system

Abstract

We provide the system. [Solution] A means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device, Means for preprocessing the aforementioned data, A means of analyzing a user's health status using pre-processed data, A means for generating personalized health and fitness advice based on analysis results, A means of notifying the user's device of the generated advice, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern society, it is very important to receive specific and effective health and fitness advice based on the lifestyle and health status of individual users. However, in conventional systems, a series of processes from data collection to analysis, advice generation, and provision are not sufficiently automated, making it difficult to provide useful information to users. It is also difficult to easily receive customized feedback from experts. Therefore, there is a need for an efficient system that provides individualized health and fitness advice and plans.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a system that includes means for collecting data on exercise capacity, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results; and means for notifying the user of the generated advice to the user's terminal. Furthermore, by providing means for providing a customized exercise plan by an expert based on the user's request, the user can also receive expert feedback. In addition, the analysis means employs regression analysis and clustering to predict the user's health status with high accuracy and provide specific advice based on the results.

[0006] A "wearable device" is an electronic device that is attached to a user's body to collect biometric data such as athletic ability, sleep habits, and heart rate.

[0007] "Physical ability" refers to data that shows the amount and type of physical activity a user performed within a specific period, such as the number of steps taken or activity level.

[0008] "Sleep habits" refers to data that shows a user's sleep patterns, sleep duration, and sleep quality.

[0009] "Heart rate" is data that shows the number of times a user's heart beats over a certain period of time.

[0010] "Data preprocessing" is the process of removing noise and outliers from collected biological data and preparing the data for analysis.

[0011] "Means for analyzing health status" refers to methods and systems that use pre-processed data to analyze a user's health status and predict their physical condition, sleep patterns, and heart rate.

[0012] "Means for generating personalized advice" refers to the process of creating health and fitness advice optimized for each user based on analysis results.

[0013] "Means of notification" refers to methods or systems that send generated advice to the user's device so that the user can review that advice.

[0014] A "customized exercise plan by an expert" is an individualized exercise program created by a specialist based on the user's specific requests.

[0015] Regression analysis is a statistical method that models the relationships between consecutive data and uses those relationships to make predictions and analyze trends.

[0016] Clustering is a technique for dividing data into several groups (clusters), and it is an analytical method characterized by the fact that data within the same cluster have similar characteristics. [Brief explanation of the drawing]

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

Embodiments for Carrying Out the Invention

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

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

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

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

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

[0023] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0025] [First Embodiment]

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

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

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

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

[0030] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0034] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

[0036] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0038] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management.

[0039] System Configuration

[0040] Data collection

[0041] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. The wearable device sends this data to the server at regular intervals. For example, it can send step count, heart rate, and sleep data to the server every 30 minutes.

[0042] Data preprocessing

[0043] The server preprocesses the collected biometric data. For example, it performs noise reduction, filters outliers, and converts the data to the required format. Since raw data may contain missing values, it performs appropriate imputation. It also formats the data on a time-based basis and converts it to a format suitable for analysis.

[0044] Data analysis

[0045] The pre-processed data is used by the server to analyze the user's health status. Specifically, statistical methods such as regression analysis and clustering are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, based on heart rate data from the past 30 days, predictions for the next 30 days can be made.

[0046] Generating advice

[0047] Based on the analysis results, the server generates personalized health and fitness advice. For example, a user who has not exercised enough in the past 30 days can be given specific advice such as "We recommend increasing your daily walking time by 10 minutes." Similarly, a user with a high heart rate can be recommended breathing exercises to help them relax.

[0048] Notification to the user

[0049] The server notifies the user's device of the generated advice according to its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone app.

[0050] Providing a customized exercise plan

[0051] When a user requests a customized exercise plan from an expert through the app, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "30 minutes of strength training three times a week."

[0052] Specific example

[0053] After a user has worn a wearable device for a day, the device collects the following data:

[0054] Step count: 8000 steps

[0055] Average heart rate: 75 bpm

[0056] Sleep duration: 7 hours

[0057] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[0058] 8,000 steps is short of the target of 10,000 steps.

[0059] The average heart rate is within a moderate range.

[0060] My sleep duration falls within the recommended range of 7-8 hours.

[0061] Based on this analysis, the server generates the following advice:

[0062] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0063] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0064] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0065] The server sends this advice to the device, allowing the user to view the advice through a smartphone app.

[0066] Furthermore, when a user requests a customized exercise plan from an expert, the server sends the request to the expert and provides the user with the exercise plan designed by the expert, thereby supporting more specific health management and fitness achievement.

[0067] As described above, the present invention integrates data collection, preprocessing, analysis, advice generation, and notification from wearable devices to provide users with personalized health management and fitness support.

[0068] The following describes the processing flow.

[0069] Step 1:

[0070] The server collects data from wearable devices. Specifically, the server periodically communicates with wearable devices to obtain biometric data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might send an API request at 12:00 every day to collect data from the previous day.

[0071] Step 2:

[0072] The server preprocesses the collected biometric data. Specifically, it removes noise from the data and filters out outliers. Next, it normalizes the preprocessed data and converts it into a format suitable for analysis. For example, if step count data is missing, it is imputed with the mean value.

[0073] Step 3:

[0074] The server analyzes the pre-processed data. Specifically, it uses regression analysis and clustering to analyze the user's exercise capacity, sleep patterns, and heart rate in detail. For example, it uses data from the past 30 days to build a predictive model for the next 30 days.

[0075] Step 4:

[0076] The server generates personalized advice based on the analysis results. For example, if a user's step count hasn't reached their goal, it will make specific suggestions such as "increase your daily step count by 2000 steps." If the user's heart rate is high, it will suggest ways to relax.

[0077] Step 5:

[0078] The server notifies the user's device of the generated advice. Specifically, it creates a notification message and sends it via push notification or in-app messaging. For example, it can send real-time notifications using Firebase Cloud Messaging (FCM).

[0079] Step 6:

[0080] The device receives notifications from the server and displays advice through the user interface. For example, the notification bar of a smartphone app might display, "Your step count today is low. Let's walk another 2000 steps!"

[0081] Step 7:

[0082] Users can request a customized exercise plan from an expert through the app. For example, they can enter a specific request in a form, such as "I want to increase my strength training."

[0083] Step 8:

[0084] The server receives requests from users and forwards them to experts. The experts create customized exercise plans based on the requests and send them back to the server. For example, a "30-minute strength training plan, three times a week" might be created.

[0085] Step 9:

[0086] The server then notifies the user's device again of the customized exercise plan from the expert, and the user can view the detailed exercise plan through the app. For example, the new exercise plan will appear on the app's dashboard.

[0087] Through the processing steps described above, this system can manage users' health conditions in a highly personalized manner and provide effective fitness and health advice.

[0088] (Example 1)

[0089] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0090] With the recent rise in health awareness, many people are using wearable devices to monitor their health. However, the amount of data obtained from these devices is enormous, making it difficult for individual users to accurately interpret it and apply it to their daily lives. Furthermore, there is a need for systems that go beyond mere data collection, comprehensively analyze the user's health status, and provide personalized health advice. Conventional systems often lack sufficient data preprocessing and the provision of customized advice from experts, which prevents users from reaping the maximum benefit.

[0091] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0092] In this invention, the server includes means for collecting biometric data from a wearable device, means for preprocessing the biometric data, means for analyzing the user's health status using the preprocessed data, means for generating individualized health and exercise advice based on the analysis results, and means for notifying the user's device of the generated advice. This enables the user to receive personalized health advice based on data collected from the wearable device, thereby achieving more effective health management and fitness support.

[0093] A "wearable device" is a device that is attached to the user's body and measures and records biometric data such as exercise ability, heart rate, and sleep habits.

[0094] "Biometric data" refers to information about a user's physical condition and activity measured by wearable devices, and specifically includes heart rate, steps taken, sleep duration, etc.

[0095] "Preprocessing" refers to the process of converting biological data into a format that is easy to analyze, and specifically includes noise reduction, filtering of outliers, and imputation of missing values.

[0096] "Analysis" refers to calculations and methods used to evaluate and predict a user's health status using pre-processed data, specifically involving the use of statistical methods such as regression analysis and clustering.

[0097] "Advice generation" is the process of creating personalized health and exercise advice for users based on the analysis results.

[0098] "User's device" refers to an information terminal used by the user, including digital devices such as smartphones, tablets, and personal computers.

[0099] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management. This system operates with three components: a server, a terminal, and a user.

[0100] First, the server collects biometric data (e.g., heart rate, steps, sleep data, etc.) from the user's wearable device (e.g., a smartwatch worn on the user's wrist). This data is sent to the server at regular intervals (e.g., every 30 minutes). Specifically, the server uses a server computer with a high-performance CPU and sufficient memory.

[0101] Next, the server preprocesses the data. This preprocessing includes denoising the received data (e.g., removing abnormally high heart rates), filtering outliers, and imputing missing values. These processes are performed using data processing libraries such as Python's Pandas and NumPy.

[0102] The pre-processed data is used by the server to analyze the user's health status. Specifically, machine learning libraries such as scikit-learn are used to perform regression analysis and clustering to predict and analyze the user's exercise capacity, sleep patterns, and heart rate trends.

[0103] Based on the analysis results, the server generates personalized health and fitness advice. For example, it predicts the heart rate for the next 30 days based on heart rate data from the past 30 days and provides specific advice to users who are not getting enough exercise, such as "We recommend increasing your daily walking time by 10 minutes." It also recommends breathing exercises to help users with elevated heart rates relax.

[0104] The generated advice is sent from the server to the user's device (e.g., a smartphone or tablet). The device displays the received advice through a user interface. For example, the advice may be displayed as a pop-up notification or on a dashboard using a smartphone app.

[0105] Furthermore, if a user requests a customized exercise plan from an expert, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "perform 30 minutes of strength training three times a week."

[0106] Specific example

[0107] As an example for one day, suppose a user wears a wearable device while performing activities, and the following data is collected:

[0108] Step count: 8000 steps

[0109] Average heart rate: 75 bpm

[0110] Sleep duration: 7 hours

[0111] The server receives this data, performs noise reduction and outlier filtering using Pandas and NumPy, and then analyzes the data using scikit-learn. The analysis results yield the following insights:

[0112] 8,000 steps is short of the target of 10,000 steps.

[0113] The average heart rate is within a moderate range.

[0114] My sleep duration falls within the recommended range of 7-8 hours.

[0115] Based on this analysis, the server generates the following advice:

[0116] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0117] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0118] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0119] The server sends this advice to the user's smartphone, and the user can view this advice through the app.

[0120] Furthermore, when a user requests a customized exercise plan, the server forwards the request to an expert, who then provides the user with an exercise plan designed by the expert. For example, if a user requests a "30-minute, 3-session strength training plan per week from an expert," the expert designs the plan and sends it to the server, which then communicates it to the user.

[0121] In this way, the system enables consistent data collection, preprocessing, analysis, advice generation, notification, and customized plan delivery. Through this process, users can gain a deeper understanding of their own health status and receive effective health management and fitness support.

[0122] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0123] Step 1: Data Collection

[0124] The server collects biometric data from the user's wearable device. This device periodically (for example, every 30 minutes) records heart rate, steps, sleep data, etc., and transmits it to the server via Bluetooth or Wi-Fi. The input data is the biometric data obtained from the wearable device, and this becomes the output data at the time it is transmitted to the server.

[0125] Specific actions:

[0126] Wearable devices measure the user's biometric data.

[0127] The measurement data is sent to the server at regular intervals.

[0128] The server stores this data in the database.

[0129] Step 2: Data preprocessing

[0130] The server performs noise reduction, filters outliers, and imputes missing values ​​in the received biometric data. The input data is the biometric data collected in step 1, and the pre-processed data becomes the output data.

[0131] Specific actions:

[0132] Load the data using libraries such as Pandas or NumPy.

[0133] Noise reduction: For example, detecting and removing extremely high heart rates or abnormally low step counts.

[0134] Outlier filtering: Replace outliers with the median or mean of the data.

[0135] Imputing missing values: For example, missing values ​​can be imputed using the mean of the preceding and succeeding data.

[0136] Step 3: Data Analysis

[0137] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning models (regression analysis, clustering, etc.). The input data is pre-processed biometric data, and the analysis results become the output data.

[0138] Specific actions:

[0139] Load the analysis model using the scikit-learn library.

[0140] Regression analysis is performed to predict future heart rate and step count based on past data.

[0141] Clustering is used to classify users' sleep patterns and athletic abilities.

[0142] As a result, analyzed health status data is generated.

[0143] Step 4: Generating advice

[0144] The server generates personalized fitness and health advice based on the analysis results. The input data is the analysis results obtained in step 3, and the generated advice becomes the output data.

[0145] Specific actions:

[0146] Based on the analysis results, a prompt message is created that generates appropriate advice using a generative AI model.

[0147] For example, it can automatically generate specific advice such as, "Your heart rate is a little high. Please do some breathing exercises to relax."

[0148] Output the advice in text format.

[0149] Step 5: Notify the user

[0150] The server sends the generated advice to the user's terminal. The input data is the generated advice, and the output data is the notification of this advice sent to the user's terminal.

[0151] Specific actions:

[0152] Once the advice is generated, the server identifies the corresponding user's terminal.

[0153] Advice will be sent as a push notification to the user's smartphone or other device.

[0154] The user's device displays the received advice, allowing the user to review it.

[0155] Step 6: Providing a customized exercise plan

[0156] When a user requests a customized exercise plan through the app, the server forwards the request to a specialist. The input data is the user's request, and the output data is the customized exercise plan provided to the user.

[0157] Specific actions:

[0158] The user submits a request through the application.

[0159] The server forwards this request to an expert.

[0160] Experts create exercise plans based on user data.

[0161] Once the exercise plan is complete, it is sent to the user via the server.

[0162] Users can view their customized exercise plan through the application.

[0163] (Application Example 1)

[0164] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0165] Current fitness and health management systems collect and analyze individual user data to provide advice, but these are primarily limited to personal use. However, providing immediate, personalized advice to customers in physical stores can offer even greater support for health management and fitness. Systems that enable this kind of immediate advice in physical stores are still lacking, and realizing immediate fitness instruction and health management support for customers within physical stores remains a challenge.

[0166] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0167] In this invention, the server includes means for collecting data on exercise capacity, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results; means for notifying the user's terminal of the generated advice; and means for understanding the individual health status of customers in a physical store and providing fitness-related advice immediately. This makes it possible to provide customers with immediate, personalized health management and fitness advice in a physical store.

[0168] A "wearable device" is an electronic device that is attached to a user's body to collect biometric data such as athletic ability, sleep habits, and heart rate.

[0169] "Exercise capacity" refers to data that indicates the quantity and quality of exercise, such as the user's step count, calories burned, and exercise intensity.

[0170] "Sleep habits" refers to data that shows the user's sleep-related behaviors and patterns, such as sleep duration, sleep quality, time to fall asleep, and time to wake up.

[0171] "Heart rate" is data that indicates the number of heartbeats per minute and is an indicator of the user's cardiac activity.

[0172] "Preprocessing" is the process of converting collected biological data into a format suitable for analysis by performing noise reduction, filtering outliers, and imputing missing values.

[0173] "Health status" refers to the overall health condition of the user, based on data such as their exercise capacity, sleep habits, and heart rate.

[0174] "Analysis" is the process of evaluating and predicting a user's health status using statistical methods and machine learning techniques based on pre-processed data.

[0175] "Personalized advice" refers to providing specific health management and fitness guidance and recommendations tailored to individual users, based on analysis results.

[0176] "Notification" refers to the act of sending generated advice or information to a user's device to inform the user.

[0177] A "physical store" is a place that provides fitness instruction and health management services, and is a physical facility that customers can visit in person.

[0178] "Providing information instantly" means collecting and analyzing user data in real time and providing advice to customers immediately based on the results.

[0179] A "customized exercise plan by an expert" is an individualized exercise program designed by a fitness professional with specialized knowledge, based on the user's specific requests.

[0180] "Regression analysis" is a statistical method used to predict a user's future health status based on past data.

[0181] Clustering is a machine learning technique used to classify user data into groups with similar characteristics.

[0182] System Configuration

[0183] This invention is a system that utilizes data collected from wearable devices to provide customers with immediate fitness advice and health management in physical stores. The specific system configuration and operation are described below.

[0184] Data collection

[0185] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices worn by the user. The wearable device transmits this data to the server at regular intervals. Examples include smartwatches and smart bands.

[0186] Data preprocessing

[0187] The server preprocesses the collected biometric data. Specifically, it uses data processing libraries such as Pandas and NumPy to remove noise, filter outliers, and impute missing values, converting the data into a format suitable for analysis. For example, if data is missing, it is imputed with the mean value.

[0188] Data analysis

[0189] The pre-processed data is used by the server to analyze the user's health status. The methods used include machine learning techniques such as regression analysis and clustering. Libraries such as Scikit-learn are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends.

[0190] Generating advice

[0191] Based on the analysis results, the server generates personalized health and fitness advice. For example, if a user's step count is insufficient based on past data, it will generate advice such as, "Try to walk more to reach your step goal." If the heart rate is within a healthy range, it will generate a message such as, "Continue managing your health at this pace."

[0192] Notification to the user

[0193] The generated advice is sent to the user's device as a notification, depending on its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone application.

[0194] In-store, immediate fitness instruction

[0195] In physical stores, servers monitor each customer's health status and provide immediate fitness-related advice. Store staff can use the customer's device to view and provide personalized advice based on real-time health data. This enables more effective fitness instruction and health management.

[0196] Specific example

[0197] After a user has worn a wearable device for a day, the device collects the following data:

[0198] Step count: 8000 steps

[0199] Average heart rate: 75 bpm

[0200] Sleep duration: 7 hours

[0201] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[0202] 8,000 steps is short of the target of 10,000 steps.

[0203] The average heart rate is within a moderate range.

[0204] My sleep duration falls within the recommended range of 7-8 hours.

[0205] Based on this analysis, the server generates the following advice:

[0206] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0207] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0208] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0209] The server sends this advice to the user's device, allowing the user to view the advice through a smartphone application.

[0210] Example of a prompt

[0211] Please generate personalized fitness and health advice based on the following data.

[0212] Data format:

[0213] {

[0214] "steps":

[8000] ,

[0215] "heart_rate":

[75] ,

[0216] "sleep_hours": [7]

[0217] }

[0218] Based on the analysis results, please generate advice using the following criteria:

[0219] 1. If your step count is less than 10,000 steps, you are advised to increase your step count to reach your goal.

[0220] 2. If the heart rate is within the range of 60-100 bpm, a notification will be issued indicating that it is normal.

[0221] 3. If your sleep duration is between 7 and 8 hours, it is recommended that you maintain good sleep habits.

[0222] This will now describe the specific form for carrying out the invention.

[0223] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0224] Step 1:

[0225] The server collects biometric data related to exercise capacity, sleep habits, and heart rate from wearable devices worn by the user at regular intervals. It receives biometric data transmitted from the wearable device as input and stores it in a database. Specifically, for example, a smartwatch sends the user's step count, average heart rate, and sleep data to the server every 30 minutes.

[0226] Step 2:

[0227] The server preprocesses the collected biometric data. It takes biometric data stored in a database as input, performs noise reduction, filters outliers, and imputes missing values. Specifically, it uses Pandas and NumPy to clean the data and convert it into a format suitable for analysis. This results in formatted data being output.

[0228] Step 3:

[0229] The server analyzes the user's health status using pre-processed data. It takes pre-processed data as input and performs regression analysis and clustering using machine learning libraries such as Scikit-learn. Specifically, it uses regression analysis to predict the next 30 days based on heart rate data from the past 30 days, and clustering to classify users into groups according to their health status. The analysis results are then output.

[0230] Step 4:

[0231] The server generates personalized health and fitness advice based on the analysis results. It takes the analysis results as input and creates advice tailored to the user's specific data. For example, it might generate advice such as "Try to walk a little more" for a user whose step count hasn't reached their goal, or "Continue managing your health at this pace" for a user whose heart rate is within the normal range. This results in personalized advice being output.

[0232] Step 5:

[0233] The server notifies the user's device of the generated advice. It retrieves the generated advice as input and sends it to the user's smartphone or tablet. The device displays the received advice message and informs the user. Specifically, the smartphone application displays the advice content as a pop-up notification or on the dashboard. This allows the user to receive feedback in real time.

[0234] Step 6:

[0235] The server analyzes user data in real time and notifies store staff to provide immediate fitness-related advice within the physical store. It uses data collected in real time as input, performs analysis and generates advice, and notifies store staff terminals. This allows store staff to understand each customer's individual health status and provide immediate, specific fitness guidance and health management.

[0236] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0237] The present invention is a system that provides personalized health and fitness advice by combining data collected from a wearable device with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[0238] System Configuration

[0239] Data collection

[0240] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. For example, data is sent from the wearable device to the server at regular intervals each day. This data includes the total number of steps taken per day, average heart rate, and sleep duration.

[0241] Data preprocessing

[0242] The server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[0243] Data analysis

[0244] The server analyzes the user's health status based on pre-processed data. Using regression analysis and clustering techniques, it analyzes and predicts the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts the amount of exercise for the next 30 days based on exercise data from the past 30 days and identifies areas for improvement.

[0245] Implementation of an emotion engine

[0246] The server also features an emotion engine. This emotion engine recognizes the user's emotions using voice, facial expressions, and text data. For example, it uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and uses an emotion recognition algorithm to identify the user's current emotional state.

[0247] Generating advice

[0248] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will recommend relaxation exercises. Also, if the server detects that the user is agitated on a day with a high heart rate, it will provide advice to adjust the amount of exercise.

[0249] Notification to the user

[0250] The server notifies the user's device of the advice it has generated. The device analyzes the advice message received from the server and displays it through the user interface. For example, a smartphone app can display pop-up notifications or a dashboard to allow the user to quickly check the advice.

[0251] Providing a customized exercise plan

[0252] Users can request a customized exercise plan from an expert through the app. They enter their specific request details into a form and submit it to the server. The server forwards this request to an expert, who designs a customized exercise plan based on the user's request. This exercise plan is then provided to the user again via the server. For example, the plan might include specific details such as "perform 30 minutes of aerobic exercise three times a week."

[0253] Specific example

[0254] Data Acquisition and Preprocessing

[0255] The server collects the following data from the user's wearable device:

[0256] Step count: 8000 steps

[0257] Average heart rate: 75 bpm

[0258] Sleep duration: 7 hours

[0259] Data Analysis

[0260] The server analyzes the pre-processed data and obtains the following conclusions:

[0261] The number of steps taken has not reached the target of 10,000 steps.

[0262] The average heart rate is within a moderate range.

[0263] Sleep duration is within the recommended range of 7-8 hours.

[0264] emotion recognition

[0265] The emotion engine uses the smartphone's camera and microphone to analyze the user's facial expressions and voice, recognizing when the user is experiencing stress.

[0266] Generating advice

[0267] The server considers both health and emotional state to generate the following advice:

[0268] "Your step count today is 8,000 steps, which is short of your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[0269] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0270] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0271] Advice notification

[0272] The server sends the generated advice to the device, and the user can check the advice through a smartphone app.

[0273] Customized exercise plan

[0274] When a user requests a customized exercise plan from an expert, the server forwards the request to the expert, who then provides the user with the designed exercise plan. For example, a specific plan such as "a 30-minute strength training session three times a week" might be provided.

[0275] As described above, the present invention is a system that combines data obtained from a wearable device with the user's emotions to provide more highly personalized health management and fitness support.

[0276] The following describes the processing flow.

[0277] Step 1:

[0278] The server collects data from wearable devices. Specifically, the server uses the device API to send regular data acquisition requests to obtain vital data such as exercise ability (number of steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it is set to collect the previous day's data at 0:00 every day.

[0279] Step 2:

[0280] The server preprocesses the collected data. First, it removes data noise, for example, filtering extremely high number of steps or abnormal heart rate. Next, it normalizes the data to make it consistent as time series data. For example, it fills in missing data with the average value.

[0281] Step 3:

[0282] The server analyzes the user's health status based on the preprocessed data. Specifically, it uses machine learning algorithms (regression analysis and clustering) to analyze and predict the trends of the user's exercise ability, sleep pattern, and heart rate. For example, it applies an algorithm that predicts the activity level for the next 30 days based on the data for the past 30 days and proposes an appropriate exercise plan.

[0283] Step 4:

[0284] The server recognizes the user's emotions through an emotion engine. The emotion engine collects the user's facial expression data and voice data using the smartphone's camera and microphone and analyzes the emotions. For example, it captures the facial expression with the camera and obtains the voice response when the user opens the app.

[0285] Step 5:

[0286] [[ID=The server integrates the health status analysis results and the emotion data recognized by the emotion engine to generate personalized health and fitness advice. For example, when the user has insufficient exercise volume and is feeling stressed, it generates advice such as "Take a light walk that also helps you relax."

[0287] Step 6:

[0288] The server notifies the user's terminal of the generated advice. Specifically, it generates a notification message and sends a push notification to the user's smartphone app using Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNs). For example, it sends a message like "Your exercise volume today has not reached the target. We recommend taking a light walk that also helps you relax."

[0289] Step 7:

[0290] The terminal analyzes the advice message received from the server and displays it on the user interface. Specifically, it displays it as a pop-up message in the notification bar of the smartphone or shows detailed advice on the in-app dashboard. For example, it displays details such as "Today's exercise volume: 8000 steps / 10000 steps" and specific suggestions like "Perform relaxation exercises."

[0291] Step 8:

[0292] The user requests a customized exercise plan from an expert through the app. For example, the user enters something like "Want to increase strength training" in the request form within the app and presses the send button.

[0293] Step 9:

[0294] The server receives the user's request and forwards it to an expert. The expert customizes the exercise plan based on the request. For example, they might create a program recommending "30 minutes of strength training three times a week."

[0295] Step 10:

[0296] The server then notifies the user's device again of the customized exercise plan received from the expert. The user can then view the new exercise plan through a smartphone app. For example, the app's dashboard might display a "Strength Training Plan" with specific exercises to be done three times a week.

[0297] In this way, this system, which incorporates an emotion engine, provides more personalized health and fitness support based on multifaceted data analysis that includes the user's emotional state.

[0298] (Example 2)

[0299] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0300] Traditional health and fitness management systems can collect users' biometric data and assess their basic health status, but they have limitations in generating personalized advice. Furthermore, advice provided without considering the user's emotional state is less effective. Additionally, users must manually request customized exercise plans from professionals, which is time-consuming and inconvenient. There is a need to address these challenges and provide more detailed and personalized health and fitness support.

[0301] The identification processing 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 means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results and emotion recognition; and means for notifying the user's terminal of the generated advice and customized exercise plan. This enables the user to receive more detailed and personalized advice that comprehensively considers their health status and emotional state. Furthermore, the request and provision of customized exercise plans by experts are automated, reducing the burden on the user.

[0302] A "wearable device" is a device that is worn on a user's body to collect biometric data. Examples include smartwatches and fitness trackers.

[0303] "Physical ability" refers to data that indicates the user's physical activity performance. Specifically, it includes steps taken, distance traveled, calories burned, and so on.

[0304] "Sleep habits" refers to data that shows a user's sleep patterns and sleep quality. Specifically, it includes sleep duration, percentage of deep sleep, and number of sleep interruptions.

[0305] "Heart rate" is data that indicates the number of times a user's heart beats. It is usually expressed as heart rate per minute (bpm).

[0306] "Preprocessing" refers to data processing to convert collected biological data into an analyzable format. Specifically, this includes noise reduction, outlier filtering, and data normalization.

[0307] "Health status" refers to data indicating the overall physical condition and health level of a user. This is comprehensively evaluated from multiple data such as exercise ability, sleep habits, and heart rate.

[0308] "Emotion recognition" is a technology that identifies a user's emotional state using voice, facial expressions, and text data. Specifically, data is collected using the camera and microphone of a smartphone and analyzed by an algorithm.

[0309] "Individualized health and fitness advice" refers to specific guidance and recommendations tailored to each individual, taking into account the user's health status and emotional state.

[0310] "Terminal" refers to an electronic device that a user can operate. Examples include smartphones, tablets, and personal computers.

[0311] "Customized exercise plan" refers to an exercise plan designed based on the specific needs and goals of a user. It is created by an expert in response to the user's request.

[0312] "Expert" refers to a person with knowledge and experience related to a user's health and fitness. Examples include trainers and nutritionists.

[0313] "Notification" refers to the act of transmitting the generated advice and customized exercise plan to the user's terminal. Specifically, it includes pop-up notifications and dashboard displays.

[0314] Mode for Carrying Out the Invention

[0315] The present invention is a system that combines data collected from a wearable device with an emotion engine that recognizes a user's emotions to provide individualized health and fitness advice. This system is realized using the following hardware and software.

[0316] Data collection

[0317] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices (e.g., smartwatches, fitness trackers). The collection process involves the wearable device sending data to the server at regular intervals each day. For example, at 6 AM every morning, a day's worth of data (steps, average heart rate, sleep duration, etc.) is collected.

[0318] Data preprocessing

[0319] The server preprocesses the collected data. This process includes noise reduction, outlier filtering, and data normalization. For example, it removes or interpolates data points where the average heart rate is extremely high (above 150 bpm) or low (below 40 bpm).

[0320] Data analysis

[0321] The server analyzes the pre-processed data. The analysis steps include predicting health status using regression analysis and clustering techniques, and analyzing trends in exercise capacity, sleep patterns, and heart rate. For example, based on exercise data from the past 30 days, it sets exercise goals for the next 30 days and identifies areas for improvement.

[0322] Implementation of an emotion engine

[0323] The server uses an emotion engine to recognize the user's emotions based on voice, facial expressions, and text data. The emotion engine uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and analyzes them with an emotion recognition algorithm. For example, while the user is using their smartphone, the camera captures their facial expressions and audio data is collected to determine whether the user is experiencing stress.

[0324] Generating advice

[0325] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it recommends relaxation exercises, and if a lack of exercise is detected, it suggests a light jog. Specific advice might include messages such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so we recommend a light walk."

[0326] Advice notification

[0327] The server notifies the user's device of the generated advice. The device analyzes the received advice message and displays it through the user interface. For example, a smartphone app might display a pop-up notification so that the user can quickly check the advice.

[0328] Customized exercise plan

[0329] Users can request a customized exercise plan from an expert through the app. They enter their request details into a form and submit it to the server. This information is forwarded to the expert, who designs an exercise plan tailored to the user's specific needs. The designed exercise plan is then provided to the user again via the server. For example, a specific plan such as "30-minute strength training sessions three times a week" might be provided.

[0330] Specific examples and prompt statements

[0331] Specific example

[0332] Data Collection: The server collects a day's worth of data from wearable devices every morning at 6:00 AM (steps: 8,000, average heart rate: 75 bpm, sleep time: 7 hours).

[0333] Data preprocessing: The server removes outliers where the heart rate exceeds 150 bpm.

[0334] Data analysis: Set exercise goals for the next 30 days based on exercise data from the past 30 days.

[0335] Emotion recognition: The system uses the smartphone's camera to recognize when the user is experiencing stress.

[0336] Advice generation: Generates the advice: "Your step count today is 8000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[0337] Advice Notification: The server sends the generated advice to the user's smartphone and displays it as a pop-up notification.

[0338] Customized Exercise Plan: Users request a "30-minute strength training plan, 3 times a week," and experts design and provide it.

[0339] Examples of prompt statements

[0340] "Create a program that recognizes the user's emotions and provides health advice based on them. For example, include a feature that recommends relaxation exercises if the user is feeling stressed."

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1: Data Collection

[0343] The server collects biometric data from the user's wearable device.

[0344] Input: Exercise capacity, sleep habits, and heart rate data transmitted from wearable devices.

[0345] Specific operation: For example, request and receive a day's worth of data (steps, average heart rate, sleep duration) from a Fitbit or smartwatch at 6 AM every morning.

[0346] Output: Collected biometric data (e.g., total daily steps 8000, average heart rate 75 bpm, sleep duration 7 hours).

[0347] Step 2: Data preprocessing

[0348] The server preprocesses the collected data.

[0349] Input: Collected biometric data.

[0350] Specific operations: Noise reduction, outlier filtering, and data normalization. For example, it detects and removes outliers such as an average heart rate exceeding 150 bpm. It also imputes missing data points.

[0351] Output: Preprocessed data.

[0352] Step 3: Data Analysis

[0353] The server analyzes the pre-processed data.

[0354] Input: Pre-processed data.

[0355] Specific actions: Using regression analysis and clustering techniques, the system analyzes the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts exercise levels for the next 30 days using data from the past 30 days.

[0356] Output: Analysis results and health status prediction.

[0357] Step 4: Emotion Recognition

[0358] The server uses an emotion engine to recognize the user's emotions.

[0359] Input: Voice, facial expressions, and text data collected from the smartphone's camera and microphone.

[0360] Specific operation: The smartphone camera is activated, and the user's facial expression and voice data are collected in real time and analyzed using an emotion recognition algorithm. For example, it can determine whether the user is experiencing stress.

[0361] Output: User's emotional state (e.g., stress).

[0362] Step 5: Generating Advice

[0363] The server generates personalized advice based on the analysis of health status and the recognition of emotions.

[0364] Input: Analysis results and emotional state.

[0365] Specific actions: For example, create advice such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[0366] Output: Generated advice message.

[0367] Step 6: Advice Notification

[0368] The server notifies the user's terminal of the generated advice.

[0369] Input: Generated advice message.

[0370] Specific actions: Send an advice message to the device and display it to the user through a pop-up notification or dashboard display. For example, display a notification via a smartphone app.

[0371] Output: Advice displayed to the user.

[0372] Step 7: Customized Exercise Plan

[0373] Users can request a customized exercise plan from an expert through the app.

[0374] Input: User request information (specific needs and goals).

[0375] Specific operation: Enter information into the request form within the app and send it to the server. The server forwards the request to an expert, who designs an exercise plan based on the user's needs. For example, a "30-minute strength training plan three times a week" might be created.

[0376] Output: A customized exercise plan is provided to the user.

[0377] (Application Example 2)

[0378] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0379] Traditional health management systems primarily focused on collecting and analyzing biometric data such as users' exercise capacity, sleep habits, and heart rate to provide fitness advice. However, they lacked personalization because they did not take into account the user's emotional state. Furthermore, they lacked suggestions for suitable meal plans in addition to health management. As a result, comprehensive health management and improvements in fitness and dietary habits were difficult.

[0380] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health and emotional state using the preprocessed data; means for generating personalized health and fitness advice based on the analyzed data; and means for notifying the user's terminal of the generated advice and suggesting meal menus based on the progress. This enables comprehensive health management that takes into account both the user's health and emotional state, and meal suggestions that are appropriate to the user's health state.

[0381] A "wearable device" is an electronic device that an individual can wear to collect biometric data such as athletic ability, sleep habits, and heart rate.

[0382] "Emotional state" refers to data that indicates the emotions and psychological state a user is experiencing at a specific time.

[0383] "Preprocessing" refers to the process of applying noise reduction, filtering outliers, and normalizing data to biometric data collected from wearable devices.

[0384] "Health status" refers to data that indicates the user's physical and physiological condition, including exercise capacity, sleep patterns, and heart rate.

[0385] "Fitness advice" refers to specific suggestions and guidance regarding exercise, diet, and rest to improve the user's health.

[0386] The "meal menu" is a list that suggests balanced meals based on the user's health and emotional state.

[0387] "Progress" refers to data that shows changes and progress in the user's health status.

[0388] A "customized exercise plan by an expert" is an exercise plan designed by an expert based on the individual user's health condition and goals.

[0389] Regression analysis is a statistical method that models the relationships between numerical data and is used to predict specific health conditions.

[0390] Clustering is a data analysis technique that groups data based on similarity and is used to identify user health patterns.

[0391] A "prompt sentence" is text input into a generative AI model that contains instructions for generating specific information or answers.

[0392] This invention is a system that analyzes data collected from a wearable device and the user's emotional state to provide personalized health and fitness advice and meal menus. Specific embodiments of this system are described in detail below.

[0393] First, the server collects data on exercise capacity, sleep habits, and heart rate from wearable devices. Wearable devices such as Apple Watch, Fitbit, and Garmin can be used. The data collected from these devices is sent to the server at regular intervals.

[0394] Next, the server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[0395] Based on the pre-processed data, the server analyzes the user's health and emotional state. The emotional state is analyzed using an emotion engine. This emotion engine uses technologies such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API, and collects the user's facial expressions and voice data through the smartphone's camera and microphone.

[0396] The server then generates personalized health and fitness advice based on the analysis results. It also suggests appropriate meal plans, taking into account the user's health and emotional state. For example, if data from a wearable device indicates that the user's heart rate is low and that calorie intake is needed, the server will suggest a meal plan suitable for energy replenishment.

[0397] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed to be intuitive and easy to use, allowing users to quickly check the advice and meal menus through pop-up notifications and dashboard displays.

[0398] As a concrete example, a notification using the following prompt statement can be considered:

[0399] "Based on your health and mood today, here are our recommended dishes: a healthy salad and lean grilled chicken. Would you like to order?"

[0400] Furthermore, users can request customized exercise and meal plans from experts through the app. These requests are sent to experts via the server, and the plans provided by the experts are then notified to the user via the server.

[0401] As described above, the system of the present invention provides comprehensive health management that takes into account both the user's physical and emotional state, as well as personalized fitness and dietary suggestions.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] The server collects biometric data from wearable devices regarding exercise capacity, sleep habits, and heart rate. Specifically, data is sent from devices such as Apple Watch, Fitbit, and Garmin at regular intervals.

[0405] Input: Biometric data related to athletic ability, sleep habits, and heart rate

[0406] Output: Unprocessed biometric data

[0407] Step 2:

[0408] The server preprocesses the collected biometric data. Specifically, it performs noise reduction (elimination of false values), filtering of outliers, and normalization of the data. For example, it removes or interpolates extremely high or low heart rate values.

[0409] Input: Unprocessed biometric data

[0410] Output: Preprocessed data

[0411] Step 3:

[0412] The server analyzes the user's health status using pre-processed data. Specifically, it analyzes data trends using regression analysis and clustering techniques to predict and evaluate health status.

[0413] Input: Preprocessed data

[0414] Output: Analysis results of health status

[0415] Step 4:

[0416] The server uses an emotion engine to analyze the user's emotional state. The emotion engine utilizes technologies such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect facial and audio data through the smartphone's camera and microphone.

[0417] Input: Facial and voice data collected from a smartphone.

[0418] Output: Emotional state evaluation results

[0419] Step 5:

[0420] The server combines the results of health status analysis and emotional state assessment to generate personalized health and fitness advice. It also suggests appropriate meal plans based on this advice.

[0421] Input: Analysis results of health status and evaluation results of emotional status

[0422] Output: Personalized health advice and meal plans

[0423] Step 6:

[0424] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed for ease of use and provides information quickly to the user through pop-up notifications and dashboard displays.

[0425] Input: Personalized health advice and meal plans

[0426] Output: Notification to smartphone app

[0427] Step 7:

[0428] Users can request customized exercise and meal plans from experts through a smartphone app. The request is sent to the expert via a server, and the provided plan is then notified to the user via the server.

[0429] Input: User request for customization plan

[0430] Output: Provision of customized plans by experts and notifications

[0431] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0432] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0433] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0434] [Second Embodiment]

[0435] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0436] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0437] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0438] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0439] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0440] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0441] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0442] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0443] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0444] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0445] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0446] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0447] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management.

[0448] System Configuration

[0449] Data collection

[0450] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. The wearable device sends this data to the server at regular intervals. For example, it can send step count, heart rate, and sleep data to the server every 30 minutes.

[0451] Data preprocessing

[0452] The server preprocesses the collected biometric data. For example, it performs noise reduction, filters outliers, and converts the data to the required format. Since raw data may contain missing values, it performs appropriate imputation. It also formats the data on a time-based basis and converts it to a format suitable for analysis.

[0453] Data analysis

[0454] The pre-processed data is used by the server to analyze the user's health status. Specifically, statistical methods such as regression analysis and clustering are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, based on heart rate data from the past 30 days, predictions for the next 30 days can be made.

[0455] Generating advice

[0456] Based on the analysis results, the server generates personalized health and fitness advice. For example, a user who has not exercised enough in the past 30 days can be given specific advice such as "We recommend increasing your daily walking time by 10 minutes." Similarly, a user with a high heart rate can be recommended breathing exercises to help them relax.

[0457] Notification to the user

[0458] The server notifies the user's device of the generated advice according to its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone app.

[0459] Providing a customized exercise plan

[0460] When a user requests a customized exercise plan from an expert through the app, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "30 minutes of strength training three times a week."

[0461] Specific example

[0462] After a user has worn a wearable device for a day, the device collects the following data:

[0463] Step count: 8000 steps

[0464] Average heart rate: 75 bpm

[0465] Sleep duration: 7 hours

[0466] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[0467] 8,000 steps is short of the target of 10,000 steps.

[0468] The average heart rate is within a moderate range.

[0469] My sleep duration falls within the recommended range of 7-8 hours.

[0470] Based on this analysis, the server generates the following advice:

[0471] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0472] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0473] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0474] The server sends this advice to the device, allowing the user to view the advice through a smartphone app.

[0475] Furthermore, when a user requests a customized exercise plan from an expert, the server sends the request to the expert and provides the user with the exercise plan designed by the expert, thereby supporting more specific health management and fitness achievement.

[0476] As described above, the present invention integrates data collection, preprocessing, analysis, advice generation, and notification from wearable devices to provide users with personalized health management and fitness support.

[0477] The following describes the processing flow.

[0478] Step 1:

[0479] The server collects data from wearable devices. Specifically, the server periodically communicates with wearable devices to obtain biometric data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might send an API request at 12:00 every day to collect data from the previous day.

[0480] Step 2:

[0481] The server preprocesses the collected biometric data. Specifically, it removes noise from the data and filters out outliers. Next, it normalizes the preprocessed data and converts it into a format suitable for analysis. For example, if step count data is missing, it is imputed with the mean value.

[0482] Step 3:

[0483] The server analyzes the pre-processed data. Specifically, it uses regression analysis and clustering to analyze the user's exercise capacity, sleep patterns, and heart rate in detail. For example, it uses data from the past 30 days to build a predictive model for the next 30 days.

[0484] Step 4:

[0485] The server generates personalized advice based on the analysis results. For example, if a user's step count hasn't reached their goal, it will make specific suggestions such as "increase your daily step count by 2000 steps." If the user's heart rate is high, it will suggest ways to relax.

[0486] Step 5:

[0487] The server notifies the user's device of the generated advice. Specifically, it creates a notification message and sends it via push notification or in-app messaging. For example, it can send real-time notifications using Firebase Cloud Messaging (FCM).

[0488] Step 6:

[0489] The device receives notifications from the server and displays advice through the user interface. For example, the notification bar of a smartphone app might display, "Your step count today is low. Let's walk another 2000 steps!"

[0490] Step 7:

[0491] Users can request a customized exercise plan from an expert through the app. For example, they can enter a specific request in a form, such as "I want to increase my strength training."

[0492] Step 8:

[0493] The server receives requests from users and forwards them to experts. The experts create customized exercise plans based on the requests and send them back to the server. For example, a "30-minute strength training plan, three times a week" might be created.

[0494] Step 9:

[0495] The server then notifies the user's device again of the customized exercise plan from the expert, and the user can view the detailed exercise plan through the app. For example, the new exercise plan will appear on the app's dashboard.

[0496] Through the processing steps described above, this system can manage users' health conditions in a highly personalized manner and provide effective fitness and health advice.

[0497] (Example 1)

[0498] Next, we will describe Example 1. 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".

[0499] With the recent rise in health awareness, many people are using wearable devices to monitor their health. However, the amount of data obtained from these devices is enormous, making it difficult for individual users to accurately interpret it and apply it to their daily lives. Furthermore, there is a need for systems that go beyond mere data collection, comprehensively analyze the user's health status, and provide personalized health advice. Conventional systems often lack sufficient data preprocessing and the provision of customized advice from experts, which prevents users from reaping the maximum benefit.

[0500] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0501] In this invention, the server includes means for collecting biometric data from a wearable device, means for preprocessing the biometric data, means for analyzing the user's health status using the preprocessed data, means for generating individualized health and exercise advice based on the analysis results, and means for notifying the user's device of the generated advice. This enables the user to receive personalized health advice based on data collected from the wearable device, thereby achieving more effective health management and fitness support.

[0502] A "wearable device" is a device that is attached to the user's body and measures and records biometric data such as exercise ability, heart rate, and sleep habits.

[0503] "Biometric data" refers to information about a user's physical condition and activity measured by wearable devices, and specifically includes heart rate, steps taken, sleep duration, etc.

[0504] "Preprocessing" refers to the process of converting biological data into a format that is easy to analyze, and specifically includes noise reduction, filtering of outliers, and imputation of missing values.

[0505] "Analysis" refers to calculations and methods used to evaluate and predict a user's health status using pre-processed data, specifically involving the use of statistical methods such as regression analysis and clustering.

[0506] "Advice generation" is the process of creating personalized health and exercise advice for users based on the analysis results.

[0507] "User's device" refers to an information terminal used by the user, including digital devices such as smartphones, tablets, and personal computers.

[0508] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management. This system operates with three components: a server, a terminal, and a user.

[0509] First, the server collects biometric data (e.g., heart rate, steps, sleep data, etc.) from the user's wearable device (e.g., a smartwatch worn on the user's wrist). This data is sent to the server at regular intervals (e.g., every 30 minutes). Specifically, the server uses a server computer with a high-performance CPU and sufficient memory.

[0510] Next, the server preprocesses the data. This preprocessing includes denoising the received data (e.g., removing abnormally high heart rates), filtering outliers, and imputing missing values. These processes are performed using data processing libraries such as Python's Pandas and NumPy.

[0511] The pre-processed data is used by the server to analyze the user's health status. Specifically, machine learning libraries such as scikit-learn are used to perform regression analysis and clustering to predict and analyze the user's exercise capacity, sleep patterns, and heart rate trends.

[0512] Based on the analysis results, the server generates personalized health and fitness advice. For example, it predicts the heart rate for the next 30 days based on heart rate data from the past 30 days and provides specific advice to users who are not getting enough exercise, such as "We recommend increasing your daily walking time by 10 minutes." It also recommends breathing exercises to help users with elevated heart rates relax.

[0513] The generated advice is sent from the server to the user's device (e.g., a smartphone or tablet). The device displays the received advice through a user interface. For example, the advice may be displayed as a pop-up notification or on a dashboard using a smartphone app.

[0514] Furthermore, if a user requests a customized exercise plan from an expert, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "perform 30 minutes of strength training three times a week."

[0515] Specific example

[0516] As an example for one day, suppose a user wears a wearable device while performing activities, and the following data is collected:

[0517] Step count: 8000 steps

[0518] Average heart rate: 75 bpm

[0519] Sleep duration: 7 hours

[0520] The server receives this data, performs noise reduction and outlier filtering using Pandas and NumPy, and then analyzes the data using scikit-learn. The analysis results yield the following insights:

[0521] 8,000 steps is short of the target of 10,000 steps.

[0522] The average heart rate is within a moderate range.

[0523] My sleep duration falls within the recommended range of 7-8 hours.

[0524] Based on this analysis, the server generates the following advice:

[0525] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0526] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0527] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0528] The server sends this advice to the user's smartphone, and the user can view this advice through the app.

[0529] Furthermore, when a user requests a customized exercise plan, the server forwards the request to an expert, who then provides the user with an exercise plan designed by the expert. For example, if a user requests a "30-minute, 3-session strength training plan per week from an expert," the expert designs the plan and sends it to the server, which then communicates it to the user.

[0530] In this way, the system enables consistent data collection, preprocessing, analysis, advice generation, notification, and customized plan delivery. Through this process, users can gain a deeper understanding of their own health status and receive effective health management and fitness support.

[0531] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0532] Step 1: Data Collection

[0533] The server collects biometric data from the user's wearable device. This device periodically (for example, every 30 minutes) records heart rate, steps, sleep data, etc., and transmits it to the server via Bluetooth or Wi-Fi. The input data is the biometric data obtained from the wearable device, and this becomes the output data at the time it is transmitted to the server.

[0534] Specific actions:

[0535] Wearable devices measure the user's biometric data.

[0536] The measurement data is sent to the server at regular intervals.

[0537] The server stores this data in the database.

[0538] Step 2: Data preprocessing

[0539] The server performs noise reduction, filters outliers, and imputes missing values ​​in the received biometric data. The input data is the biometric data collected in step 1, and the pre-processed data becomes the output data.

[0540] Specific actions:

[0541] Load the data using libraries such as Pandas or NumPy.

[0542] Noise reduction: For example, detecting and removing extremely high heart rates or abnormally low step counts.

[0543] Outlier filtering: Replace outliers with the median or mean of the data.

[0544] Imputing missing values: For example, missing values ​​can be imputed using the mean of the preceding and succeeding data.

[0545] Step 3: Data Analysis

[0546] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning models (regression analysis, clustering, etc.). The input data is pre-processed biometric data, and the analysis results become the output data.

[0547] Specific actions:

[0548] Load the analysis model using the scikit-learn library.

[0549] Regression analysis is performed to predict future heart rate and step count based on past data.

[0550] Clustering is used to classify users' sleep patterns and athletic abilities.

[0551] As a result, analyzed health status data is generated.

[0552] Step 4: Generating advice

[0553] The server generates personalized fitness and health advice based on the analysis results. The input data is the analysis results obtained in step 3, and the generated advice becomes the output data.

[0554] Specific actions:

[0555] Based on the analysis results, a prompt message is created that generates appropriate advice using a generative AI model.

[0556] For example, it can automatically generate specific advice such as, "Your heart rate is a little high. Please do some breathing exercises to relax."

[0557] Output the advice in text format.

[0558] Step 5: Notify the user

[0559] The server sends the generated advice to the user's terminal. The input data is the generated advice, and the output data is the notification of this advice sent to the user's terminal.

[0560] Specific actions:

[0561] Once the advice is generated, the server identifies the corresponding user's terminal.

[0562] Advice will be sent as a push notification to the user's smartphone or other device.

[0563] The user's device displays the received advice, allowing the user to review it.

[0564] Step 6: Providing a customized exercise plan

[0565] When a user requests a customized exercise plan through the app, the server forwards the request to a specialist. The input data is the user's request, and the output data is the customized exercise plan provided to the user.

[0566] Specific actions:

[0567] The user submits a request through the application.

[0568] The server forwards this request to an expert.

[0569] Experts create exercise plans based on user data.

[0570] Once the exercise plan is complete, it is sent to the user via the server.

[0571] Users can view their customized exercise plan through the application.

[0572] (Application Example 1)

[0573] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0574] Current fitness and health management systems collect and analyze individual user data to provide advice, but these are primarily limited to personal use. However, providing immediate, personalized advice to customers in physical stores can offer even greater support for health management and fitness. Systems that enable this kind of immediate advice in physical stores are still lacking, and realizing immediate fitness instruction and health management support for customers within physical stores remains a challenge.

[0575] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0576] In this invention, the server includes means for collecting data on exercise capacity, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results; means for notifying the user's terminal of the generated advice; and means for understanding the individual health status of customers in a physical store and providing fitness-related advice immediately. This makes it possible to provide customers with immediate, personalized health management and fitness advice in a physical store.

[0577] A "wearable device" is an electronic device that is attached to a user's body to collect biometric data such as athletic ability, sleep habits, and heart rate.

[0578] "Exercise capacity" refers to data that indicates the quantity and quality of exercise, such as the user's step count, calories burned, and exercise intensity.

[0579] "Sleep habits" refers to data that shows the user's sleep-related behaviors and patterns, such as sleep duration, sleep quality, time to fall asleep, and time to wake up.

[0580] "Heart rate" is data that indicates the number of heartbeats per minute and is an indicator of the user's cardiac activity.

[0581] "Preprocessing" is the process of converting collected biological data into a format suitable for analysis by performing noise reduction, filtering outliers, and imputing missing values.

[0582] "Health status" refers to the overall health condition of the user, based on data such as their exercise capacity, sleep habits, and heart rate.

[0583] "Analysis" is the process of evaluating and predicting a user's health status using statistical methods and machine learning techniques based on pre-processed data.

[0584] "Personalized advice" refers to providing specific health management and fitness guidance and recommendations tailored to individual users, based on analysis results.

[0585] "Notification" refers to the act of sending generated advice or information to a user's device to inform the user.

[0586] A "physical store" is a place that provides fitness instruction and health management services, and is a physical facility that customers can visit in person.

[0587] "Providing information instantly" means collecting and analyzing user data in real time and providing advice to customers immediately based on the results.

[0588] A "customized exercise plan by an expert" is an individualized exercise program designed by a fitness professional with specialized knowledge, based on the user's specific requests.

[0589] "Regression analysis" is a statistical method used to predict a user's future health status based on past data.

[0590] Clustering is a machine learning technique used to classify user data into groups with similar characteristics.

[0591] System Configuration

[0592] This invention is a system that utilizes data collected from wearable devices to provide customers with immediate fitness advice and health management in physical stores. The specific system configuration and operation are described below.

[0593] Data collection

[0594] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices worn by the user. The wearable device transmits this data to the server at regular intervals. Examples include smartwatches and smart bands.

[0595] Data preprocessing

[0596] The server preprocesses the collected biometric data. Specifically, it uses data processing libraries such as Pandas and NumPy to remove noise, filter outliers, and impute missing values, converting the data into a format suitable for analysis. For example, if data is missing, it is imputed with the mean value.

[0597] Data analysis

[0598] The pre-processed data is used by the server to analyze the user's health status. The methods used include machine learning techniques such as regression analysis and clustering. Libraries such as Scikit-learn are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends.

[0599] Generating advice

[0600] Based on the analysis results, the server generates personalized health and fitness advice. For example, if a user's step count is insufficient based on past data, it will generate advice such as, "Try to walk more to reach your step goal." If the heart rate is within a healthy range, it will generate a message such as, "Continue managing your health at this pace."

[0601] Notification to the user

[0602] The generated advice is sent to the user's device as a notification, depending on its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone application.

[0603] In-store, immediate fitness instruction

[0604] In physical stores, servers monitor each customer's health status and provide immediate fitness-related advice. Store staff can use the customer's device to view and provide personalized advice based on real-time health data. This enables more effective fitness instruction and health management.

[0605] Specific example

[0606] After a user has worn a wearable device for a day, the device collects the following data:

[0607] Step count: 8000 steps

[0608] Average heart rate: 75 bpm

[0609] Sleep duration: 7 hours

[0610] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[0611] 8,000 steps is short of the target of 10,000 steps.

[0612] The average heart rate is within a moderate range.

[0613] My sleep duration falls within the recommended range of 7-8 hours.

[0614] Based on this analysis, the server generates the following advice:

[0615] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0616] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0617] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0618] The server sends this advice to the user's device, allowing the user to view the advice through a smartphone application.

[0619] Example of a prompt

[0620] Please generate personalized fitness and health advice based on the following data.

[0621] Data format:

[0622] {

[0623] "steps":

[8000] ,

[0624] "heart_rate":

[75] ,

[0625] "sleep_hours": [7]

[0626] }

[0627] Based on the analysis results, please generate advice using the following criteria:

[0628] 1. If your step count is less than 10,000 steps, you are advised to increase your step count to reach your goal.

[0629] 2. If the heart rate is within the range of 60-100 bpm, a notification will be issued indicating that it is normal.

[0630] 3. If your sleep duration is between 7 and 8 hours, it is recommended that you maintain good sleep habits.

[0631] This will now describe the specific form for carrying out the invention.

[0632] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0633] Step 1:

[0634] The server collects biometric data related to exercise capacity, sleep habits, and heart rate from wearable devices worn by the user at regular intervals. It receives biometric data transmitted from the wearable device as input and stores it in a database. Specifically, for example, a smartwatch sends the user's step count, average heart rate, and sleep data to the server every 30 minutes.

[0635] Step 2:

[0636] The server preprocesses the collected biometric data. It takes biometric data stored in a database as input, performs noise reduction, filters outliers, and imputes missing values. Specifically, it uses Pandas and NumPy to clean the data and convert it into a format suitable for analysis. This results in formatted data being output.

[0637] Step 3:

[0638] The server analyzes the user's health status using pre-processed data. It takes pre-processed data as input and performs regression analysis and clustering using machine learning libraries such as Scikit-learn. Specifically, it uses regression analysis to predict the next 30 days based on heart rate data from the past 30 days, and clustering to classify users into groups according to their health status. The analysis results are then output.

[0639] Step 4:

[0640] The server generates personalized health and fitness advice based on the analysis results. It takes the analysis results as input and creates advice tailored to the user's specific data. For example, it might generate advice such as "Try to walk a little more" for a user whose step count hasn't reached their goal, or "Continue managing your health at this pace" for a user whose heart rate is within the normal range. This results in personalized advice being output.

[0641] Step 5:

[0642] The server notifies the user's device of the generated advice. It retrieves the generated advice as input and sends it to the user's smartphone or tablet. The device displays the received advice message and informs the user. Specifically, the smartphone application displays the advice content as a pop-up notification or on the dashboard. This allows the user to receive feedback in real time.

[0643] Step 6:

[0644] The server analyzes user data in real time and notifies store staff to provide immediate fitness-related advice within the physical store. It uses data collected in real time as input, performs analysis and generates advice, and notifies store staff terminals. This allows store staff to understand each customer's individual health status and provide immediate, specific fitness guidance and health management.

[0645] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0646] The present invention is a system that provides personalized health and fitness advice by combining data collected from a wearable device with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[0647] System Configuration

[0648] Data collection

[0649] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. For example, data is sent from the wearable device to the server at regular intervals each day. This data includes the total number of steps taken per day, average heart rate, and sleep duration.

[0650] Data preprocessing

[0651] The server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[0652] Data analysis

[0653] The server analyzes the user's health status based on pre-processed data. Using regression analysis and clustering techniques, it analyzes and predicts the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts the amount of exercise for the next 30 days based on exercise data from the past 30 days and identifies areas for improvement.

[0654] Implementation of an emotion engine

[0655] The server also features an emotion engine. This emotion engine recognizes the user's emotions using voice, facial expressions, and text data. For example, it uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and uses an emotion recognition algorithm to identify the user's current emotional state.

[0656] Generating advice

[0657] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will recommend relaxation exercises. Also, if the server detects that the user is agitated on a day with a high heart rate, it will provide advice to adjust the amount of exercise.

[0658] Notification to the user

[0659] The server notifies the user's device of the advice it has generated. The device analyzes the advice message received from the server and displays it through the user interface. For example, a smartphone app can display pop-up notifications or a dashboard to allow the user to quickly check the advice.

[0660] Providing a customized exercise plan

[0661] Users can request a customized exercise plan from an expert through the app. They enter their specific request details into a form and submit it to the server. The server forwards this request to an expert, who designs a customized exercise plan based on the user's request. This exercise plan is then provided to the user again via the server. For example, the plan might include specific details such as "perform 30 minutes of aerobic exercise three times a week."

[0662] Specific example

[0663] Data Acquisition and Preprocessing

[0664] The server collects the following data from the user's wearable device:

[0665] Step count: 8000 steps

[0666] Average heart rate: 75 bpm

[0667] Sleep duration: 7 hours

[0668] Data Analysis

[0669] The server analyzes the pre-processed data and obtains the following conclusions:

[0670] The number of steps taken has not reached the target of 10,000 steps.

[0671] The average heart rate is within a moderate range.

[0672] Sleep duration is within the recommended range of 7-8 hours.

[0673] emotion recognition

[0674] The emotion engine uses the smartphone's camera and microphone to analyze the user's facial expressions and voice, recognizing when the user is experiencing stress.

[0675] Generating advice

[0676] The server considers both health and emotional state to generate the following advice:

[0677] "Your step count today is 8,000 steps, which is short of your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[0678] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0679] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0680] Advice notification

[0681] The server sends the generated advice to the device, and the user can check the advice through a smartphone app.

[0682] Customized exercise plan

[0683] When a user requests a customized exercise plan from an expert, the server forwards the request to the expert, who then provides the user with the designed exercise plan. For example, a specific plan such as "a 30-minute strength training session three times a week" might be provided.

[0684] As described above, the present invention is a system that combines data obtained from a wearable device with the user's emotions to provide more highly personalized health management and fitness support.

[0685] The following describes the processing flow.

[0686] Step 1:

[0687] The server collects data from wearable devices. Specifically, the server uses the device API to periodically send data retrieval requests to obtain vital data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might be configured to collect the previous day's data at midnight every day.

[0688] Step 2:

[0689] The server preprocesses the collected data. First, it denoises the data, filtering out, for example, extremely high step counts or abnormal heart rates. Next, it normalizes the data to ensure consistency as time-series data. For example, it imputes missing data with the mean.

[0690] Step 3:

[0691] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning algorithms (regression analysis and clustering) to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, it applies an algorithm that predicts the amount of exercise for the next 30 days based on data from the past 30 days and proposes an appropriate exercise plan.

[0692] Step 4:

[0693] The server recognizes the user's emotions through an emotion engine. The emotion engine uses the smartphone's camera and microphone to collect the user's facial and voice data and analyze their emotions. For example, when the user opens the app, the camera captures their facial expression and the voice response is obtained.

[0694] Step 5:

[0695] The server integrates health status analysis results with emotional data recognized by the emotion engine to generate personalized health and fitness advice. For example, if a user is not getting enough exercise and is feeling stressed, it will generate advice recommending "taking a light walk to relax."

[0696] Step 6:

[0697] The server then notifies the user's device of the advice it has generated. Specifically, it generates a notification message and sends a push notification to the user's smartphone app using Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNs). For example, it might send a message such as, "Your exercise level today did not meet your goal. We recommend a light, relaxing walk."

[0698] Step 7:

[0699] The device analyzes advice messages received from the server and displays them in the user interface. Specifically, it displays them as pop-up messages in the smartphone's notification bar or shows detailed advice in the in-app dashboard. For example, it might display specific suggestions such as "Today's activity level: 8,000 steps / 10,000 steps" and "Perform relaxation exercises."

[0700] Step 8:

[0701] Users can request a customized exercise plan from an expert through the app. For example, they can enter "I want to increase my strength training" into the request form within the app and press the submit button.

[0702] Step 9:

[0703] The server receives the user's request and forwards it to an expert. The expert customizes the exercise plan based on the request. For example, they might create a program recommending "30 minutes of strength training three times a week."

[0704] Step 10:

[0705] The server then notifies the user's device again of the customized exercise plan received from the expert. The user can then view the new exercise plan through a smartphone app. For example, the app's dashboard might display a "Strength Training Plan" with specific exercises to be done three times a week.

[0706] In this way, this system, which incorporates an emotion engine, provides more personalized health and fitness support based on multifaceted data analysis that includes the user's emotional state.

[0707] (Example 2)

[0708] Next, we will describe Example 2. 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".

[0709] Traditional health and fitness management systems can collect users' biometric data and assess their basic health status, but they have limitations in generating personalized advice. Furthermore, advice provided without considering the user's emotional state is less effective. Additionally, users must manually request customized exercise plans from professionals, which is time-consuming and inconvenient. There is a need to address these challenges and provide more detailed and personalized health and fitness support.

[0710] The identification processing 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 means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results and emotion recognition; and means for notifying the user's terminal of the generated advice and customized exercise plan. This enables the user to receive more detailed and personalized advice that comprehensively considers their health status and emotional state. Furthermore, the request and provision of customized exercise plans by experts are automated, reducing the burden on the user.

[0711] A "wearable device" is a device that is worn on a user's body to collect biometric data. Examples include smartwatches and fitness trackers.

[0712] "Physical ability" refers to data that indicates the user's physical activity performance. Specifically, it includes steps taken, distance traveled, calories burned, and so on.

[0713] "Sleep habits" refers to data that shows a user's sleep patterns and sleep quality. Specifically, it includes sleep duration, percentage of deep sleep, and number of sleep interruptions.

[0714] "Heart rate" is data that indicates the number of times a user's heart beats. It is usually expressed as heart rate per minute (bpm).

[0715] "Preprocessing" refers to data processing to convert collected biological data into an analyzable format. Specifically, this includes noise reduction, outlier filtering, and data normalization.

[0716] "Health status" refers to data that indicates the user's overall physical condition and level of health. This is comprehensively evaluated from multiple data points, such as exercise capacity, sleep habits, and heart rate.

[0717] "Emotion recognition" is a technology that identifies a user's emotional state using voice, facial expression, and text data. Specifically, it collects data using a smartphone's camera and microphone and analyzes it using algorithms.

[0718] "Personalized health and fitness advice" refers to specific, tailored guidance and recommendations provided to each individual, taking into account their health and emotional state.

[0719] A "device" is an electronic device that a user can operate. Examples include smartphones, tablets, and personal computers.

[0720] A "customized exercise plan" is an exercise plan designed based on the user's specific needs and goals. It is created by a specialist in response to the user's request.

[0721] A "specialist" is someone who possesses knowledge and experience regarding the user's health and fitness. Examples include trainers and nutritionists.

[0722] "Notifications" refer to the act of delivering generated advice or customized exercise plans to the user's device. Specifically, this includes pop-up notifications and dashboard displays.

[0723] Modes for carrying out the invention

[0724] This invention is a system that provides personalized health and fitness advice by combining data collected from wearable devices with an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[0725] Data collection

[0726] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices (e.g., smartwatches, fitness trackers). The collection process involves the wearable device sending data to the server at regular intervals each day. For example, at 6 AM every morning, a day's worth of data (steps, average heart rate, sleep duration, etc.) is collected.

[0727] Data preprocessing

[0728] The server preprocesses the collected data. This process includes noise reduction, outlier filtering, and data normalization. For example, it removes or interpolates data points where the average heart rate is extremely high (above 150 bpm) or low (below 40 bpm).

[0729] Data analysis

[0730] The server analyzes the pre-processed data. The analysis steps include predicting health status using regression analysis and clustering techniques, and analyzing trends in exercise capacity, sleep patterns, and heart rate. For example, based on exercise data from the past 30 days, it sets exercise goals for the next 30 days and identifies areas for improvement.

[0731] Implementation of an emotion engine

[0732] The server uses an emotion engine to recognize the user's emotions based on voice, facial expressions, and text data. The emotion engine uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and analyzes them with an emotion recognition algorithm. For example, while the user is using their smartphone, the camera captures their facial expressions and audio data is collected to determine whether the user is experiencing stress.

[0733] Generating advice

[0734] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it recommends relaxation exercises, and if a lack of exercise is detected, it suggests a light jog. Specific advice might include messages such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so we recommend a light walk."

[0735] Advice notification

[0736] The server notifies the user's device of the generated advice. The device analyzes the received advice message and displays it through the user interface. For example, a smartphone app might display a pop-up notification so that the user can quickly check the advice.

[0737] Customized exercise plan

[0738] Users can request a customized exercise plan from an expert through the app. They enter their request details into a form and submit it to the server. This information is forwarded to the expert, who designs an exercise plan tailored to the user's specific needs. The designed exercise plan is then provided to the user again via the server. For example, a specific plan such as "30-minute strength training sessions three times a week" might be provided.

[0739] Specific examples and prompt statements

[0740] Specific example

[0741] Data Collection: The server collects a day's worth of data from wearable devices every morning at 6:00 AM (steps: 8,000, average heart rate: 75 bpm, sleep time: 7 hours).

[0742] Data preprocessing: The server removes outliers where the heart rate exceeds 150 bpm.

[0743] Data analysis: Set exercise goals for the next 30 days based on exercise data from the past 30 days.

[0744] Emotion recognition: The system uses the smartphone's camera to recognize when the user is experiencing stress.

[0745] Advice generation: Generates the advice: "Your step count today is 8000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[0746] Advice Notification: The server sends the generated advice to the user's smartphone and displays it as a pop-up notification.

[0747] Customized Exercise Plan: Users request a "30-minute strength training plan, 3 times a week," and experts design and provide it.

[0748] Examples of prompt statements

[0749] "Create a program that recognizes the user's emotions and provides health advice based on them. For example, include a feature that recommends relaxation exercises if the user is feeling stressed."

[0750] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0751] Step 1: Data Collection

[0752] The server collects biometric data from the user's wearable device.

[0753] Input: Exercise capacity, sleep habits, and heart rate data transmitted from wearable devices.

[0754] Specific operation: For example, request and receive a day's worth of data (steps, average heart rate, sleep duration) from a Fitbit or smartwatch at 6 AM every morning.

[0755] Output: Collected biometric data (e.g., total daily steps 8000, average heart rate 75 bpm, sleep duration 7 hours).

[0756] Step 2: Data preprocessing

[0757] The server preprocesses the collected data.

[0758] Input: Collected biometric data.

[0759] Specific operations: Noise reduction, outlier filtering, and data normalization. For example, it detects and removes outliers such as an average heart rate exceeding 150 bpm. It also imputes missing data points.

[0760] Output: Preprocessed data.

[0761] Step 3: Data Analysis

[0762] The server analyzes the pre-processed data.

[0763] Input: Pre-processed data.

[0764] Specific actions: Using regression analysis and clustering techniques, the system analyzes the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts exercise levels for the next 30 days using data from the past 30 days.

[0765] Output: Analysis results and health status prediction.

[0766] Step 4: Emotion Recognition

[0767] The server uses an emotion engine to recognize the user's emotions.

[0768] Input: Voice, facial expressions, and text data collected from the smartphone's camera and microphone.

[0769] Specific operation: The smartphone camera is activated, and the user's facial expression and voice data are collected in real time and analyzed using an emotion recognition algorithm. For example, it can determine whether the user is experiencing stress.

[0770] Output: User's emotional state (e.g., stress).

[0771] Step 5: Generating Advice

[0772] The server generates personalized advice based on the analysis of health status and the recognition of emotions.

[0773] Input: Analysis results and emotional state.

[0774] Specific actions: For example, create advice such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[0775] Output: Generated advice message.

[0776] Step 6: Advice Notification

[0777] The server notifies the user's terminal of the generated advice.

[0778] Input: Generated advice message.

[0779] Specific actions: Send an advice message to the device and display it to the user through a pop-up notification or dashboard display. For example, display a notification via a smartphone app.

[0780] Output: Advice displayed to the user.

[0781] Step 7: Customized Exercise Plan

[0782] Users can request a customized exercise plan from an expert through the app.

[0783] Input: User request information (specific needs and goals).

[0784] Specific operation: Enter information into the request form within the app and send it to the server. The server forwards the request to an expert, who designs an exercise plan based on the user's needs. For example, a "30-minute strength training plan three times a week" might be created.

[0785] Output: A customized exercise plan is provided to the user.

[0786] (Application Example 2)

[0787] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0788] Traditional health management systems primarily focused on collecting and analyzing biometric data such as users' exercise capacity, sleep habits, and heart rate to provide fitness advice. However, they lacked personalization because they did not take into account the user's emotional state. Furthermore, they lacked suggestions for suitable meal plans in addition to health management. As a result, comprehensive health management and improvements in fitness and dietary habits were difficult.

[0789] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health and emotional state using the preprocessed data; means for generating personalized health and fitness advice based on the analyzed data; and means for notifying the user's terminal of the generated advice and suggesting meal menus based on the progress. This enables comprehensive health management that takes into account both the user's health and emotional state, and meal suggestions that are appropriate to the user's health state.

[0790] A "wearable device" is an electronic device that an individual can wear to collect biometric data such as athletic ability, sleep habits, and heart rate.

[0791] "Emotional state" refers to data that indicates the emotions and psychological state a user is experiencing at a specific time.

[0792] "Preprocessing" refers to the process of applying noise reduction, filtering outliers, and normalizing data to biometric data collected from wearable devices.

[0793] "Health status" refers to data that indicates the user's physical and physiological condition, including exercise capacity, sleep patterns, and heart rate.

[0794] "Fitness advice" refers to specific suggestions and guidance regarding exercise, diet, and rest to improve the user's health.

[0795] The "meal menu" is a list that suggests balanced meals based on the user's health and emotional state.

[0796] "Progress" refers to data that shows changes and progress in the user's health status.

[0797] A "customized exercise plan by an expert" is an exercise plan designed by an expert based on the individual user's health condition and goals.

[0798] Regression analysis is a statistical method that models the relationships between numerical data and is used to predict specific health conditions.

[0799] Clustering is a data analysis technique that groups data based on similarity and is used to identify user health patterns.

[0800] A "prompt sentence" is text input into a generative AI model that contains instructions for generating specific information or answers.

[0801] This invention is a system that analyzes data collected from a wearable device and the user's emotional state to provide personalized health and fitness advice and meal menus. Specific embodiments of this system are described in detail below.

[0802] First, the server collects data on exercise capacity, sleep habits, and heart rate from wearable devices. Wearable devices such as Apple Watch, Fitbit, and Garmin can be used. The data collected from these devices is sent to the server at regular intervals.

[0803] Next, the server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[0804] Based on the pre-processed data, the server analyzes the user's health and emotional state. The emotional state is analyzed using an emotion engine. This emotion engine uses tools such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect the user's facial expressions and voice data through the smartphone's camera and microphone.

[0805] The server then generates personalized health and fitness advice based on the analysis results. It also suggests appropriate meal plans, taking into account the user's health and emotional state. For example, if data from a wearable device indicates that the user's heart rate is low and that calorie intake is needed, the server will suggest a meal plan suitable for energy replenishment.

[0806] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed to be intuitive and easy to use, allowing users to quickly check the advice and meal menus through pop-up notifications and dashboard displays.

[0807] As a concrete example, a notification using the following prompt statement can be considered:

[0808] "Based on your health and mood today, here are our recommended dishes: a healthy salad and lean grilled chicken. Would you like to order?"

[0809] Furthermore, users can request customized exercise and meal plans from experts through the app. These requests are sent to experts via the server, and the plans provided by the experts are then notified to the user via the server.

[0810] As described above, the system of the present invention provides comprehensive health management that takes into account both the user's physical and emotional state, as well as personalized fitness and dietary suggestions.

[0811] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0812] Step 1:

[0813] The server collects biometric data from wearable devices regarding exercise capacity, sleep habits, and heart rate. Specifically, data is sent from devices such as Apple Watch, Fitbit, and Garmin at regular intervals.

[0814] Input: Biometric data related to athletic ability, sleep habits, and heart rate

[0815] Output: Unprocessed biometric data

[0816] Step 2:

[0817] The server preprocesses the collected biometric data. Specifically, it performs noise reduction (elimination of false values), filtering of outliers, and normalization of the data. For example, it removes or interpolates extremely high or low heart rate values.

[0818] Input: Unprocessed biometric data

[0819] Output: Preprocessed data

[0820] Step 3:

[0821] The server analyzes the user's health status using pre-processed data. Specifically, it analyzes data trends using regression analysis and clustering techniques to predict and evaluate health status.

[0822] Input: Preprocessed data

[0823] Output: Analysis results of health status

[0824] Step 4:

[0825] The server uses an emotion engine to analyze the user's emotional state. The emotion engine utilizes technologies such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect facial and audio data through the smartphone's camera and microphone.

[0826] Input: Facial and voice data collected from a smartphone.

[0827] Output: Emotional state evaluation results

[0828] Step 5:

[0829] The server combines the results of health status analysis and emotional state assessment to generate personalized health and fitness advice. It also suggests appropriate meal plans based on this advice.

[0830] Input: Analysis results of health status and evaluation results of emotional status

[0831] Output: Personalized health advice and meal plans

[0832] Step 6:

[0833] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed for ease of use and provides information quickly to the user through pop-up notifications and dashboard displays.

[0834] Input: Personalized health advice and meal plans

[0835] Output: Notification to smartphone app

[0836] Step 7:

[0837] Users can request customized exercise and meal plans from experts through a smartphone app. The request is sent to the expert via a server, and the provided plan is then notified to the user via the server.

[0838] Input: User request for customization plan

[0839] Output: Provision of customized plans by experts and notifications

[0840] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0841] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0842] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0843] [Third Embodiment]

[0844] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0845] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0846] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0847] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0848] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0849] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0850] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0851] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0852] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0853] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0854] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0855] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0856] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management.

[0857] System Configuration

[0858] Data collection

[0859] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. The wearable device sends this data to the server at regular intervals. For example, it can send step count, heart rate, and sleep data to the server every 30 minutes.

[0860] Data preprocessing

[0861] The server preprocesses the collected biometric data. For example, it performs noise reduction, filters outliers, and converts the data to the required format. Since raw data may contain missing values, it performs appropriate imputation. It also formats the data on a time-based basis and converts it to a format suitable for analysis.

[0862] Data analysis

[0863] The pre-processed data is used by the server to analyze the user's health status. Specifically, statistical methods such as regression analysis and clustering are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, based on heart rate data from the past 30 days, predictions for the next 30 days can be made.

[0864] Generating advice

[0865] Based on the analysis results, the server generates personalized health and fitness advice. For example, a user who has not exercised enough in the past 30 days can be given specific advice such as "We recommend increasing your daily walking time by 10 minutes." Similarly, a user with a high heart rate can be recommended breathing exercises to help them relax.

[0866] Notification to the user

[0867] The server notifies the user's device of the generated advice according to its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone app.

[0868] Providing a customized exercise plan

[0869] When a user requests a customized exercise plan from an expert through the app, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "30 minutes of strength training three times a week."

[0870] Specific example

[0871] After a user has worn a wearable device for a day, the device collects the following data:

[0872] Step count: 8000 steps

[0873] Average heart rate: 75 bpm

[0874] Sleep duration: 7 hours

[0875] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[0876] 8,000 steps is short of the target of 10,000 steps.

[0877] The average heart rate is within a moderate range.

[0878] My sleep duration falls within the recommended range of 7-8 hours.

[0879] Based on this analysis, the server generates the following advice:

[0880] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0881] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0882] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0883] The server sends this advice to the device, allowing the user to view the advice through a smartphone app.

[0884] Furthermore, when a user requests a customized exercise plan from an expert, the server sends the request to the expert and provides the user with the exercise plan designed by the expert, thereby supporting more specific health management and fitness achievement.

[0885] As described above, the present invention integrates data collection, preprocessing, analysis, advice generation, and notification from wearable devices to provide users with personalized health management and fitness support.

[0886] The following describes the processing flow.

[0887] Step 1:

[0888] The server collects data from wearable devices. Specifically, the server periodically communicates with wearable devices to obtain biometric data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might send an API request at 12:00 every day to collect data from the previous day.

[0889] Step 2:

[0890] The server preprocesses the collected biometric data. Specifically, it removes noise from the data and filters out outliers. Next, it normalizes the preprocessed data and converts it into a format suitable for analysis. For example, if step count data is missing, it is imputed with the mean value.

[0891] Step 3:

[0892] The server analyzes the pre-processed data. Specifically, it uses regression analysis and clustering to analyze the user's exercise capacity, sleep patterns, and heart rate in detail. For example, it uses data from the past 30 days to build a predictive model for the next 30 days.

[0893] Step 4:

[0894] The server generates personalized advice based on the analysis results. For example, if a user's step count hasn't reached their goal, it will make specific suggestions such as "increase your daily step count by 2000 steps." If the user's heart rate is high, it will suggest ways to relax.

[0895] Step 5:

[0896] The server notifies the user's device of the generated advice. Specifically, it creates a notification message and sends it via push notification or in-app messaging. For example, it can send real-time notifications using Firebase Cloud Messaging (FCM).

[0897] Step 6:

[0898] The device receives notifications from the server and displays advice through the user interface. For example, the notification bar of a smartphone app might display, "Your step count today is low. Let's walk another 2000 steps!"

[0899] Step 7:

[0900] Users can request a customized exercise plan from an expert through the app. For example, they can enter a specific request in a form, such as "I want to increase my strength training."

[0901] Step 8:

[0902] The server receives requests from users and forwards them to experts. The experts create customized exercise plans based on the requests and send them back to the server. For example, a "30-minute strength training plan, three times a week" might be created.

[0903] Step 9:

[0904] The server then notifies the user's device again of the customized exercise plan from the expert, and the user can view the detailed exercise plan through the app. For example, the new exercise plan will appear on the app's dashboard.

[0905] Through the processing steps described above, this system can manage users' health conditions in a highly personalized manner and provide effective fitness and health advice.

[0906] (Example 1)

[0907] Next, we will describe Example 1. 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."

[0908] With the recent rise in health awareness, many people are using wearable devices to monitor their health. However, the amount of data obtained from these devices is enormous, making it difficult for individual users to accurately interpret it and apply it to their daily lives. Furthermore, there is a need for systems that go beyond mere data collection, comprehensively analyze the user's health status, and provide personalized health advice. Conventional systems often lack sufficient data preprocessing and the provision of customized advice from experts, which prevents users from reaping the maximum benefit.

[0909] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0910] In this invention, the server includes means for collecting biometric data from a wearable device, means for preprocessing the biometric data, means for analyzing the user's health status using the preprocessed data, means for generating individualized health and exercise advice based on the analysis results, and means for notifying the user's device of the generated advice. This enables the user to receive personalized health advice based on data collected from the wearable device, thereby achieving more effective health management and fitness support.

[0911] A "wearable device" is a device that is attached to the user's body and measures and records biometric data such as exercise ability, heart rate, and sleep habits.

[0912] "Biometric data" refers to information about a user's physical condition and activity measured by wearable devices, and specifically includes heart rate, steps taken, sleep duration, etc.

[0913] "Preprocessing" refers to the process of converting biological data into a format that is easy to analyze, and specifically includes noise reduction, filtering of outliers, and imputation of missing values.

[0914] "Analysis" refers to calculations and methods used to evaluate and predict a user's health status using pre-processed data, specifically involving the use of statistical methods such as regression analysis and clustering.

[0915] "Advice generation" is the process of creating personalized health and exercise advice for users based on the analysis results.

[0916] "User's device" refers to an information terminal used by the user, including digital devices such as smartphones, tablets, and personal computers.

[0917] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management. This system operates with three components: a server, a terminal, and a user.

[0918] First, the server collects biometric data (e.g., heart rate, steps, sleep data, etc.) from the user's wearable device (e.g., a smartwatch worn on the user's wrist). This data is sent to the server at regular intervals (e.g., every 30 minutes). Specifically, the server uses a server computer with a high-performance CPU and sufficient memory.

[0919] Next, the server preprocesses the data. This preprocessing includes denoising the received data (e.g., removing abnormally high heart rates), filtering outliers, and imputing missing values. These processes are performed using data processing libraries such as Python's Pandas and NumPy.

[0920] The pre-processed data is used by the server to analyze the user's health status. Specifically, machine learning libraries such as scikit-learn are used to perform regression analysis and clustering to predict and analyze the user's exercise capacity, sleep patterns, and heart rate trends.

[0921] Based on the analysis results, the server generates personalized health and fitness advice. For example, it predicts the heart rate for the next 30 days based on heart rate data from the past 30 days and provides specific advice to users who are not getting enough exercise, such as "We recommend increasing your daily walking time by 10 minutes." It also recommends breathing exercises to help users with elevated heart rates relax.

[0922] The generated advice is sent from the server to the user's device (e.g., a smartphone or tablet). The device displays the received advice through a user interface. For example, the advice may be displayed as a pop-up notification or on a dashboard using a smartphone app.

[0923] Furthermore, if a user requests a customized exercise plan from an expert, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "perform 30 minutes of strength training three times a week."

[0924] Specific example

[0925] As an example for one day, suppose a user wears a wearable device while performing activities, and the following data is collected:

[0926] Step count: 8000 steps

[0927] Average heart rate: 75 bpm

[0928] Sleep duration: 7 hours

[0929] The server receives this data, performs noise reduction and outlier filtering using Pandas and NumPy, and then analyzes the data using scikit-learn. The analysis results yield the following insights:

[0930] 8,000 steps is short of the target of 10,000 steps.

[0931] The average heart rate is within a moderate range.

[0932] My sleep duration falls within the recommended range of 7-8 hours.

[0933] Based on this analysis, the server generates the following advice:

[0934] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[0935] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[0936] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[0937] The server sends this advice to the user's smartphone, and the user can view this advice through the app.

[0938] Furthermore, when a user requests a customized exercise plan, the server forwards the request to an expert, who then provides the user with an exercise plan designed by the expert. For example, if a user requests a "30-minute, 3-session strength training plan per week from an expert," the expert designs the plan and sends it to the server, which then communicates it to the user.

[0939] In this way, the system enables consistent data collection, preprocessing, analysis, advice generation, notification, and customized plan delivery. Through this process, users can gain a deeper understanding of their own health status and receive effective health management and fitness support.

[0940] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0941] Step 1: Data Collection

[0942] The server collects biometric data from the user's wearable device. This device periodically (for example, every 30 minutes) records heart rate, steps, sleep data, etc., and transmits it to the server via Bluetooth or Wi-Fi. The input data is the biometric data obtained from the wearable device, and this becomes the output data at the time it is transmitted to the server.

[0943] Specific actions:

[0944] Wearable devices measure the user's biometric data.

[0945] The measurement data is sent to the server at regular intervals.

[0946] The server stores this data in the database.

[0947] Step 2: Data preprocessing

[0948] The server performs noise reduction, filters outliers, and imputes missing values ​​in the received biometric data. The input data is the biometric data collected in step 1, and the pre-processed data becomes the output data.

[0949] Specific actions:

[0950] Load the data using libraries such as Pandas or NumPy.

[0951] Noise reduction: For example, detecting and removing extremely high heart rates or abnormally low step counts.

[0952] Outlier filtering: Replace outliers with the median or mean of the data.

[0953] Imputing missing values: For example, missing values ​​can be imputed using the mean of the preceding and succeeding data.

[0954] Step 3: Data Analysis

[0955] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning models (regression analysis, clustering, etc.). The input data is pre-processed biometric data, and the analysis results become the output data.

[0956] Specific actions:

[0957] Load the analysis model using the scikit-learn library.

[0958] Regression analysis is performed to predict future heart rate and step count based on past data.

[0959] Clustering is used to classify users' sleep patterns and athletic abilities.

[0960] As a result, analyzed health status data is generated.

[0961] Step 4: Generating advice

[0962] The server generates personalized fitness and health advice based on the analysis results. The input data is the analysis results obtained in step 3, and the generated advice becomes the output data.

[0963] Specific actions:

[0964] Based on the analysis results, a prompt message is created that generates appropriate advice using a generative AI model.

[0965] For example, it can automatically generate specific advice such as, "Your heart rate is a little high. Please do some breathing exercises to relax."

[0966] Output the advice in text format.

[0967] Step 5: Notify the user

[0968] The server sends the generated advice to the user's terminal. The input data is the generated advice, and the output data is the notification of this advice sent to the user's terminal.

[0969] Specific actions:

[0970] Once the advice is generated, the server identifies the corresponding user's terminal.

[0971] Advice will be sent as a push notification to the user's smartphone or other device.

[0972] The user's device displays the received advice, allowing the user to review it.

[0973] Step 6: Providing a customized exercise plan

[0974] When a user requests a customized exercise plan through the app, the server forwards the request to a specialist. The input data is the user's request, and the output data is the customized exercise plan provided to the user.

[0975] Specific actions:

[0976] The user submits a request through the application.

[0977] The server forwards this request to an expert.

[0978] Experts create exercise plans based on user data.

[0979] Once the exercise plan is complete, it is sent to the user via the server.

[0980] Users can view their customized exercise plan through the application.

[0981] (Application Example 1)

[0982] Next, we will explain Application Example 1. In the following explanation, 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."

[0983] Current fitness and health management systems collect and analyze individual user data to provide advice, but these are primarily limited to personal use. However, providing immediate, personalized advice to customers in physical stores can offer even greater support for health management and fitness. Systems that enable this kind of immediate advice in physical stores are still lacking, and realizing immediate fitness instruction and health management support for customers within physical stores remains a challenge.

[0984] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0985] In this invention, the server includes means for collecting data on exercise capacity, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results; means for notifying the user's terminal of the generated advice; and means for understanding the individual health status of customers in a physical store and providing fitness-related advice immediately. This makes it possible to provide customers with immediate, personalized health management and fitness advice in a physical store.

[0986] A "wearable device" is an electronic device that is attached to a user's body to collect biometric data such as athletic ability, sleep habits, and heart rate.

[0987] "Exercise capacity" refers to data that indicates the quantity and quality of exercise, such as the user's step count, calories burned, and exercise intensity.

[0988] "Sleep habits" refers to data that shows the user's sleep-related behaviors and patterns, such as sleep duration, sleep quality, time to fall asleep, and time to wake up.

[0989] "Heart rate" is data that indicates the number of heartbeats per minute and is an indicator of the user's cardiac activity.

[0990] "Preprocessing" is the process of converting collected biological data into a format suitable for analysis by performing noise reduction, filtering outliers, and imputing missing values.

[0991] "Health status" refers to the overall health condition of the user, based on data such as their exercise capacity, sleep habits, and heart rate.

[0992] "Analysis" is the process of evaluating and predicting a user's health status using statistical methods and machine learning techniques based on pre-processed data.

[0993] "Personalized advice" refers to providing specific health management and fitness guidance and recommendations tailored to individual users, based on analysis results.

[0994] "Notification" refers to the act of sending generated advice or information to a user's device to inform the user.

[0995] A "physical store" is a place that provides fitness instruction and health management services, and is a physical facility that customers can visit in person.

[0996] "Providing information instantly" means collecting and analyzing user data in real time and providing advice to customers immediately based on the results.

[0997] A "customized exercise plan by an expert" is an individualized exercise program designed by a fitness professional with specialized knowledge, based on the user's specific requests.

[0998] "Regression analysis" is a statistical method used to predict a user's future health status based on past data.

[0999] Clustering is a machine learning technique used to classify user data into groups with similar characteristics.

[1000] System Configuration

[1001] This invention is a system that utilizes data collected from wearable devices to provide customers with immediate fitness advice and health management in physical stores. The specific system configuration and operation are described below.

[1002] Data collection

[1003] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices worn by the user. The wearable device transmits this data to the server at regular intervals. Examples include smartwatches and smart bands.

[1004] Data preprocessing

[1005] The server preprocesses the collected biometric data. Specifically, it uses data processing libraries such as Pandas and NumPy to remove noise, filter outliers, and impute missing values, converting the data into a format suitable for analysis. For example, if data is missing, it is imputed with the mean value.

[1006] Data analysis

[1007] The pre-processed data is used by the server to analyze the user's health status. The methods used include machine learning techniques such as regression analysis and clustering. Libraries such as Scikit-learn are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends.

[1008] Generating advice

[1009] Based on the analysis results, the server generates personalized health and fitness advice. For example, if a user's step count is insufficient based on past data, it will generate advice such as, "Try to walk more to reach your step goal." If the heart rate is within a healthy range, it will generate a message such as, "Continue managing your health at this pace."

[1010] Notification to the user

[1011] The generated advice is sent to the user's device as a notification, depending on its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone application.

[1012] In-store, immediate fitness instruction

[1013] In physical stores, servers monitor each customer's health status and provide immediate fitness-related advice. Store staff can use the customer's device to view and provide personalized advice based on real-time health data. This enables more effective fitness instruction and health management.

[1014] Specific example

[1015] After a user has worn a wearable device for a day, the device collects the following data:

[1016] Step count: 8000 steps

[1017] Average heart rate: 75 bpm

[1018] Sleep duration: 7 hours

[1019] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[1020] 8,000 steps is short of the target of 10,000 steps.

[1021] The average heart rate is within a moderate range.

[1022] My sleep duration falls within the recommended range of 7-8 hours.

[1023] Based on this analysis, the server generates the following advice:

[1024] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[1025] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[1026] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[1027] The server sends this advice to the user's device, allowing the user to view the advice through a smartphone application.

[1028] Example of a prompt

[1029] Please generate personalized fitness and health advice based on the following data.

[1030] Data format:

[1031] {

[1032] "steps":

[8000] ,

[1033] "heart_rate":

[75] ,

[1034] "sleep_hours": [7]

[1035] }

[1036] Based on the analysis results, please generate advice using the following criteria:

[1037] 1. If your step count is less than 10,000 steps, you are advised to increase your step count to reach your goal.

[1038] 2. If the heart rate is within the range of 60-100 bpm, a notification will be issued indicating that it is normal.

[1039] 3. If your sleep duration is between 7 and 8 hours, it is recommended that you maintain good sleep habits.

[1040] This will now describe the specific form for carrying out the invention.

[1041] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1042] Step 1:

[1043] The server collects biometric data related to exercise capacity, sleep habits, and heart rate from wearable devices worn by the user at regular intervals. It receives biometric data transmitted from the wearable device as input and stores it in a database. Specifically, for example, a smartwatch sends the user's step count, average heart rate, and sleep data to the server every 30 minutes.

[1044] Step 2:

[1045] The server preprocesses the collected biometric data. It takes biometric data stored in a database as input, performs noise reduction, filters outliers, and imputes missing values. Specifically, it uses Pandas and NumPy to clean the data and convert it into a format suitable for analysis. This results in formatted data being output.

[1046] Step 3:

[1047] The server analyzes the user's health status using pre-processed data. It takes pre-processed data as input and performs regression analysis and clustering using machine learning libraries such as Scikit-learn. Specifically, it uses regression analysis to predict the next 30 days based on heart rate data from the past 30 days, and clustering to classify users into groups according to their health status. The analysis results are then output.

[1048] Step 4:

[1049] The server generates personalized health and fitness advice based on the analysis results. It takes the analysis results as input and creates advice tailored to the user's specific data. For example, it might generate advice such as "Try to walk a little more" for a user whose step count hasn't reached their goal, or "Continue managing your health at this pace" for a user whose heart rate is within the normal range. This results in personalized advice being output.

[1050] Step 5:

[1051] The server notifies the user's device of the generated advice. It retrieves the generated advice as input and sends it to the user's smartphone or tablet. The device displays the received advice message and informs the user. Specifically, the smartphone application displays the advice content as a pop-up notification or on the dashboard. This allows the user to receive feedback in real time.

[1052] Step 6:

[1053] The server analyzes user data in real time and notifies store staff to provide immediate fitness-related advice within the physical store. It uses data collected in real time as input, performs analysis and generates advice, and notifies store staff terminals. This allows store staff to understand each customer's individual health status and provide immediate, specific fitness guidance and health management.

[1054] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1055] The present invention is a system that provides personalized health and fitness advice by combining data collected from a wearable device with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[1056] System Configuration

[1057] Data collection

[1058] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. For example, data is sent from the wearable device to the server at regular intervals each day. This data includes the total number of steps taken per day, average heart rate, and sleep duration.

[1059] Data preprocessing

[1060] The server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[1061] Data analysis

[1062] The server analyzes the user's health status based on pre-processed data. Using regression analysis and clustering techniques, it analyzes and predicts the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts the amount of exercise for the next 30 days based on exercise data from the past 30 days and identifies areas for improvement.

[1063] Implementation of an emotion engine

[1064] The server also features an emotion engine. This emotion engine recognizes the user's emotions using voice, facial expressions, and text data. For example, it uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and uses an emotion recognition algorithm to identify the user's current emotional state.

[1065] Generating advice

[1066] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will recommend relaxation exercises. Also, if the server detects that the user is agitated on a day with a high heart rate, it will provide advice to adjust the amount of exercise.

[1067] Notification to the user

[1068] The server notifies the user's device of the advice it has generated. The device analyzes the advice message received from the server and displays it through the user interface. For example, a smartphone app can display pop-up notifications or a dashboard to allow the user to quickly check the advice.

[1069] Providing a customized exercise plan

[1070] Users can request a customized exercise plan from an expert through the app. They enter their specific request details into a form and submit it to the server. The server forwards this request to an expert, who designs a customized exercise plan based on the user's request. This exercise plan is then provided to the user again via the server. For example, the plan might include specific details such as "perform 30 minutes of aerobic exercise three times a week."

[1071] Specific example

[1072] Data Acquisition and Preprocessing

[1073] The server collects the following data from the user's wearable device:

[1074] Step count: 8000 steps

[1075] Average heart rate: 75 bpm

[1076] Sleep duration: 7 hours

[1077] Data Analysis

[1078] The server analyzes the pre-processed data and obtains the following conclusions:

[1079] The number of steps taken has not reached the target of 10,000 steps.

[1080] The average heart rate is within a moderate range.

[1081] Sleep duration is within the recommended range of 7-8 hours.

[1082] emotion recognition

[1083] The emotion engine uses the smartphone's camera and microphone to analyze the user's facial expressions and voice, recognizing when the user is experiencing stress.

[1084] Generating advice

[1085] The server considers both health and emotional state to generate the following advice:

[1086] "Your step count today is 8,000 steps, which is short of your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[1087] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[1088] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[1089] Advice notification

[1090] The server sends the generated advice to the device, and the user can check the advice through a smartphone app.

[1091] Customized exercise plan

[1092] When a user requests a customized exercise plan from an expert, the server forwards the request to the expert, who then provides the user with the designed exercise plan. For example, a specific plan such as "a 30-minute strength training session three times a week" might be provided.

[1093] As described above, the present invention is a system that combines data obtained from a wearable device with the user's emotions to provide more highly personalized health management and fitness support.

[1094] The following describes the processing flow.

[1095] Step 1:

[1096] The server collects data from wearable devices. Specifically, the server uses the device API to periodically send data retrieval requests to obtain vital data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might be configured to collect the previous day's data at midnight every day.

[1097] Step 2:

[1098] The server preprocesses the collected data. First, it denoises the data, filtering out, for example, extremely high step counts or abnormal heart rates. Next, it normalizes the data to ensure consistency as time-series data. For example, it imputes missing data with the mean.

[1099] Step 3:

[1100] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning algorithms (regression analysis and clustering) to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, it applies an algorithm that predicts the amount of exercise for the next 30 days based on data from the past 30 days and proposes an appropriate exercise plan.

[1101] Step 4:

[1102] The server recognizes the user's emotions through an emotion engine. The emotion engine uses the smartphone's camera and microphone to collect the user's facial and voice data and analyze their emotions. For example, when the user opens the app, the camera captures their facial expression and the voice response is obtained.

[1103] Step 5:

[1104] The server integrates health status analysis results with emotional data recognized by the emotion engine to generate personalized health and fitness advice. For example, if a user is not getting enough exercise and is feeling stressed, it will generate advice recommending "taking a light walk to relax."

[1105] Step 6:

[1106] The server then notifies the user's device of the advice it has generated. Specifically, it generates a notification message and sends a push notification to the user's smartphone app using Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNs). For example, it might send a message such as, "Your exercise level today did not meet your goal. We recommend a light, relaxing walk."

[1107] Step 7:

[1108] The device analyzes advice messages received from the server and displays them in the user interface. Specifically, it displays them as pop-up messages in the smartphone's notification bar or shows detailed advice in the in-app dashboard. For example, it might display specific suggestions such as "Today's activity level: 8,000 steps / 10,000 steps" and "Perform relaxation exercises."

[1109] Step 8:

[1110] Users can request a customized exercise plan from an expert through the app. For example, they can enter "I want to increase my strength training" into the request form within the app and press the submit button.

[1111] Step 9:

[1112] The server receives the user's request and forwards it to an expert. The expert customizes the exercise plan based on the request. For example, they might create a program recommending "30 minutes of strength training three times a week."

[1113] Step 10:

[1114] The server then notifies the user's device again of the customized exercise plan received from the expert. The user can then view the new exercise plan through a smartphone app. For example, the app's dashboard might display a "Strength Training Plan" with specific exercises to be done three times a week.

[1115] In this way, this system, which incorporates an emotion engine, provides more personalized health and fitness support based on multifaceted data analysis that includes the user's emotional state.

[1116] (Example 2)

[1117] Next, we will describe Example 2. 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."

[1118] Traditional health and fitness management systems can collect users' biometric data and assess their basic health status, but they have limitations in generating personalized advice. Furthermore, advice provided without considering the user's emotional state is less effective. Additionally, users must manually request customized exercise plans from professionals, which is time-consuming and inconvenient. There is a need to address these challenges and provide more detailed and personalized health and fitness support.

[1119] The identification processing 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 means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results and emotion recognition; and means for notifying the user's terminal of the generated advice and customized exercise plan. This enables the user to receive more detailed and personalized advice that comprehensively considers their health status and emotional state. Furthermore, the request and provision of customized exercise plans by experts are automated, reducing the burden on the user.

[1120] A "wearable device" is a device that is worn on a user's body to collect biometric data. Examples include smartwatches and fitness trackers.

[1121] "Physical ability" refers to data that indicates the user's physical activity performance. Specifically, it includes steps taken, distance traveled, calories burned, and so on.

[1122] "Sleep habits" refers to data that shows a user's sleep patterns and sleep quality. Specifically, it includes sleep duration, percentage of deep sleep, and number of sleep interruptions.

[1123] "Heart rate" is data that indicates the number of times a user's heart beats. It is usually expressed as heart rate per minute (bpm).

[1124] "Preprocessing" refers to data processing to convert collected biological data into an analyzable format. Specifically, this includes noise reduction, outlier filtering, and data normalization.

[1125] "Health status" refers to data that indicates the user's overall physical condition and level of health. This is comprehensively evaluated from multiple data points, such as exercise capacity, sleep habits, and heart rate.

[1126] "Emotion recognition" is a technology that identifies a user's emotional state using voice, facial expression, and text data. Specifically, it collects data using a smartphone's camera and microphone and analyzes it using algorithms.

[1127] "Personalized health and fitness advice" refers to specific, tailored guidance and recommendations provided to each individual, taking into account their health and emotional state.

[1128] A "device" is an electronic device that a user can operate. Examples include smartphones, tablets, and personal computers.

[1129] A "customized exercise plan" is an exercise plan designed based on the user's specific needs and goals. It is created by a specialist in response to the user's request.

[1130] A "specialist" is someone who possesses knowledge and experience regarding the user's health and fitness. Examples include trainers and nutritionists.

[1131] "Notifications" refer to the act of delivering generated advice or customized exercise plans to the user's device. Specifically, this includes pop-up notifications and dashboard displays.

[1132] Modes for carrying out the invention

[1133] This invention is a system that provides personalized health and fitness advice by combining data collected from wearable devices with an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[1134] Data collection

[1135] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices (e.g., smartwatches, fitness trackers). The collection process involves the wearable device sending data to the server at regular intervals each day. For example, at 6 AM every morning, a day's worth of data (steps, average heart rate, sleep duration, etc.) is collected.

[1136] Data preprocessing

[1137] The server preprocesses the collected data. This process includes noise reduction, outlier filtering, and data normalization. For example, it removes or interpolates data points where the average heart rate is extremely high (above 150 bpm) or low (below 40 bpm).

[1138] Data analysis

[1139] The server analyzes the pre-processed data. The analysis steps include predicting health status using regression analysis and clustering techniques, and analyzing trends in exercise capacity, sleep patterns, and heart rate. For example, based on exercise data from the past 30 days, it sets exercise goals for the next 30 days and identifies areas for improvement.

[1140] Implementation of an emotion engine

[1141] The server uses an emotion engine to recognize the user's emotions based on voice, facial expressions, and text data. The emotion engine uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and analyzes them with an emotion recognition algorithm. For example, while the user is using their smartphone, the camera captures their facial expressions and audio data is collected to determine whether the user is experiencing stress.

[1142] Generating advice

[1143] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it recommends relaxation exercises, and if a lack of exercise is detected, it suggests a light jog. Specific advice might include messages such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so we recommend a light walk."

[1144] Advice notification

[1145] The server notifies the user's device of the generated advice. The device analyzes the received advice message and displays it through the user interface. For example, a smartphone app might display a pop-up notification so that the user can quickly check the advice.

[1146] Customized exercise plan

[1147] Users can request a customized exercise plan from an expert through the app. They enter their request details into a form and submit it to the server. This information is forwarded to the expert, who designs an exercise plan tailored to the user's specific needs. The designed exercise plan is then provided to the user again via the server. For example, a specific plan such as "30-minute strength training sessions three times a week" might be provided.

[1148] Specific examples and prompt statements

[1149] Specific example

[1150] Data Collection: The server collects a day's worth of data from wearable devices every morning at 6:00 AM (steps: 8,000, average heart rate: 75 bpm, sleep time: 7 hours).

[1151] Data preprocessing: The server removes outliers where the heart rate exceeds 150 bpm.

[1152] Data analysis: Set exercise goals for the next 30 days based on exercise data from the past 30 days.

[1153] Emotion recognition: The system uses the smartphone's camera to recognize when the user is experiencing stress.

[1154] Advice generation: Generates the advice: "Your step count today is 8000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[1155] Advice Notification: The server sends the generated advice to the user's smartphone and displays it as a pop-up notification.

[1156] Customized Exercise Plan: Users request a "30-minute strength training plan, 3 times a week," and experts design and provide it.

[1157] Examples of prompt statements

[1158] "Create a program that recognizes the user's emotions and provides health advice based on them. For example, include a feature that recommends relaxation exercises if the user is feeling stressed."

[1159] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1160] Step 1: Data Collection

[1161] The server collects biometric data from the user's wearable device.

[1162] Input: Exercise capacity, sleep habits, and heart rate data transmitted from wearable devices.

[1163] Specific operation: For example, request and receive a day's worth of data (steps, average heart rate, sleep duration) from a Fitbit or smartwatch at 6 AM every morning.

[1164] Output: Collected biometric data (e.g., total daily steps 8000, average heart rate 75 bpm, sleep duration 7 hours).

[1165] Step 2: Data preprocessing

[1166] The server preprocesses the collected data.

[1167] Input: Collected biometric data.

[1168] Specific operations: Noise reduction, outlier filtering, and data normalization. For example, it detects and removes outliers such as an average heart rate exceeding 150 bpm. It also imputes missing data points.

[1169] Output: Preprocessed data.

[1170] Step 3: Data Analysis

[1171] The server analyzes the pre-processed data.

[1172] Input: Pre-processed data.

[1173] Specific actions: Using regression analysis and clustering techniques, the system analyzes the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts exercise levels for the next 30 days using data from the past 30 days.

[1174] Output: Analysis results and health status prediction.

[1175] Step 4: Emotion Recognition

[1176] The server uses an emotion engine to recognize the user's emotions.

[1177] Input: Voice, facial expressions, and text data collected from the smartphone's camera and microphone.

[1178] Specific operation: The smartphone camera is activated, and the user's facial expression and voice data are collected in real time and analyzed using an emotion recognition algorithm. For example, it can determine whether the user is experiencing stress.

[1179] Output: User's emotional state (e.g., stress).

[1180] Step 5: Generating Advice

[1181] The server generates personalized advice based on the analysis of health status and the recognition of emotions.

[1182] Input: Analysis results and emotional state.

[1183] Specific actions: For example, create advice such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[1184] Output: Generated advice message.

[1185] Step 6: Advice Notification

[1186] The server notifies the user's terminal of the generated advice.

[1187] Input: Generated advice message.

[1188] Specific actions: Send an advice message to the device and display it to the user through a pop-up notification or dashboard display. For example, display a notification via a smartphone app.

[1189] Output: Advice displayed to the user.

[1190] Step 7: Customized Exercise Plan

[1191] Users can request a customized exercise plan from an expert through the app.

[1192] Input: User request information (specific needs and goals).

[1193] Specific operation: Enter information into the request form within the app and send it to the server. The server forwards the request to an expert, who designs an exercise plan based on the user's needs. For example, a "30-minute strength training plan three times a week" might be created.

[1194] Output: A customized exercise plan is provided to the user.

[1195] (Application Example 2)

[1196] Next, we will explain application example 2. In the following explanation, 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."

[1197] Traditional health management systems primarily focused on collecting and analyzing biometric data such as users' exercise capacity, sleep habits, and heart rate to provide fitness advice. However, they lacked personalization because they did not take into account the user's emotional state. Furthermore, they lacked suggestions for suitable meal plans in addition to health management. As a result, comprehensive health management and improvements in fitness and dietary habits were difficult.

[1198] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health and emotional state using the preprocessed data; means for generating personalized health and fitness advice based on the analyzed data; and means for notifying the user's terminal of the generated advice and suggesting meal menus based on the progress. This enables comprehensive health management that takes into account both the user's health and emotional state, and meal suggestions that are appropriate to the user's health state.

[1199] A "wearable device" is an electronic device that an individual can wear to collect biometric data such as athletic ability, sleep habits, and heart rate.

[1200] "Emotional state" refers to data that indicates the emotions and psychological state a user is experiencing at a specific time.

[1201] "Preprocessing" refers to the process of applying noise reduction, filtering outliers, and normalizing data to biometric data collected from wearable devices.

[1202] "Health status" refers to data that indicates the user's physical and physiological condition, including exercise capacity, sleep patterns, and heart rate.

[1203] "Fitness advice" refers to specific suggestions and guidance regarding exercise, diet, and rest to improve the user's health.

[1204] The "meal menu" is a list that suggests balanced meals based on the user's health and emotional state.

[1205] "Progress" refers to data that shows changes and progress in the user's health status.

[1206] A "customized exercise plan by an expert" is an exercise plan designed by an expert based on the individual user's health condition and goals.

[1207] Regression analysis is a statistical method that models the relationships between numerical data and is used to predict specific health conditions.

[1208] Clustering is a data analysis technique that groups data based on similarity and is used to identify user health patterns.

[1209] A "prompt sentence" is text input into a generative AI model that contains instructions for generating specific information or answers.

[1210] This invention is a system that analyzes data collected from a wearable device and the user's emotional state to provide personalized health and fitness advice and meal menus. Specific embodiments of this system are described in detail below.

[1211] First, the server collects data on exercise capacity, sleep habits, and heart rate from wearable devices. Wearable devices such as Apple Watch, Fitbit, and Garmin can be used. The data collected from these devices is sent to the server at regular intervals.

[1212] Next, the server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[1213] Based on the pre-processed data, the server analyzes the user's health and emotional state. The emotional state is analyzed using an emotion engine. This emotion engine uses tools such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect the user's facial expressions and voice data through the smartphone's camera and microphone.

[1214] The server then generates personalized health and fitness advice based on the analysis results. It also suggests appropriate meal plans, taking into account the user's health and emotional state. For example, if data from a wearable device indicates that the user's heart rate is low and that calorie intake is needed, the server will suggest a meal plan suitable for energy replenishment.

[1215] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed to be intuitive and easy to use, allowing users to quickly check the advice and meal menus through pop-up notifications and dashboard displays.

[1216] As a concrete example, a notification using the following prompt statement can be considered:

[1217] "Based on your health and mood today, here are our recommended dishes: a healthy salad and lean grilled chicken. Would you like to order?"

[1218] Furthermore, users can request customized exercise and meal plans from experts through the app. These requests are sent to experts via the server, and the plans provided by the experts are then notified to the user via the server.

[1219] As described above, the system of the present invention provides comprehensive health management that takes into account both the user's physical and emotional state, as well as personalized fitness and dietary suggestions.

[1220] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1221] Step 1:

[1222] The server collects biometric data from wearable devices regarding exercise capacity, sleep habits, and heart rate. Specifically, data is sent from devices such as Apple Watch, Fitbit, and Garmin at regular intervals.

[1223] Input: Biometric data related to athletic ability, sleep habits, and heart rate

[1224] Output: Unprocessed biometric data

[1225] Step 2:

[1226] The server preprocesses the collected biometric data. Specifically, it performs noise reduction (elimination of false values), filtering of outliers, and normalization of the data. For example, it removes or interpolates extremely high or low heart rate values.

[1227] Input: Unprocessed biometric data

[1228] Output: Preprocessed data

[1229] Step 3:

[1230] The server analyzes the user's health status using pre-processed data. Specifically, it analyzes data trends using regression analysis and clustering techniques to predict and evaluate health status.

[1231] Input: Preprocessed data

[1232] Output: Analysis results of health status

[1233] Step 4:

[1234] The server uses an emotion engine to analyze the user's emotional state. The emotion engine utilizes technologies such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect facial and audio data through the smartphone's camera and microphone.

[1235] Input: Facial and voice data collected from a smartphone.

[1236] Output: Emotional state evaluation results

[1237] Step 5:

[1238] The server combines the results of health status analysis and emotional state assessment to generate personalized health and fitness advice. It also suggests appropriate meal plans based on this advice.

[1239] Input: Analysis results of health status and evaluation results of emotional status

[1240] Output: Personalized health advice and meal plans

[1241] Step 6:

[1242] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed for ease of use and provides information quickly to the user through pop-up notifications and dashboard displays.

[1243] Input: Personalized health advice and meal plans

[1244] Output: Notification to smartphone app

[1245] Step 7:

[1246] Users can request customized exercise and meal plans from experts through a smartphone app. The request is sent to the expert via a server, and the provided plan is then notified to the user via the server.

[1247] Input: User request for customization plan

[1248] Output: Provision of customized plans by experts and notifications

[1249] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1250] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1251] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1252] [Fourth Embodiment]

[1253] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1254] As shown in Figure 7, the 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.

[1255] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1256] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1257] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1258] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1259] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1260] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1261] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1262] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1263] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1264] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1265] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1266] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management.

[1267] System Configuration

[1268] Data collection

[1269] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. The wearable device sends this data to the server at regular intervals. For example, it can send step count, heart rate, and sleep data to the server every 30 minutes.

[1270] Data preprocessing

[1271] The server preprocesses the collected biometric data. For example, it performs noise reduction, filters outliers, and converts the data to the required format. Since raw data may contain missing values, it performs appropriate imputation. It also formats the data on a time-based basis and converts it to a format suitable for analysis.

[1272] Data analysis

[1273] The pre-processed data is used by the server to analyze the user's health status. Specifically, statistical methods such as regression analysis and clustering are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, based on heart rate data from the past 30 days, predictions for the next 30 days can be made.

[1274] Generating advice

[1275] Based on the analysis results, the server generates personalized health and fitness advice. For example, a user who has not exercised enough in the past 30 days can be given specific advice such as "We recommend increasing your daily walking time by 10 minutes." Similarly, a user with a high heart rate can be recommended breathing exercises to help them relax.

[1276] Notification to the user

[1277] The server notifies the user's device of the generated advice according to its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone app.

[1278] Providing a customized exercise plan

[1279] When a user requests a customized exercise plan from an expert through the app, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "30 minutes of strength training three times a week."

[1280] Specific example

[1281] After a user has worn a wearable device for a day, the device collects the following data:

[1282] Step count: 8000 steps

[1283] Average heart rate: 75 bpm

[1284] Sleep duration: 7 hours

[1285] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[1286] 8,000 steps is short of the target of 10,000 steps.

[1287] The average heart rate is within a moderate range.

[1288] My sleep duration falls within the recommended range of 7-8 hours.

[1289] Based on this analysis, the server generates the following advice:

[1290] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[1291] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[1292] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[1293] The server sends this advice to the device, allowing the user to view the advice through a smartphone app.

[1294] Furthermore, when a user requests a customized exercise plan from an expert, the server sends the request to the expert and provides the user with the exercise plan designed by the expert, thereby supporting more specific health management and fitness achievement.

[1295] As described above, the present invention integrates data collection, preprocessing, analysis, advice generation, and notification from wearable devices to provide users with personalized health management and fitness support.

[1296] The following describes the processing flow.

[1297] Step 1:

[1298] The server collects data from wearable devices. Specifically, the server periodically communicates with wearable devices to obtain biometric data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might send an API request at 12:00 every day to collect data from the previous day.

[1299] Step 2:

[1300] The server preprocesses the collected biometric data. Specifically, it removes noise from the data and filters out outliers. Next, it normalizes the preprocessed data and converts it into a format suitable for analysis. For example, if step count data is missing, it is imputed with the mean value.

[1301] Step 3:

[1302] The server analyzes the pre-processed data. Specifically, it uses regression analysis and clustering to analyze the user's exercise capacity, sleep patterns, and heart rate in detail. For example, it uses data from the past 30 days to build a predictive model for the next 30 days.

[1303] Step 4:

[1304] The server generates personalized advice based on the analysis results. For example, if a user's step count hasn't reached their goal, it will make specific suggestions such as "increase your daily step count by 2000 steps." If the user's heart rate is high, it will suggest ways to relax.

[1305] Step 5:

[1306] The server notifies the user's device of the generated advice. Specifically, it creates a notification message and sends it via push notification or in-app messaging. For example, it can send real-time notifications using Firebase Cloud Messaging (FCM).

[1307] Step 6:

[1308] The device receives notifications from the server and displays advice through the user interface. For example, the notification bar of a smartphone app might display, "Your step count today is low. Let's walk another 2000 steps!"

[1309] Step 7:

[1310] Users can request a customized exercise plan from an expert through the app. For example, they can enter a specific request in a form, such as "I want to increase my strength training."

[1311] Step 8:

[1312] The server receives requests from users and forwards them to experts. The experts create customized exercise plans based on the requests and send them back to the server. For example, a "30-minute strength training plan, three times a week" might be created.

[1313] Step 9:

[1314] The server then notifies the user's device again of the customized exercise plan from the expert, and the user can view the detailed exercise plan through the app. For example, the new exercise plan will appear on the app's dashboard.

[1315] Through the processing steps described above, this system can manage users' health conditions in a highly personalized manner and provide effective fitness and health advice.

[1316] (Example 1)

[1317] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1318] With the recent rise in health awareness, many people are using wearable devices to monitor their health. However, the amount of data obtained from these devices is enormous, making it difficult for individual users to accurately interpret it and apply it to their daily lives. Furthermore, there is a need for systems that go beyond mere data collection, comprehensively analyze the user's health status, and provide personalized health advice. Conventional systems often lack sufficient data preprocessing and the provision of customized advice from experts, which prevents users from reaping the maximum benefit.

[1319] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1320] In this invention, the server includes means for collecting biometric data from a wearable device, means for preprocessing the biometric data, means for analyzing the user's health status using the preprocessed data, means for generating individualized health and exercise advice based on the analysis results, and means for notifying the user's device of the generated advice. This enables the user to receive personalized health advice based on data collected from the wearable device, thereby achieving more effective health management and fitness support.

[1321] A "wearable device" is a device that is attached to the user's body and measures and records biometric data such as exercise ability, heart rate, and sleep habits.

[1322] "Biometric data" refers to information about a user's physical condition and activity measured by wearable devices, and specifically includes heart rate, steps taken, sleep duration, etc.

[1323] "Preprocessing" refers to the process of converting biological data into a format that is easy to analyze, and specifically includes noise reduction, filtering of outliers, and imputation of missing values.

[1324] "Analysis" refers to calculations and methods used to evaluate and predict a user's health status using pre-processed data, specifically involving the use of statistical methods such as regression analysis and clustering.

[1325] "Advice generation" is the process of creating personalized health and exercise advice for users based on the analysis results.

[1326] "User's device" refers to an information terminal used by the user, including digital devices such as smartphones, tablets, and personal computers.

[1327] This invention is a system that utilizes data collected from wearable devices to analyze a user's health status and provide personalized fitness advice and health management. This system operates with three components: a server, a terminal, and a user.

[1328] First, the server collects biometric data (e.g., heart rate, steps, sleep data, etc.) from the user's wearable device (e.g., a smartwatch worn on the user's wrist). This data is sent to the server at regular intervals (e.g., every 30 minutes). Specifically, the server uses a server computer with a high-performance CPU and sufficient memory.

[1329] Next, the server preprocesses the data. This preprocessing includes denoising the received data (e.g., removing abnormally high heart rates), filtering outliers, and imputing missing values. These processes are performed using data processing libraries such as Python's Pandas and NumPy.

[1330] The pre-processed data is used by the server to analyze the user's health status. Specifically, machine learning libraries such as scikit-learn are used to perform regression analysis and clustering to predict and analyze the user's exercise capacity, sleep patterns, and heart rate trends.

[1331] Based on the analysis results, the server generates personalized health and fitness advice. For example, it predicts the heart rate for the next 30 days based on heart rate data from the past 30 days and provides specific advice to users who are not getting enough exercise, such as "We recommend increasing your daily walking time by 10 minutes." It also recommends breathing exercises to help users with elevated heart rates relax.

[1332] The generated advice is sent from the server to the user's device (e.g., a smartphone or tablet). The device displays the received advice through a user interface. For example, the advice may be displayed as a pop-up notification or on a dashboard using a smartphone app.

[1333] Furthermore, if a user requests a customized exercise plan from an expert, the server forwards the request to the expert. The expert designs an exercise plan based on the user's request and provides it to the user through the server. For example, the plan might include "perform 30 minutes of strength training three times a week."

[1334] Specific example

[1335] As an example for one day, suppose a user wears a wearable device while performing activities, and the following data is collected:

[1336] Step count: 8000 steps

[1337] Average heart rate: 75 bpm

[1338] Sleep duration: 7 hours

[1339] The server receives this data, performs noise reduction and outlier filtering using Pandas and NumPy, and then analyzes the data using scikit-learn. The analysis results yield the following insights:

[1340] 8,000 steps is short of the target of 10,000 steps.

[1341] The average heart rate is within a moderate range.

[1342] My sleep duration falls within the recommended range of 7-8 hours.

[1343] Based on this analysis, the server generates the following advice:

[1344] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[1345] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[1346] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[1347] The server sends this advice to the user's smartphone, and the user can view this advice through the app.

[1348] Furthermore, when a user requests a customized exercise plan, the server forwards the request to an expert, who then provides the user with an exercise plan designed by the expert. For example, if a user requests a "30-minute, 3-session strength training plan per week from an expert," the expert designs the plan and sends it to the server, which then communicates it to the user.

[1349] In this way, the system enables consistent data collection, preprocessing, analysis, advice generation, notification, and customized plan delivery. Through this process, users can gain a deeper understanding of their own health status and receive effective health management and fitness support.

[1350] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1351] Step 1: Data Collection

[1352] The server collects biometric data from the user's wearable device. This device periodically (for example, every 30 minutes) records heart rate, steps, sleep data, etc., and transmits it to the server via Bluetooth or Wi-Fi. The input data is the biometric data obtained from the wearable device, and this becomes the output data at the time it is transmitted to the server.

[1353] Specific actions:

[1354] Wearable devices measure the user's biometric data.

[1355] The measurement data is sent to the server at regular intervals.

[1356] The server stores this data in the database.

[1357] Step 2: Data preprocessing

[1358] The server performs noise reduction, filters outliers, and imputes missing values ​​in the received biometric data. The input data is the biometric data collected in step 1, and the pre-processed data becomes the output data.

[1359] Specific actions:

[1360] Load the data using libraries such as Pandas or NumPy.

[1361] Noise reduction: For example, detecting and removing extremely high heart rates or abnormally low step counts.

[1362] Outlier filtering: Replace outliers with the median or mean of the data.

[1363] Imputing missing values: For example, missing values ​​can be imputed using the mean of the preceding and succeeding data.

[1364] Step 3: Data Analysis

[1365] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning models (regression analysis, clustering, etc.). The input data is pre-processed biometric data, and the analysis results become the output data.

[1366] Specific actions:

[1367] Load the analysis model using the scikit-learn library.

[1368] Regression analysis is performed to predict future heart rate and step count based on past data.

[1369] Clustering is used to classify users' sleep patterns and athletic abilities.

[1370] As a result, analyzed health status data is generated.

[1371] Step 4: Generating advice

[1372] The server generates personalized fitness and health advice based on the analysis results. The input data is the analysis results obtained in step 3, and the generated advice becomes the output data.

[1373] Specific actions:

[1374] Based on the analysis results, a prompt message is created that generates appropriate advice using a generative AI model.

[1375] For example, it can automatically generate specific advice such as, "Your heart rate is a little high. Please do some breathing exercises to relax."

[1376] Output the advice in text format.

[1377] Step 5: Notify the user

[1378] The server sends the generated advice to the user's terminal. The input data is the generated advice, and the output data is the notification of this advice sent to the user's terminal.

[1379] Specific actions:

[1380] Once the advice is generated, the server identifies the corresponding user's terminal.

[1381] Advice will be sent as a push notification to the user's smartphone or other device.

[1382] The user's device displays the received advice, allowing the user to review it.

[1383] Step 6: Providing a customized exercise plan

[1384] When a user requests a customized exercise plan through the app, the server forwards the request to a specialist. The input data is the user's request, and the output data is the customized exercise plan provided to the user.

[1385] Specific actions:

[1386] The user submits a request through the application.

[1387] The server forwards this request to an expert.

[1388] Experts create exercise plans based on user data.

[1389] Once the exercise plan is complete, it is sent to the user via the server.

[1390] Users can view their customized exercise plan through the application.

[1391] (Application Example 1)

[1392] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1393] Current fitness and health management systems collect and analyze individual user data to provide advice, but these are primarily limited to personal use. However, providing immediate, personalized advice to customers in physical stores can offer even greater support for health management and fitness. Systems that enable this kind of immediate advice in physical stores are still lacking, and realizing immediate fitness instruction and health management support for customers within physical stores remains a challenge.

[1394] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1395] In this invention, the server includes means for collecting data on exercise capacity, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results; means for notifying the user's terminal of the generated advice; and means for understanding the individual health status of customers in a physical store and providing fitness-related advice immediately. This makes it possible to provide customers with immediate, personalized health management and fitness advice in a physical store.

[1396] A "wearable device" is an electronic device that is attached to a user's body to collect biometric data such as athletic ability, sleep habits, and heart rate.

[1397] "Exercise capacity" refers to data that indicates the quantity and quality of exercise, such as the user's step count, calories burned, and exercise intensity.

[1398] "Sleep habits" refers to data that shows the user's sleep-related behaviors and patterns, such as sleep duration, sleep quality, time to fall asleep, and time to wake up.

[1399] "Heart rate" is data that indicates the number of heartbeats per minute and is an indicator of the user's cardiac activity.

[1400] "Preprocessing" is the process of converting collected biological data into a format suitable for analysis by performing noise reduction, filtering outliers, and imputing missing values.

[1401] "Health status" refers to the overall health condition of the user, based on data such as their exercise capacity, sleep habits, and heart rate.

[1402] "Analysis" is the process of evaluating and predicting a user's health status using statistical methods and machine learning techniques based on pre-processed data.

[1403] "Personalized advice" refers to providing specific health management and fitness guidance and recommendations tailored to individual users, based on analysis results.

[1404] "Notification" refers to the act of sending generated advice or information to a user's device to inform the user.

[1405] A "physical store" is a place that provides fitness instruction and health management services, and is a physical facility that customers can visit in person.

[1406] "Providing information instantly" means collecting and analyzing user data in real time and providing advice to customers immediately based on the results.

[1407] A "customized exercise plan by an expert" is an individualized exercise program designed by a fitness professional with specialized knowledge, based on the user's specific requests.

[1408] "Regression analysis" is a statistical method used to predict a user's future health status based on past data.

[1409] Clustering is a machine learning technique used to classify user data into groups with similar characteristics.

[1410] System Configuration

[1411] This invention is a system that utilizes data collected from wearable devices to provide customers with immediate fitness advice and health management in physical stores. The specific system configuration and operation are described below.

[1412] Data collection

[1413] The server collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices worn by the user. The wearable device transmits this data to the server at regular intervals. Examples include smartwatches and smart bands.

[1414] Data preprocessing

[1415] The server preprocesses the collected biometric data. Specifically, it uses data processing libraries such as Pandas and NumPy to remove noise, filter outliers, and impute missing values, converting the data into a format suitable for analysis. For example, if data is missing, it is imputed with the mean value.

[1416] Data analysis

[1417] The pre-processed data is used by the server to analyze the user's health status. The methods used include machine learning techniques such as regression analysis and clustering. Libraries such as Scikit-learn are used to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends.

[1418] Generating advice

[1419] Based on the analysis results, the server generates personalized health and fitness advice. For example, if a user's step count is insufficient based on past data, it will generate advice such as, "Try to walk more to reach your step goal." If the heart rate is within a healthy range, it will generate a message such as, "Continue managing your health at this pace."

[1420] Notification to the user

[1421] The generated advice is sent to the user's device as a notification, depending on its content. The device analyzes the advice message received from the server and displays it through the user interface. For example, the advice can be displayed as a pop-up notification or on a dashboard using a smartphone application.

[1422] In-store, immediate fitness instruction

[1423] In physical stores, servers monitor each customer's health status and provide immediate fitness-related advice. Store staff can use the customer's device to view and provide personalized advice based on real-time health data. This enables more effective fitness instruction and health management.

[1424] Specific example

[1425] After a user has worn a wearable device for a day, the device collects the following data:

[1426] Step count: 8000 steps

[1427] Average heart rate: 75 bpm

[1428] Sleep duration: 7 hours

[1429] The server receives this data, performs noise reduction and filters outliers, and then analyzes the data. The analysis results yield the following conclusions:

[1430] 8,000 steps is short of the target of 10,000 steps.

[1431] The average heart rate is within a moderate range.

[1432] My sleep duration falls within the recommended range of 7-8 hours.

[1433] Based on this analysis, the server generates the following advice:

[1434] "You walked 8,000 steps today. To reach your goal of 10,000 steps, please try to walk a little more."

[1435] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[1436] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[1437] The server sends this advice to the user's device, allowing the user to view the advice through a smartphone application.

[1438] Example of a prompt

[1439] Please generate personalized fitness and health advice based on the following data.

[1440] Data format:

[1441] {

[1442] "steps":

[8000] ,

[1443] "heart_rate":

[75] ,

[1444] "sleep_hours": [7]

[1445] }

[1446] Based on the analysis results, please generate advice using the following criteria:

[1447] 1. If your step count is less than 10,000 steps, you are advised to increase your step count to reach your goal.

[1448] 2. If the heart rate is within the range of 60-100 bpm, a notification will be issued indicating that it is normal.

[1449] 3. If your sleep duration is between 7 and 8 hours, it is recommended that you maintain good sleep habits.

[1450] This will now describe the specific form for carrying out the invention.

[1451] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1452] Step 1:

[1453] The server collects biometric data related to exercise capacity, sleep habits, and heart rate from wearable devices worn by the user at regular intervals. It receives biometric data transmitted from the wearable device as input and stores it in a database. Specifically, for example, a smartwatch sends the user's step count, average heart rate, and sleep data to the server every 30 minutes.

[1454] Step 2:

[1455] The server preprocesses the collected biometric data. It takes biometric data stored in a database as input, performs noise reduction, filters outliers, and imputes missing values. Specifically, it uses Pandas and NumPy to clean the data and convert it into a format suitable for analysis. This results in formatted data being output.

[1456] Step 3:

[1457] The server analyzes the user's health status using pre-processed data. It takes pre-processed data as input and performs regression analysis and clustering using machine learning libraries such as Scikit-learn. Specifically, it uses regression analysis to predict the next 30 days based on heart rate data from the past 30 days, and clustering to classify users into groups according to their health status. The analysis results are then output.

[1458] Step 4:

[1459] The server generates personalized health and fitness advice based on the analysis results. It takes the analysis results as input and creates advice tailored to the user's specific data. For example, it might generate advice such as "Try to walk a little more" for a user whose step count hasn't reached their goal, or "Continue managing your health at this pace" for a user whose heart rate is within the normal range. This results in personalized advice being output.

[1460] Step 5:

[1461] The server notifies the user's device of the generated advice. It retrieves the generated advice as input and sends it to the user's smartphone or tablet. The device displays the received advice message and informs the user. Specifically, the smartphone application displays the advice content as a pop-up notification or on the dashboard. This allows the user to receive feedback in real time.

[1462] Step 6:

[1463] The server analyzes user data in real time and notifies store staff to provide immediate fitness-related advice within the physical store. It uses data collected in real time as input, performs analysis and generates advice, and notifies store staff terminals. This allows store staff to understand each customer's individual health status and provide immediate, specific fitness guidance and health management.

[1464] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1465] The present invention is a system that provides personalized health and fitness advice by combining data collected from a wearable device with an emotion engine that recognizes the user's emotions. Specific embodiments of the system of the present invention will be described in detail below.

[1466] System Configuration

[1467] Data collection

[1468] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from the user's wearable device. For example, data is sent from the wearable device to the server at regular intervals each day. This data includes the total number of steps taken per day, average heart rate, and sleep duration.

[1469] Data preprocessing

[1470] The server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[1471] Data analysis

[1472] The server analyzes the user's health status based on pre-processed data. Using regression analysis and clustering techniques, it analyzes and predicts the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts the amount of exercise for the next 30 days based on exercise data from the past 30 days and identifies areas for improvement.

[1473] Implementation of an emotion engine

[1474] The server also features an emotion engine. This emotion engine recognizes the user's emotions using voice, facial expressions, and text data. For example, it uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and uses an emotion recognition algorithm to identify the user's current emotional state.

[1475] Generating advice

[1476] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it will recommend relaxation exercises. Also, if the server detects that the user is agitated on a day with a high heart rate, it will provide advice to adjust the amount of exercise.

[1477] Notification to the user

[1478] The server notifies the user's device of the advice it has generated. The device analyzes the advice message received from the server and displays it through the user interface. For example, a smartphone app can display pop-up notifications or a dashboard to allow the user to quickly check the advice.

[1479] Providing a customized exercise plan

[1480] Users can request a customized exercise plan from an expert through the app. They enter their specific request details into a form and submit it to the server. The server forwards this request to an expert, who designs a customized exercise plan based on the user's request. This exercise plan is then provided to the user again via the server. For example, the plan might include specific details such as "perform 30 minutes of aerobic exercise three times a week."

[1481] Specific example

[1482] Data Acquisition and Preprocessing

[1483] The server collects the following data from the user's wearable device:

[1484] Step count: 8000 steps

[1485] Average heart rate: 75 bpm

[1486] Sleep duration: 7 hours

[1487] Data Analysis

[1488] The server analyzes the pre-processed data and obtains the following conclusions:

[1489] The number of steps taken has not reached the target of 10,000 steps.

[1490] The average heart rate is within a moderate range.

[1491] Sleep duration is within the recommended range of 7-8 hours.

[1492] emotion recognition

[1493] The emotion engine uses the smartphone's camera and microphone to analyze the user's facial expressions and voice, recognizing when the user is experiencing stress.

[1494] Generating advice

[1495] The server considers both health and emotional state to generate the following advice:

[1496] "Your step count today is 8,000 steps, which is short of your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[1497] "Your heart rate is within the normal range. Please continue to manage your health at this pace."

[1498] "Your sleep duration is 7 hours, which is within the recommended range. Please maintain good sleep habits."

[1499] Advice notification

[1500] The server sends the generated advice to the device, and the user can check the advice through a smartphone app.

[1501] Customized exercise plan

[1502] When a user requests a customized exercise plan from an expert, the server forwards the request to the expert, who then provides the user with the designed exercise plan. For example, a specific plan such as "a 30-minute strength training session three times a week" might be provided.

[1503] As described above, the present invention is a system that combines data obtained from a wearable device with the user's emotions to provide more highly personalized health management and fitness support.

[1504] The following describes the processing flow.

[1505] Step 1:

[1506] The server collects data from wearable devices. Specifically, the server uses the device API to periodically send data retrieval requests to obtain vital data such as exercise capacity (steps, activity level), sleep habits (sleep duration, sleep quality), and heart rate. For example, it might be configured to collect the previous day's data at midnight every day.

[1507] Step 2:

[1508] The server preprocesses the collected data. First, it denoises the data, filtering out, for example, extremely high step counts or abnormal heart rates. Next, it normalizes the data to ensure consistency as time-series data. For example, it imputes missing data with the mean.

[1509] Step 3:

[1510] The server analyzes the user's health status based on pre-processed data. Specifically, it uses machine learning algorithms (regression analysis and clustering) to analyze and predict the user's exercise capacity, sleep patterns, and heart rate trends. For example, it applies an algorithm that predicts the amount of exercise for the next 30 days based on data from the past 30 days and proposes an appropriate exercise plan.

[1511] Step 4:

[1512] The server recognizes the user's emotions through an emotion engine. The emotion engine uses the smartphone's camera and microphone to collect the user's facial and voice data and analyze their emotions. For example, when the user opens the app, the camera captures their facial expression and the voice response is obtained.

[1513] Step 5:

[1514] The server integrates health status analysis results with emotional data recognized by the emotion engine to generate personalized health and fitness advice. For example, if a user is not getting enough exercise and is feeling stressed, it will generate advice recommending "taking a light walk to relax."

[1515] Step 6:

[1516] The server then notifies the user's device of the advice it has generated. Specifically, it generates a notification message and sends a push notification to the user's smartphone app using Firebase Cloud Messaging (FCM) or Apple Push Notification Service (APNs). For example, it might send a message such as, "Your exercise level today did not meet your goal. We recommend a light, relaxing walk."

[1517] Step 7:

[1518] The device analyzes advice messages received from the server and displays them in the user interface. Specifically, it displays them as pop-up messages in the smartphone's notification bar or shows detailed advice in the in-app dashboard. For example, it might display specific suggestions such as "Today's activity level: 8,000 steps / 10,000 steps" and "Perform relaxation exercises."

[1519] Step 8:

[1520] Users can request a customized exercise plan from an expert through the app. For example, they can enter "I want to increase my strength training" into the request form within the app and press the submit button.

[1521] Step 9:

[1522] The server receives the user's request and forwards it to an expert. The expert customizes the exercise plan based on the request. For example, they might create a program recommending "30 minutes of strength training three times a week."

[1523] Step 10:

[1524] The server then notifies the user's device again of the customized exercise plan received from the expert. The user can then view the new exercise plan through a smartphone app. For example, the app's dashboard might display a "Strength Training Plan" with specific exercises to be done three times a week.

[1525] In this way, this system, which incorporates an emotion engine, provides more personalized health and fitness support based on multifaceted data analysis that includes the user's emotional state.

[1526] (Example 2)

[1527] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1528] Traditional health and fitness management systems can collect users' biometric data and assess their basic health status, but they have limitations in generating personalized advice. Furthermore, advice provided without considering the user's emotional state is less effective. Additionally, users must manually request customized exercise plans from professionals, which is time-consuming and inconvenient. There is a need to address these challenges and provide more detailed and personalized health and fitness support.

[1529] The identification processing 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 means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health status using the preprocessed data; means for generating personalized health and fitness advice based on the analysis results and emotion recognition; and means for notifying the user's terminal of the generated advice and customized exercise plan. This enables the user to receive more detailed and personalized advice that comprehensively considers their health status and emotional state. Furthermore, the request and provision of customized exercise plans by experts are automated, reducing the burden on the user.

[1530] A "wearable device" is a device that is worn on a user's body to collect biometric data. Examples include smartwatches and fitness trackers.

[1531] "Physical ability" refers to data that indicates the user's physical activity performance. Specifically, it includes steps taken, distance traveled, calories burned, and so on.

[1532] "Sleep habits" refers to data that shows a user's sleep patterns and sleep quality. Specifically, it includes sleep duration, percentage of deep sleep, and number of sleep interruptions.

[1533] "Heart rate" is data that indicates the number of times a user's heart beats. It is usually expressed as heart rate per minute (bpm).

[1534] "Preprocessing" refers to data processing to convert collected biological data into an analyzable format. Specifically, this includes noise reduction, outlier filtering, and data normalization.

[1535] "Health status" refers to data that indicates the user's overall physical condition and level of health. This is comprehensively evaluated from multiple data points, such as exercise capacity, sleep habits, and heart rate.

[1536] "Emotion recognition" is a technology that identifies a user's emotional state using voice, facial expression, and text data. Specifically, it collects data using a smartphone's camera and microphone and analyzes it using algorithms.

[1537] "Personalized health and fitness advice" refers to specific, tailored guidance and recommendations provided to each individual, taking into account their health and emotional state.

[1538] A "device" is an electronic device that a user can operate. Examples include smartphones, tablets, and personal computers.

[1539] A "customized exercise plan" is an exercise plan designed based on the user's specific needs and goals. It is created by a specialist in response to the user's request.

[1540] A "specialist" is someone who possesses knowledge and experience regarding the user's health and fitness. Examples include trainers and nutritionists.

[1541] "Notifications" refer to the act of delivering generated advice or customized exercise plans to the user's device. Specifically, this includes pop-up notifications and dashboard displays.

[1542] Modes for carrying out the invention

[1543] This invention is a system that provides personalized health and fitness advice by combining data collected from wearable devices with an emotion engine that recognizes the user's emotions. This system is implemented using the following hardware and software.

[1544] Data collection

[1545] The server periodically collects biometric data such as exercise capacity, sleep habits, and heart rate from wearable devices (e.g., smartwatches, fitness trackers). The collection process involves the wearable device sending data to the server at regular intervals each day. For example, at 6 AM every morning, a day's worth of data (steps, average heart rate, sleep duration, etc.) is collected.

[1546] Data preprocessing

[1547] The server preprocesses the collected data. This process includes noise reduction, outlier filtering, and data normalization. For example, it removes or interpolates data points where the average heart rate is extremely high (above 150 bpm) or low (below 40 bpm).

[1548] Data analysis

[1549] The server analyzes the pre-processed data. The analysis steps include predicting health status using regression analysis and clustering techniques, and analyzing trends in exercise capacity, sleep patterns, and heart rate. For example, based on exercise data from the past 30 days, it sets exercise goals for the next 30 days and identifies areas for improvement.

[1550] Implementation of an emotion engine

[1551] The server uses an emotion engine to recognize the user's emotions based on voice, facial expressions, and text data. The emotion engine uses the smartphone's camera and microphone to collect the user's facial expressions and voice, and analyzes them with an emotion recognition algorithm. For example, while the user is using their smartphone, the camera captures their facial expressions and audio data is collected to determine whether the user is experiencing stress.

[1552] Generating advice

[1553] The server generates personalized health and fitness advice based on the analysis of the user's health status and the emotions recognized by the emotion engine. For example, if the user is feeling stressed, it recommends relaxation exercises, and if a lack of exercise is detected, it suggests a light jog. Specific advice might include messages such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so we recommend a light walk."

[1554] Advice notification

[1555] The server notifies the user's device of the generated advice. The device analyzes the received advice message and displays it through the user interface. For example, a smartphone app might display a pop-up notification so that the user can quickly check the advice.

[1556] Customized exercise plan

[1557] Users can request a customized exercise plan from an expert through the app. They enter their request details into a form and submit it to the server. This information is forwarded to the expert, who designs an exercise plan tailored to the user's specific needs. The designed exercise plan is then provided to the user again via the server. For example, a specific plan such as "30-minute strength training sessions three times a week" might be provided.

[1558] Specific examples and prompt statements

[1559] Specific example

[1560] Data Collection: The server collects a day's worth of data from wearable devices every morning at 6:00 AM (steps: 8,000, average heart rate: 75 bpm, sleep time: 7 hours).

[1561] Data preprocessing: The server removes outliers where the heart rate exceeds 150 bpm.

[1562] Data analysis: Set exercise goals for the next 30 days based on exercise data from the past 30 days.

[1563] Emotion recognition: The system uses the smartphone's camera to recognize when the user is experiencing stress.

[1564] Advice generation: Generates the advice: "Your step count today is 8000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[1565] Advice Notification: The server sends the generated advice to the user's smartphone and displays it as a pop-up notification.

[1566] Customized Exercise Plan: Users request a "30-minute strength training plan, 3 times a week," and experts design and provide it.

[1567] Examples of prompt statements

[1568] "Create a program that recognizes the user's emotions and provides health advice based on them. For example, include a feature that recommends relaxation exercises if the user is feeling stressed."

[1569] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1570] Step 1: Data Collection

[1571] The server collects biometric data from the user's wearable device.

[1572] Input: Exercise capacity, sleep habits, and heart rate data transmitted from wearable devices.

[1573] Specific operation: For example, request and receive a day's worth of data (steps, average heart rate, sleep duration) from a Fitbit or smartwatch at 6 AM every morning.

[1574] Output: Collected biometric data (e.g., total daily steps 8000, average heart rate 75 bpm, sleep duration 7 hours).

[1575] Step 2: Data preprocessing

[1576] The server preprocesses the collected data.

[1577] Input: Collected biometric data.

[1578] Specific operations: Noise reduction, outlier filtering, and data normalization. For example, it detects and removes outliers such as an average heart rate exceeding 150 bpm. It also imputes missing data points.

[1579] Output: Preprocessed data.

[1580] Step 3: Data Analysis

[1581] The server analyzes the pre-processed data.

[1582] Input: Pre-processed data.

[1583] Specific actions: Using regression analysis and clustering techniques, the system analyzes the user's exercise capacity, sleep patterns, and heart rate trends. For example, it predicts exercise levels for the next 30 days using data from the past 30 days.

[1584] Output: Analysis results and health status prediction.

[1585] Step 4: Emotion Recognition

[1586] The server uses an emotion engine to recognize the user's emotions.

[1587] Input: Voice, facial expressions, and text data collected from the smartphone's camera and microphone.

[1588] Specific operation: The smartphone camera is activated, and the user's facial expression and voice data are collected in real time and analyzed using an emotion recognition algorithm. For example, it can determine whether the user is experiencing stress.

[1589] Output: User's emotional state (e.g., stress).

[1590] Step 5: Generating Advice

[1591] The server generates personalized advice based on the analysis of health status and the recognition of emotions.

[1592] Input: Analysis results and emotional state.

[1593] Specific actions: For example, create advice such as, "Your step count today is 8,000 steps, which is below your goal. You seem to be feeling stressed, so I recommend taking a light walk."

[1594] Output: Generated advice message.

[1595] Step 6: Advice Notification

[1596] The server notifies the user's terminal of the generated advice.

[1597] Input: Generated advice message.

[1598] Specific actions: Send an advice message to the device and display it to the user through a pop-up notification or dashboard display. For example, display a notification via a smartphone app.

[1599] Output: Advice displayed to the user.

[1600] Step 7: Customized Exercise Plan

[1601] Users can request a customized exercise plan from an expert through the app.

[1602] Input: User request information (specific needs and goals).

[1603] Specific operation: Enter information into the request form within the app and send it to the server. The server forwards the request to an expert, who designs an exercise plan based on the user's needs. For example, a "30-minute strength training plan three times a week" might be created.

[1604] Output: A customized exercise plan is provided to the user.

[1605] (Application Example 2)

[1606] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1607] Traditional health management systems primarily focused on collecting and analyzing biometric data such as users' exercise capacity, sleep habits, and heart rate to provide fitness advice. However, they lacked personalization because they did not take into account the user's emotional state. Furthermore, they lacked suggestions for suitable meal plans in addition to health management. As a result, comprehensive health management and improvements in fitness and dietary habits were difficult.

[1608] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting data on exercise ability, sleep habits, and heart rate from a wearable device; means for preprocessing the data; means for analyzing the user's health and emotional state using the preprocessed data; means for generating personalized health and fitness advice based on the analyzed data; and means for notifying the user's terminal of the generated advice and suggesting meal menus based on the progress. This enables comprehensive health management that takes into account both the user's health and emotional state, and meal suggestions that are appropriate to the user's health state.

[1609] A "wearable device" is an electronic device that an individual can wear to collect biometric data such as athletic ability, sleep habits, and heart rate.

[1610] "Emotional state" refers to data that indicates the emotions and psychological state a user is experiencing at a specific time.

[1611] "Preprocessing" refers to the process of applying noise reduction, filtering outliers, and normalizing data to biometric data collected from wearable devices.

[1612] "Health status" refers to data that indicates the user's physical and physiological condition, including exercise capacity, sleep patterns, and heart rate.

[1613] "Fitness advice" refers to specific suggestions and guidance regarding exercise, diet, and rest to improve the user's health.

[1614] The "meal menu" is a list that suggests balanced meals based on the user's health and emotional state.

[1615] "Progress" refers to data that shows changes and progress in the user's health status.

[1616] A "customized exercise plan by an expert" is an exercise plan designed by an expert based on the individual user's health condition and goals.

[1617] Regression analysis is a statistical method that models the relationships between numerical data and is used to predict specific health conditions.

[1618] Clustering is a data analysis technique that groups data based on similarity and is used to identify user health patterns.

[1619] A "prompt sentence" is text input into a generative AI model that contains instructions for generating specific information or answers.

[1620] This invention is a system that analyzes data collected from a wearable device and the user's emotional state to provide personalized health and fitness advice and meal menus. Specific embodiments of this system are described in detail below.

[1621] First, the server collects data on exercise capacity, sleep habits, and heart rate from wearable devices. Wearable devices such as Apple Watch, Fitbit, and Garmin can be used. The data collected from these devices is sent to the server at regular intervals.

[1622] Next, the server preprocesses the collected data. Specifically, it performs noise reduction, filters outliers, and normalizes the data. For example, if the average heart rate is extremely high or low, it will be removed or interpolated.

[1623] Based on the pre-processed data, the server analyzes the user's health and emotional state. The emotional state is analyzed using an emotion engine. This emotion engine uses tools such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect the user's facial expressions and voice data through the smartphone's camera and microphone.

[1624] The server then generates personalized health and fitness advice based on the analysis results. It also suggests appropriate meal plans, taking into account the user's health and emotional state. For example, if data from a wearable device indicates that the user's heart rate is low and that calorie intake is needed, the server will suggest a meal plan suitable for energy replenishment.

[1625] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed to be intuitive and easy to use, allowing users to quickly check the advice and meal menus through pop-up notifications and dashboard displays.

[1626] As a concrete example, a notification using the following prompt statement can be considered:

[1627] "Based on your health and mood today, here are our recommended dishes: a healthy salad and lean grilled chicken. Would you like to order?"

[1628] Furthermore, users can request customized exercise and meal plans from experts through the app. These requests are sent to experts via the server, and the plans provided by the experts are then notified to the user via the server.

[1629] As described above, the system of the present invention provides comprehensive health management that takes into account both the user's physical and emotional state, as well as personalized fitness and dietary suggestions.

[1630] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1631] Step 1:

[1632] The server collects biometric data from wearable devices regarding exercise capacity, sleep habits, and heart rate. Specifically, data is sent from devices such as Apple Watch, Fitbit, and Garmin at regular intervals.

[1633] Input: Biometric data related to athletic ability, sleep habits, and heart rate

[1634] Output: Unprocessed biometric data

[1635] Step 2:

[1636] The server preprocesses the collected biometric data. Specifically, it performs noise reduction (elimination of false values), filtering of outliers, and normalization of the data. For example, it removes or interpolates extremely high or low heart rate values.

[1637] Input: Unprocessed biometric data

[1638] Output: Preprocessed data

[1639] Step 3:

[1640] The server analyzes the user's health status using pre-processed data. Specifically, it analyzes data trends using regression analysis and clustering techniques to predict and evaluate health status.

[1641] Input: Preprocessed data

[1642] Output: Analysis results of health status

[1643] Step 4:

[1644] The server uses an emotion engine to analyze the user's emotional state. The emotion engine utilizes technologies such as OpenCV, Google Cloud Vision API, and Microsoft Azure Face API to collect facial and audio data through the smartphone's camera and microphone.

[1645] Input: Facial and voice data collected from a smartphone.

[1646] Output: Emotional state evaluation results

[1647] Step 5:

[1648] The server combines the results of health status analysis and emotional state assessment to generate personalized health and fitness advice. It also suggests appropriate meal plans based on this advice.

[1649] Input: Analysis results of health status and evaluation results of emotional status

[1650] Output: Personalized health advice and meal plans

[1651] Step 6:

[1652] The generated advice and meal menus are notified to the user's device (smartphone app). The user interface is designed for ease of use and provides information quickly to the user through pop-up notifications and dashboard displays.

[1653] Input: Personalized health advice and meal plans

[1654] Output: Notification to smartphone app

[1655] Step 7:

[1656] Users can request customized exercise and meal plans from experts through a smartphone app. The request is sent to the expert via a server, and the provided plan is then notified to the user via the server.

[1657] Input: User request for customization plan

[1658] Output: Provision of customized plans by experts and notifications

[1659] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1660] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1661] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1662] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1663] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1664] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1665] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1666] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1667] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1668] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1669] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1670] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1671] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1672] 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.

[1673] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1674] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1675] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1676] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1677] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1678] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1679] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1680] The following is further disclosed regarding the embodiments described above.

[1681] (Claim 1)

[1682] A means of collecting data on exercise capacity, sleep habits, and heart rate from wearable devices,

[1683] Means for preprocessing the aforementioned data,

[1684] A means of analyzing a user's health status using pre-processed data,

[1685] A means for generating personalized health and fitness advice based on analysis results,

[1686] A means of notifying the user's device of the generated advice,

[1687] A system that includes this.

[1688] (Claim 2)

[1689] The system according to claim 1, further comprising means for providing a customized exercise plan by an expert based on the user's request.

[1690] (Claim 3)

[1691] The system according to claim 1, characterized in that the analysis means predicts health status using regression analysis and clustering.

[1692] "Example 1"

[1693] (Claim 1)

[1694] A means of collecting biometric data from wearable devices,

[1695] Means for preprocessing the aforementioned biological data,

[1696] A means for analyzing the user's health status using pre-processed data,

[1697] A means for generating individual health and exercise advice based on the analyzed results,

[1698] A means of notifying the user's device of the generated advice,

[1699] A system that includes this.

[1700] (Claim 2)

[1701] The system according to claim 1, further comprising means for providing a customized exercise plan by an expert based on the user's requirements.

[1702] (Claim 3)

[1703] The system according to claim 1, characterized in that the analysis means predicts health status using statistical methods.

[1704] "Application Example 1"

[1705] (Claim 1)

[1706] A means of collecting data on exercise capacity, sleep habits, and heart rate from wearable devices,

[1707] Means for preprocessing the aforementioned data,

[1708] A means of analyzing a user's health status using pre-processed data,

[1709] A means for generating personalized health and fitness advice based on analysis results,

[1710] A means of notifying the user's device of the generated advice,

[1711] A means of understanding each customer's health condition within a physical store and providing immediate fitness-related advice,

[1712] A system that includes this.

[1713] (Claim 2)

[1714] The system according to claim 1, further comprising means for providing a customized exercise plan by an expert based on the user's request.

[1715] (Claim 3)

[1716] The system according to claim 1, characterized in that the analysis means predicts health status using regression analysis and clustering.

[1717] "Example 2 of combining an emotion engine"

[1718] (Claim 1)

[1719] A means of collecting data on exercise capacity, sleep habits, and heart rate from wearable devices,

[1720] Means for preprocessing the aforementioned data,

[1721] A means of analyzing a user's health status using pre-processed data,

[1722] A means for generating personalized health and fitness advice based on analysis results and emotional recognition,

[1723] A means for notifying the user's terminal of the generated advice and customized exercise plan,

[1724] A system that includes this.

[1725] (Claim 2)

[1726] The system according to claim 1, further comprising means for providing a customized exercise plan by an expert based on the user's request.

[1727] (Claim 3)

[1728] The system according to claim 1, characterized in that the analysis means predicts health status using regression analysis and clustering.

[1729] "Application example 2 when combining with an emotional engine"

[1730] (Claim 1)

[1731] A means of collecting data on exercise capacity, sleep habits, and heart rate from wearable devices,

[1732] Means for preprocessing the aforementioned data,

[1733] A means for analyzing a user's health and emotional state using pre-processed data,

[1734] A means for generating personalized health and fitness advice based on analyzed data,

[1735] A means of notifying the user's device of the generated advice and suggesting meal menus based on the progress,

[1736] A system that includes this.

[1737] (Claim 2)

[1738] The system according to claim 1, further comprising means for providing a customized exercise plan and meal plan by an expert based on the user's request.

[1739] (Claim 3)

[1740] The system according to claim 1, characterized in that the analysis means predicts health status and emotional status using regression analysis and clustering. [Explanation of Symbols]

[1741] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting data on exercise capacity, sleep habits, and heart rate from wearable devices, Means for preprocessing the aforementioned data, A means of analyzing a user's health status using pre-processed data, A means for generating personalized health and fitness advice based on analysis results, A means of notifying the user's device of the generated advice, A system that includes this.

2. The system according to claim 1, further comprising means for providing a customized exercise plan by an expert based on the user's request.

3. The system according to claim 1, characterized in that the analysis means predicts health status using regression analysis and clustering.

Images