized health advice

[1311] Output: Health advice notification delivered to the user's device

[1312] Example prompt sentence:

[1313] User ID: 12345

[1314] Number of steps for each day: [7500, 8000, 5600, 10000, 8500, 6200, 9000]

[1315] Heart rate for each day: [65, 70, 68, 75, 72, 65, 71]

[1316] Sleep hours each day: [7.5, 8, 6, 7, 7.5, 6.5, 7]

[1317] Use this data to generate personalized health improvement advice for users.

[1318]

[1319] (Application example 1)

[1320] 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."

[1321] Conventional health management systems only collect users' biometric information and provide health advice based on the analysis results. However, they do not consider recommending specific products based on the user's health status or providing related discounts or campaign information. As a result, there is a lack of means to encourage users to make practical and economical improvements. This problem remains unsolved due to a lack of incentives to motivate users and encourage behavioral change.

[1322] 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.

[1323] In this invention, the server includes means for collecting data from devices that monitor a user's biological information, means for transmitting the data to the server, means for storing and pre-processing the data in the server, means for analyzing the pre-processed data to identify the user's lifestyle habits, means for generating personalized health advice for each user using a generation AI based on the analysis results, means for transmitting the health advice to the user's terminal and notifying the user, means for recommending products based on the generated health advice according to the user's health condition, and means for generating discount and campaign information based on the health condition. This makes it easier for users to purchase specific products and services based on their health condition, thereby increasing their motivation to improve their health.

[1324] "User's biological information" is data that indicates the user's health condition, such as heart rate, number of steps, sleep time, and calories burned.

[1325] A "monitoring device" is a device for collecting biometric information from a user. Examples include smartwatches and fitness trackers.

[1326] A "server" is a computer system for storing, preprocessing, and analyzing collected biometric information.

[1327] "Storage" means recording collected data for future reference.

[1328] "Preprocessing" refers to the process of correcting errors in biometric information data, complementing missing values, and filtering outliers.

[1329] "Analysis" refers to identifying a user's lifestyle and health status using preprocessed data.

[1330] "Generative AI" is a technology that uses artificial intelligence to generate useful information and advice from specific input data.

[1331] "Health advice" refers to specific instructions or recommendations based on the analysis results aimed at improving the user's lifestyle habits.

[1332] A "terminal" is a device through which a user receives health advice. Examples include smartphones and tablets.

[1333] "Product recommendation" refers to recommending specific products to encourage purchase based on the user's health status.

[1334] "Discount and campaign information" is information about special offers and price reductions that are intended to increase the user's purchasing motivation.

[1335] This invention is a system that collects data from devices that monitor a user's biometric information, transmits the data to a server, stores it, preprocesses it, and analyzes it. Furthermore, it uses generative AI to provide personalized health advice, and generates and provides product recommendations and discount information based on the user's health status, thereby supporting the user's health management and purchasing behavior.

[1336] System Configuration

[1337] The system consists of the following main components:

[1338] 1. Monitoring devices: Devices such as smartwatches and fitness trackers collect biometric information such as a user's heart rate, steps taken, sleep time, and calories burned.

[1339] 2. Server:

[1340] Data storage: The biometric data sent from the monitoring device is stored in a database such as Amazon RDS.

[1341] Preprocessing: Use AWS Lambda to perform error correction, missing value imputation, and outlier filtering.

[1342] Data analysis: Use Amazon SageMaker to analyze data and identify user habits and health conditions.

[1343] Generative AI: Using generative AI models such as GPT-4, personalized health advice is generated based on the analysis results.

[1344] 3. Mobile Applications: Applications developed on iOS and Android platforms (e.g., Xcode, Android Studio) inform users of health advice, product recommendations, and discount information.

[1345] Program processing

[1346] 1. Data collection and transmission: The monitoring device collects the user's biometric information in real time and transmits the data to the server at regular intervals. This data is marked with a timestamp and user ID.

[1347] 2. Data storage and preprocessing: The server stores the data in a database and then uses AWS Lambda to preprocess the data, specifically imputing missing data and filtering outliers.

[1348] 3. Data analysis and generation: Using Amazon SageMaker, the preprocessed data is analyzed to identify the user's lifestyle habits and health status. A generative AI (e.g., GPT-4) generates personalized health advice based on the analysis results.

[1349] 4. Advice Delivery: The generated health advice, product recommendations, and discount information are sent to the user via the mobile application. For example, specific advice such as "You haven't been exercising enough today, so aim for 2,000 more steps" is provided.

[1350] 5. Product recommendations based on health status: Generative AI recommends appropriate products (e.g., health foods and fitness products) based on the user's health status.

[1351] 6. Discount and campaign information: Generate discount codes and campaign information linked to the user's health status and provide it to the user.

[1352] Examples of concrete examples and prompts

[1353] For example, if the user's biometric information is "heart rate: 70 bpm, number of steps: 8,000, sleep time: 7 hours, calories burned: 2,500 kcal," the following prompt sentence is input to the generation AI:

[1354] Based on the user's health data (heart rate: 70 bpm, number of steps: 8000 steps, sleep time: 7 hours, calories burned: 2500 kcal), recommend healthy foods and exercise equipment, and generate discount and campaign information applicable to their purchase.

[1355] This will enable the realization of a system that provides users with specific advice and recommended products tailored to their health, as well as economic incentives, leading to the maintenance of their health and behavioral changes.

[1356] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1357] Step 1:

[1358] The monitoring device (terminal) collects biometric information such as the user's heart rate, number of steps, sleep time, and calories burned in real time. This data is temporarily stored in the terminal's local storage at regular intervals (e.g., every hour). The terminal then transmits the data to a server. The input is the user's biometric information, and the output is a data file sent to the server.

[1359] Step 2:

[1360] The server receives the biometric data sent from the device and records it in a database. The data is assigned a timestamp and user ID and is organized by user. The input is the biometric data sent from the device, and the output is the data stored in the database.

[1361] Step 3:

[1362] The server preprocesses the incoming data. It uses AWS Lambda to impute missing data and filter outliers. This processing improves the accuracy of the data. The input is the stored biometric data, and the output is the preprocessed data.

[1363] Step 4:

[1364] The server analyzes the preprocessed data. Amazon SageMaker is used to identify the user's lifestyle and health status (for example, average heart rate, total number of steps, sleep patterns, etc.). The input is the preprocessed data, and the output is the analysis results. Specifically, the server analyzes the data and extracts trends.

[1365] Step 5:

[1366] The generative AI (for example, GPT-4) generates individual health advice based on the analysis results. Specific advice is generated based on the analysis results, which are input as a prompt. The input is the analysis results, and the output is the generated health advice. Specifically, the prompt is input into the generative AI model, and the result is received as text.

[1367] Step 6:

[1368] The server sends the generated health advice to the user's device. The user's device receives a notification through the application and can check the advice. The input is the generated health advice, and the output is the notification to the user's device. Specifically, the server pushes the advice through the notification system.

[1369] Step 7:

[1370] The server recommends suitable products to the user based on the generated health advice. These recommendations include products according to the user's health condition (e.g., health foods and fitness products). The input is the generated health advice, and the output is a list of recommended products. Specifically, the server selects suitable products from a database and creates a list.

[1371] Step 8:

[1372] The server generates discount and campaign information based on the user's health status. It uses a generative AI model to create optimal discount codes and campaign information. The input is the user's health information and analysis results, and the output is discount and campaign information. Specifically, the server works in conjunction with the sales promotion system to generate applicable promotions.

[1373] Step 9:

[1374] The server sends the generated discount and campaign information to the user's terminal. The user's terminal can receive and use this information through an application. The input is the generated discount and campaign information, and the output is a notification to the user's terminal. In concrete terms, the server distributes the information via the campaign management system.

[1375] 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.

[1376] This invention combines a monitoring device that monitors a user's biometric information, a system that transmits the data to a server, and provides individually optimized health advice using preprocessing, analysis, and generation AI, with an emotion engine that recognizes the user's emotions.

[1377] Program processing

[1378] Data collection

[1379] The terminal (monitoring device) constantly monitors and collects biometric information from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned. The device stores this data in local storage at regular intervals and then transmits it to the server at the data transfer timing.

[1380] As a concrete example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device will collect this data and send it to the server every hour.

[1381] Data storage

[1382] The server receives the data sent from the device and stores it in a database. The received data is accompanied by a timestamp and user ID, and the data is organized by user.

[1383] For example, daily exercise data and heart rate data are organized by each user's ID and stored in a database.

[1384] Data Preprocessing

[1385] The server preprocesses the received data, including correcting errors in the data, imputing missing values, and filtering outliers. The resulting preprocessed data is then stored back in the database.

[1386] For example, if heart rate data is missing, it is supplemented based on valid data before and after. Also, abnormally high heart rate data is excluded.

[1387] Emotion recognition

[1388] The server recognizes the user's emotions based on the pre-processed data using an emotion engine, which analyzes the user's short-term and long-term emotional state from their biometric and activity data.

[1389] For example, the possibility that the user is feeling stressed can be estimated based on fluctuations in heart rate and activity patterns.

[1390] Lifestyle analysis

[1391] The server then comprehensively analyzes the pre-processed data, including the results of the emotion engine analysis, to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information.

[1392] For example, the system can calculate a user's average number of steps and sleep time from a week's data to evaluate their exercise habits and sleep quality, and identify stress levels and emotional fluctuation patterns from emotional data.

[1393] Generating health advice

[1394] The server generates personalized health advice based on the analysis results using a generation AI, which receives the analysis results and emotional data as input and creates optimal advice for each user.

[1395] For example, if it determines that you are not getting enough exercise, it will generate specific advice such as "We recommend walking 30 minutes every day." If it detects signs of stress, it will provide advice such as "We recommend deep breathing exercises to help you relax."

[1396] Advice Delivery

[1397] The server sends the generated health advice to the user's terminal and delivers it to the user through a notification system.

[1398] Users can view the advice by receiving a notification on their device, or by tapping the notification, they can open the app and view the detailed advice.

[1399] For example, you can receive notifications such as "You haven't been exercising enough today, so aim for 2,000 more steps" or "Try meditating for 5 minutes to relax."

[1400] In this way, the present invention provides multifaceted support for the user's health management by providing individually optimized health advice based on the user's biometric information and emotional data.

[1401] The processing flow will be explained below.

[1402] Step 1: Data collection

[1403] The device (monitoring device) monitors the user's biometric information in real time, collecting data such as heart rate, number of steps, sleep time, and calories burned. For example, the device counts steps when the user starts walking, and the heart rate sensor continuously records heart rate data. The device temporarily stores this data in local storage.

[1404] Step 2: Data Transfer

[1405] The device sends the collected data to the server at regular intervals (e.g., every hour). The device's communication module is activated and starts communication with the server. The transferred data includes a timestamp and user ID.

[1406] Step 3: Receiving and storing data

[1407] The server receives the data sent from the device and stores it in a database, which organizes the data based on user ID and timestamp for easy access later.

[1408] Step 4: Preprocessing the data

[1409] The server preprocesses the received data. This includes filling in missing values ​​and filtering outliers. For example, if there are missing heart rate data, the server fills in the appropriate value based on the previous and following data. It also filters out abnormally high heart rate data.

[1410] Step 5: Recognize emotions

[1411] The server uses an emotion engine to recognize the user's emotions based on the preprocessed data. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it estimates the possibility that the user is feeling stressed based on fluctuations in their heart rate and activity patterns.

[1412] Step 6: Lifestyle analysis

[1413] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[1414] Step 7: Generate health advice

[1415] The server uses a generation AI to generate personalized health advice based on the analysis results. The generation AI receives the analysis results and emotional data as input and creates optimal advice for each user. For example, if it determines that a user is not getting enough exercise, it generates specific advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, it also provides advice such as "We recommend deep breathing exercises to relax."

[1416] Step 8: Distributing Advice

[1417] The server sends the generated health advice to the user's device, and a notification system is used to set up the advice so that it is delivered to the user in real time.

[1418] Step 9: Receive and review advice

[1419] Users receive a notification on their device and can check the advice. By tapping the notification, they can open the app and view detailed advice. For example, they can receive a notification such as "Today you haven't been exercising enough, so aim for 2,000 more steps" or "Try 5 minutes of meditation to relax."

[1420] In this way, the present invention assists users in managing their health by collecting and analyzing their data and providing personalized advice based on the results.

[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 robot 414 will be referred to as a "terminal."

[1423] The problem that this invention aims to solve is to efficiently and accurately collect a user's biometric information and provide individually optimized health advice based on that data. In particular, it is necessary to generate health advice that takes into account the user's emotional state and support comprehensive health management in daily life. It is also necessary to appropriately handle quality issues such as missing data and outliers, and to achieve high-precision data analysis.

[1424] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes a preprocessing means for correcting data errors, complementing missing values, and filtering outliers, a means for recognizing a user's emotions through an emotion engine using the preprocessed data, a means for identifying the user's lifestyle habits by analyzing the preprocessed data and emotion data, a means for generating individual health advice for each user using a generation AI based on the analysis results and emotion data, and a means for transmitting the health advice to the user's terminal and notifying the user. This makes it possible to provide individually optimized health advice with high accuracy based on the user's biometric information and emotion data.

[1425] "User's biometric information" refers to physical data from the user's daily life, such as heart rate, number of steps, sleep time, and calories burned.

[1426] "Monitoring device" refers to a terminal used to constantly monitor and collect a user's biometric information.

[1427] "Server" refers to a computer system for storing, pre-processing, and analyzing data transmitted from monitoring devices.

[1428] "Preprocessing" refers to the process of correcting errors in the collected raw data, filling in missing values, and filtering outliers.

[1429] "Emotion engine" refers to a function that uses biometric and activity data to analyze and recognize a user's emotional state.

[1430] "Generative AI" refers to artificial intelligence that automatically generates optimal health advice for each user based on analysis results and emotional data.

[1431] "Health advice" refers to specific advice aimed at improving lifestyle habits and promoting health, generated based on the user's biometric information and emotional data.

[1432] "Missing value imputation" refers to the process of filling in missing data with other valid data.

[1433] "Outlier filtering" refers to the process of removing values ​​in the data that are deemed to be clearly inaccurate, such as abnormally high or low values.

[1434] "Database" refers to a system within the server for organizing and storing received and pre-processed data.

[1435] "Notification system" refers to a function for sending health advice to a user's terminal and notifying the user.

[1436] This invention is a system for monitoring and collecting a user's biometric information and providing individually optimized health advice to the user. Specifically, the system uses data acquired by a monitoring device, preprocesses and analyzes the data, and provides advice using generative AI.

[1437] Hardware and Software Configuration

[1438] Monitoring Devices:

[1439] Devices (e.g. fitness trackers, smartwatches) contain sensors such as:

[1440] Heart rate sensor

[1441] Acceleration sensor

[1442] Gyroscope

[1443] This allows the system to constantly monitor and collect biometric information such as the user's heart rate, number of steps taken, sleep time, and calories burned.

[1444] server:

[1445] The following hardware and software are used for data storage, preprocessing, and analysis:

[1446] Database servers (e.g. MySQL, MongoDB)

[1447] Data analysis tools (e.g., Scikit-learn, TensorFlow)

[1448] Emotion engine (e.g. Microsoft Azure Emotion API)

[1449] Generative AI models (e.g., OpenAI GPT-4)

[1450] Communication modules (e.g. REST API servers)

[1451] Processing Flow

[1452] First, the device collects the user's biometric information in real time. For example, a heart rate sensor measures the heart rate every second, and an acceleration sensor counts the number of steps. This data is accumulated in local storage at regular intervals (for example, every hour).

[1453] Next, the device transmits the collected data to the server via wireless communication (Bluetooth or Wi-Fi). When the transmitted data is received by the server, it is first stored in a database.

[1454] The server preprocesses the received raw data, which includes error correction, missing value imputation, and outlier filtering. The preprocessed data is then stored in the database again.

[1455] The server then uses an emotion engine to recognize the user's emotions based on the pre-processed data, analyzing the short-term and long-term emotional states to obtain emotion data.

[1456] The server comprehensively analyzes the pre-processed data and emotional data to identify the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc. Based on the results of this analysis, a generative AI model is run to generate personalized health advice for each user.

[1457] The generated health advice is sent to the user's device via the notification system. The user can then check the notification displayed on the device and view the detailed advice in the app.

[1458] Examples and prompts

[1459] For example, if a user takes 8,000 steps in a day and their heart rate averages 70 bpm, the monitoring device collects this data and sends it to the server every hour. The server then preprocesses the data and recognizes their emotional state, determining that the user is experiencing moderate stress.

[1460] At this point, the database contains preprocessed data and emotion data. The server analyzes this data and inputs the following prompt to the generative AI model:

[1461] Generate health advice based on the user's biometric and emotional data. Use the following data:

[1462] Heart rate: 70 bpm

[1463] Daily steps: 8,000

[1464] Stress level: Moderate

[1465] Sleep time: 6 hours

[1466] Based on this prompt, the generative AI model generates health advice such as, "Based on your recent data, your daily exercise volume is appropriate, but your sleep time is somewhat insufficient. Try to get at least seven hours of sleep each night. Also, you appear to be at a moderate level of stress, so try incorporating deep breathing exercises to help you relax."

[1467] As a result, the present invention provides individually optimized health advice based on the user's biometric information and emotional data, and provides comprehensive support for the user's health management.

[1468] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1469] Step 1: Data collection

[1470] Devices (e.g., fitness trackers, smartwatches) use sensors to collect biometric information such as a user's heart rate, number of steps, sleep time, and calories burned in real time. Specifically, the heart rate sensor measures the heart rate every second, the accelerometer counts the number of steps, and the gyroscope detects the user's movements and estimates sleep time.

[1471] Input: The user's actual biometric data

[1472] Output: Measured biological information data (heart rate, steps, sleep time, calories burned)

[1473] Step 2: Sending data

[1474] The device accumulates the collected data in local storage at regular intervals (for example, every hour), and then transmits it to the server via wireless communication (Bluetooth or Wi-Fi). The data is packetized and sent to the server using a secure communication protocol (for example, HTTPS).

[1475] Input: Biometric data stored in local storage

[1476] Output: Biometric data sent to the server

[1477] Step 3: Save your data

[1478] The server receives the data sent from the device, temporarily stores it in memory, and then saves it in a database (e.g., MySQL or MongoDB). The data is assigned a timestamp and user ID and organized appropriately.

[1479] Input: Received biometric data

[1480] Output: Biometric data stored in a database

[1481] Step 4: Preprocessing the data

[1482] The server preprocesses the stored data. This preprocessing includes correcting errors in the data, imputing missing values, and filtering outliers. The preprocessed data is then saved back into the database. Specifically, the raw data is read from the database, and a Python script cleans the data using the Pandas library.

[1483] Input: Biometric data stored in a database

[1484] Output: Preprocessed biometric data

[1485] Step 5: Recognize emotions

[1486] The server analyzes the user's emotions using an emotion engine (e.g., Microsoft Azure Emotion API) based on the preprocessed data. It sends the input data to the API and obtains the emotion recognition results, which are then stored in a database.

[1487] Input: Preprocessed biometric data

[1488] Output: Emotion data obtained from the emotion engine

[1489] Step 6: Lifestyle analysis

[1490] The server uses data analysis tools (e.g., Scikit-learn, TensorFlow) to comprehensively analyze the preprocessed data and emotion data, thereby identifying the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, etc.

[1491] Input: Preprocessed biometric and emotion data

[1492] Output: Analyzed lifestyle data

[1493] Step 7: Generate health advice

[1494] The server generates health advice using a generative AI model (e.g., OpenAI GPT-4) based on the analysis results and emotion data. The generative AI model receives specific prompts as input and generates optimal advice.

[1495] Example prompt:

[1496] Generate health advice based on the user's biometric and emotional data. Use the following data:

[1497] Heart rate: 70 bpm

[1498] Daily steps: 8,000

[1499] Stress level: Moderate

[1500] Sleep time: 6 hours

[1501] Input: Analysis results and emotion data

[1502] Output: Generated health advice

[1503] Step 8: Distributing Advice

[1504] The server sends the generated health advice to the user's device using a notification system (e.g., Firebase Cloud Messaging). The user receives a notification displayed on the device and can view detailed advice in the app.

[1505] Input: Generated health advice

[1506] Output: Notification sent to the user's device

[1507] (Application example 2)

[1508] 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."

[1509] Conventional health advice systems provide certain health advice based on a user's biometric information, but because they do not take the user's emotional state into account, it is difficult to provide individual dietary and health advice tailored to the user's actual needs. This also limits the effectiveness of the advice provided, resulting in a low effectiveness in managing the user's health.

[1510] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1511] In this invention, the server includes means for identifying the user's biometric information and emotional data, means for generating personalized health and dietary advice using a generation AI based on the analysis results and emotional data, and means for transmitting and notifying the generated health and dietary advice to the user's terminal. This allows for the provision of personalized dietary and health advice based on the user's actual health and emotional state, making it possible to more effectively manage the user's health.

[1512] - "Biometric information" refers to data that indicates the user's physical condition, such as the user's heart rate, number of steps taken, and calories burned.

[1513] A "device" is a device for monitoring a user's biometric information and collecting data.

[1514] "Server" means a device or system that receives collected data and performs storage, pre-processing, analysis, and generative AI.

[1515] "Preprocessing" refers to the process of correcting or removing errors, missing values, and outliers from collected data and converting it into a format suitable for analysis.

[1516] "Analysis" is the process of identifying a user's lifestyle habits and emotions based on preprocessed data.

[1517] "Emotion data" is data relating to the emotional state of the user analyzed from biometric information and activity data.

[1518] "Generative AI" is an artificial intelligence technology that generates individual health and dietary advice for each user based on analysis results and emotional data.

[1519] "Health advice" is specific instructions or suggestions related to a user's exercise, diet, and rest.

[1520] "Sending" is the process of delivering the generated advice from the server to the user's terminal.

[1521] "Notifications" is a feature that notifies users of advice and reminders displayed on the device.

[1522] The present invention is a system that monitors a user's biological information and provides personalized health and dietary advice based on the acquired data. The system consists of a monitoring device, a server, a food delivery application, and a user terminal.

[1523] First, the user wears a monitoring device. This device collects biometric information such as heart rate, number of steps, and calories burned in real time. This data is stored in local storage at regular intervals and sent to the server as appropriate. For example, if a user walks 8,000 steps in a day and their average heart rate is 70 bpm, this data will be collected and sent to the server every hour.

[1524] The server receives the data sent from the device and stores it in a database. The received data is appended with a timestamp and user ID, and the data is organized for each user. Daily exercise data and heart rate data are organized by each user's ID and stored in the database.

[1525] Data preprocessing involves error correction, missing value completion, and outlier filtering. For example, if heart rate data is missing, it is completed based on valid data before and after, and abnormally high heart rate data is excluded. The preprocessed data is then resaved.

[1526] The server then uses the preprocessed data to recognize the user's emotions using an emotion engine. The emotion engine analyzes the user's short-term and long-term emotional state from their biometric and activity data. For example, it can estimate the user's likelihood of feeling stressed based on fluctuations in their heart rate and activity patterns.

[1527] The server comprehensively analyzes the preprocessed data, including the results of the emotion engine analysis. The data analysis identifies the user's lifestyle habits, exercise patterns, average heart rate, sleep patterns, and other information. For example, the server calculates the user's average number of steps and sleep time from a week's worth of data, and evaluates their exercise habits and sleep quality. It also identifies stress levels and patterns of emotional fluctuations from the emotion data.

[1528] Based on the analysis results and emotion data, the generative AI generates optimal health and dietary advice for each user. The generative AI model is built using TensorFlow and inputs the analysis results and emotion data as prompts. The generated advice includes specific exercise, diet, and rest recommendations.

[1529] For example, if a user is judged to be lacking in exercise, the system will generate advice such as "We recommend walking 30 minutes every day." If signs of stress are detected, the system will provide advice such as "We recommend deep breathing exercises to help you relax." Furthermore, a system built into a food delivery application will recommend menus containing ingredients that have a relaxing effect to users who are feeling stressed.

[1530] The generated health and diet advice is sent to the user's device and delivered to them through a notification system, where they can tap on the notification to view the detailed advice.

[1531] The following are examples of specific prompt sentences:

[1532] Prompt Sentence Examples

[1533] Input data:

[1534] Heart rate: 72 bpm

[1535] Steps: 5,000 steps

[1536] Calories burned: 350 kcal

[1537] Emotional state: Stress level 0.7

[1538] Generation advice:

[1539] Your heart rate is in the normal range, but you may not be getting enough exercise. Your stress levels are high, so we recommend a dinner that includes foods that have a relaxing effect (e.g., bananas and nuts). You should also set a goal to walk a little more each day. For example, aim for 7,000 steps tomorrow.

[1540] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1541] Step 1:

[1542] The monitoring device collects the user's biometric information. The input is data such as heart rate, steps, and calories burned. The device monitors this data in real time and stores it in local storage. The output is the collected biometric data.

[1543] Step 2:

[1544] The monitoring device transmits biometric data to the server at regular intervals. The input is the biometric data stored in the local storage. The data is transmitted from the device to the server. The output is the biometric data transmitted to the server.

[1545] Step 3:

[1546] The server receives the transmitted biometric data and stores it in a database. The input is the biometric data sent from the device. The data is stored in the database and organized by timestamp and user ID. The output is organized and stored biometric data.

[1547] Step 4:

[1548] The server preprocesses the received data. Preprocessing includes missing value imputation, outlier filtering, and error correction. The input is biometric data stored in a database. For example, if heart rate data is missing, it is imputed based on previous and subsequent data, and abnormally high heart rate data is excluded. The output is the preprocessed biometric data.

[1549] Step 5:

[1550] The server analyzes the user's emotions using an emotion engine based on the preprocessed data. The input is preprocessed biometric data. The emotion engine estimates the user's stress level and emotional state from fluctuations in heart rate and activity patterns. The output is analyzed emotion data.

[1551] Step 6:

[1552] The server comprehensively analyzes the preprocessed data and emotional data. The input is the preprocessed biometric data and emotional data. The data analysis identifies the user's lifestyle habits, exercise patterns, stress level, etc. The output is the analysis results.

[1553] Step 7:

[1554] The server uses generative AI to generate personalized health and diet advice based on the analysis results and emotional data. The input is the analysis results and emotional data. The generative AI model (e.g., TensorFlow) uses the analysis results and emotional data to generate advice. For example, advice such as "30 minutes of walking daily is recommended" may be generated for lack of exercise, or "a dinner containing ingredients with a relaxing effect is recommended" for high stress levels. The output is the generated health and diet advice.

[1555] Step 8:

[1556] The server sends the generated health and diet advice to the user's device and notifies them. The input is the generated health and diet advice. The advice is sent to the device and delivered to the user through the notification system. When the user receives the notification, they can tap it to view the detailed advice. The output is the advice and notification displayed on the user's device.

[1557] This process allows users to receive personalized health and dietary advice based on their biometrics and emotional state.

[1558] 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.

[1559] 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.

[1560] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1561] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1562] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1563] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1564] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1565] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1566] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1567] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1568] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1569] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1570] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1571] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1572] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1573] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1574] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1575] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1576] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1577] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1578] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1579] The following is further disclosed regarding the above embodiment.

[1580] (Claim 1)

[1581] means for collecting data from a device that monitors a user's biometric information;

[1582] means for transmitting said data to a server;

[1583] means for storing and pre-processing said data at said server;

[1584] means for analyzing the preprocessed data to identify the lifestyle habits of the user;

[1585] A means for generating individual health advice for each user using generation AI based on the analysis results;

[1586] means for transmitting the health advice to a user's terminal and notifying the user;

[1587] A system including:

[1588] (Claim 2)

[1589] 2. The system of claim 1, further comprising a preprocessing means for imputing missing values ​​and filtering outliers, and a means for recording data preprocessed by said preprocessing means in a database.

[1590] (Claim 3)

[1591] The system of claim 1 , wherein the generating AI includes means for generating health advice regarding exercise, diet, and rest based on the analysis results.

[1592] "Example 1"

[1593] (Claim 1)

[1594] means for collecting data from a device that monitors a user's biometric information;

[1595] means for transmitting said data to a server;

[1596] means for storing and pre-processing said data at said server;

[1597] means for analyzing the preprocessed data to identify the lifestyle habits of the user;

[1598] A means for generating individual health advice for each user using generation AI based on the analysis results;

[1599] means for transmitting the health advice to a user's terminal and notifying the user;

[1600] Means for the monitoring device to collect and transmit data at regular intervals

[1601] A system including:

[1602] (Claim 2)

[1603] 2. The system of claim 1, further comprising a preprocessing means for imputing missing values ​​and filtering outliers, and a means for recording data preprocessed by said preprocessing means in a database.

[1604] (Claim 3)

[1605] The system of claim 1 , wherein the generating AI includes means for generating health advice regarding exercise, diet, and rest based on the analysis results.

[1606] "Application Example 1"

[1607] (Claim 1)

[1608] means for collecting data from a device that monitors a user's biometric information;

[1609] means for transmitting said data to a server;

[1610] means for storing and pre-processing said data at said server;

[1611] means for analyzing the preprocessed data to identify the lifestyle habits of the user;

[1612] A means for generating individual health advice for each user using generation AI based on the analysis results;

[1613] means for transmitting the health advice to a user's terminal and notifying the user;

[1614] A means for recommending products according to the user's health condition based on the generated health advice;

[1615] means for generating discount and campaign information based on said health condition;

[1616] A system including:

[1617] (Claim 2)

[1618] 2. The system of claim 1, further comprising a preprocessing means for imputing missing values ​​and filtering outliers, and a means for recording data preprocessed by said preprocessing means in a database.

[1619] (Claim 3)

[1620] The system of claim 1 , wherein the generating AI includes means for generating health advice regarding exercise, diet, and rest based on the analysis results.

[1621] "Example 2: Combining Emotion Engines"

[1622] (Claim 1)

[1623] means for collecting data from a device that monitors a user's biometric information;

[1624] means for transmitting data from said device to a server;

[1625] means for storing and pre-processing said data at said server;

[1626] means for recognizing a user's emotion through an emotion engine using the preprocessed data;

[1627] means for analyzing the preprocessed data and emotion data to identify a lifestyle habit of a user;

[1628] A means for generating personalized health advice for each user using a generation AI based on the analysis results and emotion data;

[1629] means for transmitting the health advice to a user's terminal and notifying the user;

[1630] A system including:

[1631] (Claim 2)

[1632] 2. The system of claim 1, further comprising a preprocessing means for imputing missing values ​​and filtering outliers, and a means for recording data preprocessed by said preprocessing means in a database.

[1633] (Claim 3)

[1634] 2. The system of claim 1, wherein the generating AI comprises means for generating health advice regarding exercise, diet, and rest based on the analysis results and emotional data.

[1635] "Application example 2 when combining emotion engines"

[1636] (Claim 1)

[1637] means for collecting data from a device that monitors a user's biometric information;

[1638] means for transmitting said data to a server;

[1639] means for storing and pre-processing said data at said server;

[1640] means for analyzing the pre-processed data to identify the user's lifestyle habits and emotions;

[1641] A means for generating personalized health and dietary advice for each user using generative AI based on the analysis results and emotional data;

[1642] means for transmitting and notifying said health and diet advice to a user's terminal;

[1643] A system including:

[1644] (Claim 2)

[1645] 2. The system of claim 1, further comprising a preprocessing means for imputing missing values ​​and filtering outliers, and a means for recording data preprocessed by said preprocessing means in a database.

[1646] (Claim 3)

[1647] 2. The system of claim 1, wherein the generating AI comprises means for generating health advice regarding exercise, diet, and rest based on the analysis results and emotional data. [Explanation of symbols]

[1648] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting data from a device that monitors a user's biometric information; means for transmitting said data to a server; means for storing and pre-processing said data at said server; means for analyzing the preprocessed data to identify the lifestyle habits of the user; A means for generating individual health advice for each user using generation AI based on the analysis results; means for transmitting the health advice to a user's terminal and notifying the user; A system including:

2. The system according to claim 1 , further comprising a preprocessing means for imputing missing values ​​and filtering outliers, and a means for recording data preprocessed by said preprocessing means in a database.

3. The system according to claim 1 , wherein the generating AI comprises means for generating health advice regarding exercise, diet, and rest based on the analysis results.

Images