System

Abstract

A system is provided.SOLUTION: A system comprising: a wearable device; and a server, wherein the wearable device is configured to collect physiological information of a user; the server is configured to receive the physiological information from the wearable device and store the physiological information in a database; the server is configured to predict a physical condition of the user using a generative AI model; the server is configured to generate an advice for improving a health condition of the user based on the predicted physical condition.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional health management systems have difficulty comprehensively predicting a user's physical condition and providing specific advice for improvement. Furthermore, with the increase in remote work, it has been difficult for companies to grasp the health status of their employees and provide measures to improve employee benefits. Therefore, both individuals and companies have a strong demand for more effective and efficient ways to manage and improve their health. [Means for solving the problem]

[0005] This invention provides a system that uses a wearable device, a terminal, and a server to comprehensively manage a user's physiological data and lifestyle data, and provides health predictions and advice on how to improve the user's condition. Specifically, the wearable device collects the user's physiological data, the terminal integrates the physiological data collected from the wearable device with dietary data and diary data entered by the user to generate transmission data, and the server receives the transmission data and stores it in a database. Furthermore, the server predicts the user's health using a generative AI model, generates specific advice for improving the user's health based on the prediction results, and notifies the terminal. For companies, the system also includes a means for aggregating employee health data and providing measures to improve employee benefits, enabling effective employee health management.

[0006] A "wearable device" is an electronic device worn by a user that collects physiological data such as heart rate, exercise volume, and sleep information.

[0007] "Physiological data" is a general term for data that indicates the user's physical condition, such as heart rate, amount of exercise, and sleep information.

[0008] A "terminal" is an electronic device, such as a smartphone or tablet, that receives data from a wearable device and processes information, including data entered by a user.

[0009] "Dietary data" is data that indicates the contents and times of meals consumed by the user.

[0010] "Diary data" is data entered by the user that records the user's physical condition, stress level, activities, and so on for that day.

[0011] "Transmitted data" refers to a data packet in which physiological data, dietary data, and diary data from the wearable device are integrated by the terminal.

[0012] The "server" is a computer system that receives data sent from the device, stores it in a database, and uses a generative AI model to predict physical condition and generate advice.

[0013] A "database" is a system provided on a server for efficiently storing and managing data.

[0014] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to predict a user's physical condition and generate advice for improving their health.

[0015] "Health prediction" is the process of using a generative AI model to predict a user's health condition for the current day and the next day.

[0016] "Advice" refers to specific instructions or recommendations for improving health status that are generated by the server based on the results of health prediction.

[0017] "Incremental learning" is the process by which a generative AI model learns from new data over time, improving its predictive accuracy.

[0018] "Corporate welfare benefits" is a general term for the systems and programs for health management and lifestyle support that companies provide to their employees.

[0019] "Health data" is a general term for data related to a user's health condition and lifestyle habits, such as physiological data, dietary data, and diary data. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0025] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0028] [First embodiment]

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

[0030] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0037] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[0042] Overall system configuration

[0043] Wearable devices

[0044] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[0045] Terminal

[0046] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the dietary and diary data entered by the user. This application integrates the physiological data received from the wearable device and the dietary and diary data entered by the user, and prepares it for transmission to the server.

[0047] server

[0048] The server receives data sent from the device and stores it in a database. Based on the stored data, a generative AI model is used to predict the user's physical condition and generate specific advice for improvement.

[0049] Program processing

[0050] Data collection and integration

[0051] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application running on the device receives this data, and also incorporates dietary and diary data entered by the user, and combines them to generate a single transmission data packet.

[0052] Sending data

[0053] The terminal sends the generated transmission data to the server automatically, but the user can also trigger the transmission manually if necessary.

[0054] Data storage and analysis

[0055] The server stores the received data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[0056] Advice generation and notification

[0057] The server generates specific advice to improve the user's health based on the results of the health prediction. The advice is sent to the device, which then notifies the user via push notification or in-app message. This allows the user to take actions that will contribute to improving their lifestyle the next day.

[0058] Specific examples

[0059] Example 1: For a general user

[0060] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. At night, the device consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you go to bed early and relax today," and the device notifies User A of this advice.

[0061] Example 2: For a company

[0062] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0063] The above is a specific embodiment for carrying out the present invention. This system can provide more effective health management and improvement for both individual users and companies.

[0064] The processing flow will be explained below.

[0065] Step 1:

[0066] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[0067] Step 2:

[0068] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[0069] Step 3:

[0070] The terminal periodically receives data from the wearable device and temporarily stores it. An application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[0071] Step 4:

[0072] The user uses an application on the device to input diary data about the day's diet and physical condition, specifically, what they ate for breakfast, lunch, and dinner, as well as changes in their mood.

[0073] Step 5:

[0074] The terminal combines the physiological data received from the wearable device with the dietary and diary data entered by the user to generate a single transmission data packet, which includes time series information and the user ID.

[0075] Step 6:

[0076] The terminal transmits the generated transmission data to the server. This transmission is usually automatic, but can also be triggered manually by the user.

[0077] Step 7:

[0078] The server stores the received data in a database using encryption technology to ensure data security.

[0079] Step 8:

[0080] The server uses a generative AI model to analyze the data stored in the database, which uses machine learning algorithms to predict the user's physical condition.

[0081] Step 9:

[0082] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[0083] Step 10:

[0084] The server predicts the user's health condition for the next day based on the predicted physical condition and generates specific advice for improving health, such as ensuring adequate sleep and recommending light exercise.

[0085] Step 11:

[0086] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[0087] Step 12:

[0088] The server analyzes the aggregated employee health data and generates reports for companies, including recommendations for improving employee benefits, which can be used to support corporate health management programs.

[0089] Example 1

[0090] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0091] In modern society, individuals are in need of ways to efficiently manage and improve their own health. However, conventional systems have difficulty integrating users' physiological data, dietary data, and diary data to provide health predictions and health improvement advice. Furthermore, companies lack systems that can effectively monitor the health status of their employees and provide improvement measures for employee benefits.

[0092] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0093] In this invention, the server includes a means for automatically or manually transmitting user data from the device to the server, a means for successively training the generative AI model based on new data to improve prediction accuracy, and a means for notifying the user of the generated advice via push notification or in-app message. This allows users to centrally manage their own physiological data, dietary data, and diary data and easily receive health predictions and health improvement advice. Companies can also aggregate employee health data and provide employee benefit improvement measures based on their health status.

[0094] A "wearable device" is a portable device used to collect physiological data such as a user's heart rate, exercise volume, and sleep information.

[0095] A "terminal" is an electronic device that has the function of receiving data from a wearable device, integrating the dietary data and diary data entered by the user, and transmitting the data to a server.

[0096] "Physiological data" is data that indicates the physiological state of the body, such as the user's heart rate, amount of exercise, and sleep time.

[0097] "Dietary data" refers to data that indicates information about the contents of meals consumed by the user.

[0098] "Diary data" is data entered by the user that records the user's physical condition and activities for that day.

[0099] "Transmission data" refers to data generated by integrating physiological data collected by the terminal from the wearable device, dietary data entered by the user, and diary data.

[0100] The "server" is a device that receives data sent from the device, stores it in a database, and uses a generative AI model to generate health predictions and health improvement advice.

[0101] A "database" is a collection of information that allows a server to systematically manage and store data received.

[0102] A "generative AI model" is an artificial intelligence model that generates predictions about a user's physical condition and health advice based on stored data.

[0103] "Health prediction" refers to the use of a generative AI model to predict a user's current and future health status.

[0104] "Advice for improving health condition" refers to specific suggestions and instructions for improving the user's health that are provided based on the predicted physical condition.

[0105] "Incremental learning" is the process by which a generative AI model incorporates new data and learns repeatedly to improve its prediction accuracy.

[0106] "Push notification" is a feature that allows an application to send a message directly to a user's device and provide specific information.

[0107] "Automatic transmission" is a function that allows a terminal to automatically transmit data to a server based on specific times or conditions.

[0108] "Manual transmission" is a function that allows the terminal to transmit data to the server in response to a user operation.

[0109] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[0110] Overall system configuration

[0111] The embodiment for implementing this system is configured as follows.

[0112] Wearable devices

[0113] Users wear wearable devices to collect physiological data such as heart rate, exercise volume (number of steps), and sleep information (quality and duration). The devices synchronize data with a terminal via Bluetooth or Wi-Fi. Specifically, users wear small devices (e.g., smartwatches) that fit on their wrists and can collect data throughout the day.

[0114] Terminal

[0115] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the meal data and diary data entered by the user. This application integrates the physiological data received from the wearable device with the meal data and diary data entered by the user and prepares it to be sent to the server. For example, when a user enters "Breakfast: tamagoyaki, salad, coffee" into the app, the meal data is imported.

[0116] server

[0117] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition and generate specific advice for improving their health. Furthermore, the server can continuously train the generative AI model based on new data to improve prediction accuracy. For example, it can generate advice such as, "Based on yesterday's data, you should increase your exercise today."

[0118] Specific examples

[0119] An embodiment of the system will be specifically described below.

[0120] Example 1: For a general user

[0121] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives this data from the wearable device, and User A enters a diary entry about the day's meals and physical condition into the app. That night, the device consolidates this data and sends it to the server. Late at night, the server stores the received data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you drink plenty of water and do some light exercise today," and the device notifies User A of this advice.

[0122] Example 2: For a company

[0123] All employees of a company wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report suggesting improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0124] Prompt Sentence Examples

[0125] Below are some example prompts that can be used as input to a generative AI model:

[0126] "User A's average heart rate yesterday was 60 beats per minute, the number of steps taken was 8,000, and the amount of sleep was 7 hours. Please predict his / her physical condition today and generate appropriate health improvement advice."

[0127] "Use employee health data to suggest ways to improve employee benefits for companies."

[0128] This system can provide more effective health management and improvement for both individuals and businesses.

[0129] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0130] Step 1: Data collection

[0131] The user wears a wearable device to collect physiological data such as heart rate, exercise amount (number of steps), and sleep information. The input data includes heart rate, number of steps, and sleep information.

[0132] The wearable device collects this physiological data 24 hours a day and stores it in its internal memory. Specifically, the device measures heart rate at regular intervals and calculates the amount of exercise.

[0133] Step 2: Synchronize data

[0134] The terminal periodically synchronizes with the wearable device via Bluetooth or Wi-Fi and receives the collected physiological data. The input is physiological data from the wearable device, and the output is data stored in a database within the terminal.

[0135] Specifically, the terminal starts communicating with the wearable device every hour and downloads new data to the terminal.

[0136] Step 3: Entering food and diary data

[0137] The user uses an application installed on their smartphone to enter diary data about their diet and their physical condition for that day. The input is done manually by the user, and the output is saved in a database on the device.

[0138] As a concrete example, a user enters "Breakfast: toast, coffee" into a text field in an app.

[0139] Step 4: Integrate the data

[0140] The terminal integrates physiological data received from the wearable device and dietary and diary data entered by the user. The inputs are physiological data, dietary data, and diary data, and the output is an integrated data packet.

[0141] Specifically, the application in the device organizes each piece of data in chronological order and packs it into a single JSON data packet.

[0142] Step 5: Sending data

[0143] The terminal automatically transmits the combined data packet to the server, or the user can transmit it manually. The input is the combined data packet, and the output is the completion status of transmission to the server.

[0144] For example, a scheduled job runs overnight and sends a data packet as an HTTP POST request to a server's API endpoint.

[0145] Step 6: Save your data

[0146] The server stores the received data packet in a database. The input is the data packet from the terminal, and the output is the status of successful storage in the database.

[0147] Specifically, the server-side script receives the received data and performs an INSERT operation on the database.

[0148] Step 7: Analyze the data

[0149] The server uses the stored data as input to run the generative AI model and analyze the user's physical condition prediction and health status. The input is the data stored in the database, and the output is the physical condition prediction result.

[0150] Specifically, the server runs a generative AI model implemented in Python as a scheduled task, and calculates a health prediction based on features (e.g., heart rate, amount of exercise, sleep time, etc.).

[0151] Step 8: Generating Advice

[0152] The server generates advice for improving health based on the health prediction results. The input is the health prediction results, and the output is health advice.

[0153] For example, if the AI ​​model predicts that the user is feeling fatigued, the server will generate advice such as, "Try to do some light exercise today and get plenty of rest."

[0154] Step 9: Advice Notification

[0155] The device uses push notification and in-app messaging functions to notify the user of the advice received from the server. The input is the health advice from the server, and the output is the completion status of the notification to the user.

[0156] Specifically, the device's notification system will push a message to the user saying, "Today's advice: Try to do some light exercise and get plenty of rest."

[0157] (Application example 1)

[0158] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0159] Traditionally, employee health management and work efficiency improvement at logistics centers have been limited to fragmented data collection and individual measures, making it difficult to achieve effective and integrated management.In addition, it has been difficult to provide specific advice in real time that responds to changes in each employee's physical condition, resulting in problems that make it difficult to optimize employee performance and health.

[0160] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0161] In this invention, the server includes: means for collecting physiological data of a user using a wearable device; means for generating transmission data by integrating the physiological data collected from the wearable device and dietary data and diary data entered by the user using a terminal; means for receiving the transmission data and storing it in a database; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving health based on the physical condition prediction; means for notifying the terminal of the generated advice; and means for collecting physiological data, dietary data, and work records of employees at a logistics center and providing a physical condition prediction and advice for improving work performance based on the generative AI model. This makes it possible to individually manage the physical condition and work performance of each employee working at a logistics center and provide specific advice for improving health and work efficiency in real time.

[0162] A "wearable device" is a device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[0163] A "terminal" is a device that receives physiological data from a wearable device, imports dietary data and diary data entered by the user, and is an electronic device such as a smartphone or tablet that integrates this data to generate transmission data.

[0164] "Transmission data" refers to a data packet generated by integrating physiological data, dietary data, and diary data collected from the wearable device and the terminal, and is the entire data transmitted to the server.

[0165] The "server" is a computer system that receives data sent from the device, stores the data in a database, uses a generative AI model to predict the user's physical condition, and generates advice for improving their health.

[0166] The "generative AI model" is an artificial intelligence model that predicts a user's physical condition based on collected physiological data, dietary data, and diary data, and generates appropriate health improvement advice.

[0167] "Health prediction" is the process of using a generative AI model to predict a user's current and future health status, and to identify changes and risks in health based on analyzed data.

[0168] "Advice generation" is the process of generating specific guidelines and suggestions for improving the user's health based on the results of the health prediction.

[0169] A "logistics center" is a facility where operations such as storing, sorting, and preparing products for delivery are carried out, and is a work environment where employees work intensively.

[0170] "Employee physiological data" refers to physical data about employees, such as heart rate, activity level, and sleep information, that is collected by wearable devices.

[0171] "Work performance improvement advice" refers to specific suggestions and instructions for improving work efficiency and job performance based on employees' physiological data and work records.

[0172] This invention is a system aimed at managing the health and performance of employees working at logistics centers. It uses wearable devices, terminals (e.g., smartphones), and a server to collect and integrate employees' physiological data, dietary data, and work records, and uses a generative AI model to predict their physical condition and provide advice to improve their work performance.

[0173] Hardware and software used

[0174] Hardware

[0175] Wearable devices: Collect physiological data such as heart rate, exercise, and sleep information 24 hours a day.

[0176] Smartphone (or tablet): Receives data from the wearable device and runs an application that allows the user to enter food and diary data.

[0177] software

[0178] Server system: Utilizing a database and generative AI models, the system analyzes data and generates health predictions and health improvement advice.

[0179] Database system (e.g. MySQL, MongoDB): stores the data submitted by users.

[0180] Generative AI model (e.g., TensorFlow, PyTorch): Predicts the user's physical condition and generates advice.

[0181] Data collection

[0182] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume, and sleep information. A smartphone app receives this data from the wearable device and also incorporates dietary and diary data entered by the user. This integrated data is sent to a server as a data packet.

[0183] Data analysis

[0184] The server receives the transmitted data and stores it in a database. The generative AI model predicts the user's physical condition based on the stored data and generates specific advice for improving their health. For example, if the user's heart rate is high and the number of steps taken is low, advice such as "Take a break and take a deep breath" will be generated.

[0185] Advice Notice

[0186] The server sends the generated advice to a smartphone app and notifies the user, allowing the user to receive specific advice on improving their health and work efficiency in real time.

[0187] Specific examples

[0188] While User A is working at a logistics center, a wearable device collects data such as a heart rate of 130, steps taken 4,500, and sleep quality of 0.3. User A enters his / her breakfast "salad and yogurt," lunch "chicken and rice," and dinner "fish and vegetables" in a smartphone app, and writes in his / her diary, "I feel good today. Work is going smoothly." Using this data, the server uses a generative AI model to generate specific advice such as "Your heart rate is high, so take a break and take a deep breath. Walk a little more. I recommend you go to bed earlier tonight," and notifies the smartphone.

[0189] Prompt Sentence Examples

[0190] User: 32-year-old male, Occupation: Logistics center worker. Current heart rate: 130, steps: 4500, sleep quality: 0.3.

[0191] Food notes: Breakfast: Salad and yogurt, Lunch: Chicken and rice, Dinner: Fish and vegetables.

[0192] Health diary: I feel good today. Work is progressing smoothly.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] The user wears a wearable device to collect physiological data. Specifically, the wearable device continuously records heart rate, physical activity (number of steps), and sleep information (quality and duration of sleep). This data is sent to a terminal in real time.

[0196] Input: Wearable device

[0197] Output: Physiological data (heart rate, steps, sleep information)

[0198] Step 2:

[0199] The terminal receives physiological data from the wearable device, and at the same time, the user inputs food and diary data using the terminal application, thereby collecting the user's daily health information.

[0200] Input: physiological data, dietary data, diary data

[0201] Output: Integrated data

[0202] Step 3:

[0203] The device combines the physiological data received with the dietary and diary data entered by the user to generate a single data packet for transmission. Specifically, each data field is compiled in a unified format to form a data packet.

[0204] Input: Integrated data

[0205] Output: Transmitted data packets

[0206] Step 4:

[0207] The terminal generates and transmits the transmitted data packets to the server, which can be transmitted in real time or at regular intervals.

[0208] Input: Transmit data packet

[0209] Output: Sending data packet (server side)

[0210] Step 5:

[0211] The server receives the transmitted data packets and stores them in a database, storing each piece of data in a corresponding field along with metadata such as the date and user ID.

[0212] Input: Transmit data packet

[0213] Output: Saved data (database)

[0214] Step 6:

[0215] The server uses the generative AI model to predict physical condition based on the stored data. Specifically, the server inputs the stored physiological data, dietary data, and diary data into the generative AI model and executes the prediction algorithm.

[0216] Input: Stored data (database)

[0217] Output: Health prediction results

[0218] Step 7:

[0219] The server generates specific advice for improving health based on the health prediction results. Using a generative AI model, the prediction results are analyzed and optimal advice is created for the user.

[0220] Input: Health prediction result

[0221] Output: Health improvement advice

[0222] Step 8:

[0223] The server sends the generated advice to the device, which receives it and displays it to the user as a push notification or in-app message.

[0224] Input: Health Improvement Advice

[0225] Output: Advice notified (terminal side)

[0226] The above are the specific processing steps for realizing this invention, which make it possible to manage the physical condition and work performance of each employee working at a logistics center in real time and provide appropriate advice.

[0227] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0228] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[0229] Overall system configuration

[0230] Wearable devices

[0231] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[0232] Terminal

[0233] The terminal (e.g., a smartphone) receives data from the wearable device and runs an application that incorporates the dietary and diary data entered by the user, as well as the emotion data analyzed by the emotion engine. This application then integrates this data and prepares it for transmission to the server.

[0234] Emotion Engine

[0235] The emotion engine analyzes the user's diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis techniques to extract emotions from the diary content.

[0236] server

[0237] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate. Furthermore, the server generates specific advice to improve the user's health.

[0238] Program processing

[0239] Data collection and integration

[0240] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application on the device receives this data and integrates it with dietary data and diary data entered by the user, and emotional data analyzed by an emotion engine.

[0241] Sending data

[0242] The device transmits the consolidated data to the server automatically, but can also be triggered manually by the user.

[0243] Data storage and analysis

[0244] The server stores the received integrated data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and their health condition for the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[0245] Advice generation and notification

[0246] Based on the results of the health prediction, the server generates specific advice to improve the user's health. This advice also takes into account emotional data, so it includes consideration of emotional aspects, such as "Today, it would be good to do some light exercise to change your mood."

[0247] The generated advice is sent to the device, which then notifies the user via push notifications or in-app messages, allowing the user to review and incorporate the advice into their daily lives.

[0248] Specific examples

[0249] Example 1: For a general user

[0250] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[0251] Example 2: For a company

[0252] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. An emotion engine analyzes the diary data and extracts emotional data. The devices send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0253] The above is a specific embodiment of the present invention that combines an emotion engine. This system allows both individual users and companies to more effectively manage and improve their health conditions.

[0254] The processing flow will be explained below.

[0255] Step 1:

[0256] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[0257] Step 2:

[0258] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[0259] Step 3:

[0260] The terminal periodically receives data from the wearable device and temporarily stores it. At the same time, an application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[0261] Step 4:

[0262] The user uses an application on the device to enter diary data about the day's diet and physical condition, specifically recording what they ate for breakfast, lunch, and dinner, as well as changes in their emotions and notable events.

[0263] Step 5:

[0264] The emotion engine analyzes the diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis technology to extract and classify emotions from the diary content.

[0265] Step 6:

[0266] The terminal combines the physiological data received from the wearable device with the dietary data and diary data entered by the user, and the emotional data analyzed by the emotion engine, to generate a single transmission data packet, which includes time series information and the user ID.

[0267] Step 7:

[0268] The terminal sends the generated transmission data packets to the server, usually automatically, but can also be triggered manually by the user.

[0269] Step 8:

[0270] The server stores the received data in a database using encryption technology to ensure data security.

[0271] Step 9:

[0272] The server uses a generative AI model to analyze the data stored in the database. This AI model uses machine learning algorithms to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate.

[0273] Step 10:

[0274] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[0275] Step 11:

[0276] The server predicts the user's health condition for the next day based on the physical condition prediction and generates specific health improvement advice. For example, based on the prediction results, it may generate a suggestion such as "Today, it would be good to incorporate deep breathing and light exercise to relax."

[0277] Step 12:

[0278] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[0279] Step 13:

[0280] The server analyzes the aggregated employee health data and generates reports for companies that include recommendations for improving employee benefits. These reports can be used to support corporate health management programs, and may include recommendations such as introducing yoga classes or meditation sessions.

[0281] The above is the specific processing flow of the system that combines the emotion engine. This system enables more accurate health management and improvement that also takes into account the user's emotional state.

[0282] Example 2

[0283] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0284] In modern society, personal health management and improving corporate employee benefits are important issues. However, conventional health management systems rely on limited information sources, such as physiological and dietary data, making it difficult to provide comprehensive health predictions and advice that reflect users' emotions and daily events. It is also difficult to collect and analyze data in real time and provide appropriate advice to individual users. Furthermore, systems that enable companies to effectively aggregate employee health data and propose measures to improve employee benefits are insufficient.

[0285] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0286] In this invention, the server includes: means for collecting a user's physiological data using a wearable device; means for integrating the physiological data collected from the wearable device and dietary and diary data entered by the user via a terminal, and generating transmission data including emotion data analyzed by an emotion engine; means for transmitting the transmission data to the server; means for receiving the transmission data and storing it in a database; means for using the data stored in the database to use a generative AI model to predict the user's physical condition based on a prompt; means for generating advice for improving the user's health condition based on the predicted physical condition; and means for notifying the terminal of the generated advice. This enables integrated management of a user's personal physiological data, dietary data, diary data, and emotion data, and provides comprehensive health predictions and individual health improvement advice. Furthermore, companies can effectively aggregate employee health data and propose specific data-based improvements to employee benefits.

[0287] A "wearable device" is a device worn by a user that measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via a communication means.

[0288] A "terminal" is a device that manages physiological data collected from a wearable device, as well as dietary data and diary data entered by the user, integrates them to generate transmission data, and transmits this data to a server, including emotional data analyzed by an emotion engine.

[0289] The "emotion engine" is software that analyzes a user's diary data, recognizes their emotional state using text analysis technology, and extracts emotional data.

[0290] The "server" is a system that receives data sent from the device, stores it in a database, predicts physical condition using a generative AI model, generates advice for improving health, and notifies the device.

[0291] "Physiological data" refers to data relating to the user's physical condition, such as heart rate, amount of exercise, and sleep information.

[0292] "Dietary data" refers to data relating to the type, amount, and time of food intake by the user.

[0293] "Diary data" is text data in which a user describes daily events, emotions, physical condition, and the like.

[0294] "Emotion data" is data relating to the user's emotional state that is extracted by the emotion engine by analyzing the diary data.

[0295] A "generative AI model" is an artificial intelligence model that predicts physical condition based on stored data and generates health improvement advice, and includes models with sequential learning capabilities.

[0296] A "prompt sentence" is a sentence input into the generative AI model that specifically describes instructions for predicting physical condition and generating advice.

[0297] A "database" is a storage device that stores data received by the server and is used for subsequent analysis and learning.

[0298] "Advice" is a specific suggestion for improving the user's health based on the health predictions made by the generative AI model.

[0299] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[0300] Hardware and software used

[0301] Wearable device: A device that collects physiological data such as a user's heart rate, exercise amount (e.g., number of steps), and sleep information (e.g., quality and duration of sleep) 24 hours a day.

[0302] Terminal (e.g., smartphone): A device that runs an application that receives data from a wearable device and integrates the food and diary data entered by the user with the emotion data analyzed by the emotion engine.

[0303] Server: A device that receives data sent from the device, stores it in a database, predicts the user's physical condition using a generative AI model, and generates health improvement advice.

[0304] Emotion engine: Software that analyzes the user's diary data and recognizes their emotional state (e.g., joy, sadness, anger, surprise).

[0305] Data collection and integration

[0306] The user puts on a wearable device. The device measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via Bluetooth or Wi-Fi. The user uses the terminal's application to enter food data (e.g., one apple, two slices of toast, coffee) and diary data (e.g., "Today was a stressful day"). The emotion engine analyzes the diary data and extracts the emotion data, such as "stressful." This data is then integrated into the terminal.

[0307] Data transmission and storage

[0308] The device sends the integrated data to the server, which can be done automatically or manually by the user, and the server stores the received data in a database.

[0309] Health prediction using generative AI models

[0310] The server inputs the data stored in the database into a generative AI model to predict the user's physical condition for the day and the next day. For example, a prompt might be used: "Based on user A's heart rate data, exercise data, sleep data, dietary data, diary data, and emotion data, please predict tomorrow's physical condition and generate specific health improvement advice."

[0311] Generate and notify health improvement advice

[0312] The server generates specific advice to improve the user's health based on the generative AI model. This advice also takes into account emotional data, so it may include, for example, "Today, it would be good to incorporate deep breathing and light exercise to relax." The generated advice is sent to the device, which then notifies the user via push notification or in-app message.

[0313] Specific examples

[0314] For general users

[0315] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[0316] The system allows both individuals and businesses to more effectively manage and improve their health.

[0317] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0318] Step 1:

[0319] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day. The collected data is temporarily stored in the device's memory.

[0320] Input: User's heart rate, exercise, and sleep information

[0321] Output: Physiological data from a wearable device

[0322] Step 2:

[0323] The wearable device uses Bluetooth or Wi-Fi to transmit the collected physiological data to a terminal, which receives the data through a dedicated application.

[0324] Input: Physiological data from a wearable device

[0325] Output: Physiological data to the device

[0326] Step 3:

[0327] The user uses the device's application to input meal data (date, time, and food eaten) and diary data (diary contents), which are then stored in a database on the device.

[0328] Input: User's meal data, diary data

[0329] Output: Meal data and diary data stored on the device

[0330] Step 4:

[0331] The device application uses an emotion engine to analyze the diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Emotional data is extracted and integrated into the device's database.

[0332] Input: Diary data

[0333] Output: Emotion data

[0334] Step 5:

[0335] The terminal integrates physiological data from the wearable device, dietary data entered by the user, diary data, and emotion data generated by the emotion engine to generate transmission data, which is then sent to the server.

[0336] Input: physiological data, dietary data, diary data, emotional data

[0337] Output: Data sent to the server

[0338] Step 6:

[0339] The server receives the integrated data sent from the devices and stores it in a database, which is used for subsequent analysis and learning.

[0340] Input: Send data

[0341] Output: Data saved to database

[0342] Step 7:

[0343] The server inputs the integrated data stored in the database into the generative AI model to predict the user's physical condition on that day and the next day. The output of the generative AI model is stored in the database as the physical condition prediction result.

[0344] Input: Prompt: "Please predict tomorrow's physical condition based on user A's heart rate data, exercise amount data, sleep data, dietary data, diary data, and emotional data, and generate specific health improvement advice."

[0345] Output: Health prediction results

[0346] Step 8:

[0347] The server generates specific advice for improving health based on the health prediction results of the AI ​​model. This advice is created taking into account emotional data.

[0348] Input: Health prediction result

[0349] Output: Health improvement advice

[0350] Step 9:

[0351] The server generates health improvement advice and sends it to the device. The device notifies the user of this advice via push notifications or in-app messages. The user can then check the advice content on their device.

[0352] Input: Health Improvement Advice

[0353] Output: Notification information to the user

[0354] Through the above steps, a system is realized that manages a user's personal physiological data, dietary data, diary data, and emotional data in an integrated manner, and provides comprehensive health predictions and individual advice on improving health.

[0355] (Application example 2)

[0356] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0357] Conventional health management systems often collect and analyze users' physiological, dietary, and emotional data separately, and systems that manage and analyze this information in an integrated manner are rare. Furthermore, particularly in security services where risk management is crucial, risk prediction based on changes in the user's emotions and physical condition is currently insufficient. This makes it difficult to comprehensively evaluate a user's health status, detect risks early, and take countermeasures. Therefore, there is a need for a new system that can comprehensively analyze a user's physiological and emotional data and provide specific advice for risk management and health improvement, as well as incident response.

[0358] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting physiological data of the user using a wearable device; means for integrating the physiological data collected from the wearable device and the dietary data and diary data entered by the user by a terminal to generate transmission data; means for receiving the transmission data and storing it in a database by the server; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving the health condition based on the physical condition prediction; means for notifying the terminal of the generated advice; means for analyzing the diary data using an emotion analysis engine and extracting emotion data; means for predicting potential risks based on the subject's emotion data and physiological data; and means for generating specific countermeasures and response instructions based on the risk prediction and notifying the terminal. This enables a comprehensive evaluation of the user's health condition, enabling early detection of risks, and the implementation of countermeasures.

[0359] A "wearable device" is an electronic device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[0360] A "terminal" is an electronic device that receives data from a wearable device, integrates the meal data and diary data entered by the user, and generates transmission data, and includes smartphones and tablets.

[0361] An "emotion analysis engine" is a software component that uses text analysis technology to recognize emotions from text data such as a user's diary data and extract emotion data.

[0362] A "generative AI model" is a machine learning model that uses integrated data as input to predict a user's physical condition and risks, and improves prediction accuracy by successively learning based on new data.

[0363] The "server" is an electronic device that receives data sent from the device, stores it in a database, and processes it using a generative AI model to analyze the data and predict the user's health condition.

[0364] "Database" means an information management system for storing integrated data received by the server, and for enabling efficient search and utilization of required information.

[0365] "Notification means" is a function for notifying the user of advice and risk countermeasure instructions generated by the server, and is done through push notifications or in-app messages.

[0366] "Physiological data" refers to data relating to the user's physical condition, such as the user's heart rate, amount of exercise, and sleep information, and is collected by a wearable device.

[0367] "Emotion data" is data relating to the user's emotional state extracted from text such as diary data by an emotion analysis engine, and includes emotions such as joy, sadness, anger, and surprise.

[0368] "Risk prediction" refers to predictions made by a generative AI model based on emotional and physiological data to estimate the user's health and safety risks.

[0369] The "advice generation means" is a function that generates specific advice and measures to improve the user's health condition based on the results of physical condition prediction and risk prediction.

[0370] This invention is a system for predicting and improving health status by integrating and managing a user's physiological data, dietary data, diary data, and emotional data. This system is composed of a wearable device, a terminal, a server, an emotion analysis engine, and a generative AI model.

[0371] Wearable devices

[0372] Wearable devices collect physiological data such as the user's heart rate, activity, and sleep information 24 hours a day. For example, they measure heart rate, steps, and sleep quality. The collected data is synchronized to a device via Bluetooth or Wi-Fi. Examples of specific devices that use this include smartwatches and fitness trackers.

[0373] Terminal

[0374] The device, which is typically a smartphone or tablet, collects physiological data received from the wearable device and integrates it with dietary and diary data entered by the user. Emotional data analyzed by an emotion analysis engine is also collected. The integrated data is then sent to a server, where the application generates advice and notifies users about risks based on the collected data.

[0375] Sentiment Analysis Engine

[0376] The sentiment analysis engine uses text analysis technology to analyze the user's diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Specifically, it extracts emotions from text using natural language processing tools such as Google Cloud Natural Language API and IBM Watson NLU. This emotional data is used to predict the user's physical condition and risks.

[0377] server

[0378] The server receives and stores the integrated data sent from the device. The server stores the received data in a database and uses a generative AI model to predict physical condition and risks. Specific examples of AI models used include Google Vertex AI and OpenAI GPT-4. Specific advice and countermeasures are generated based on the predicted risks and health condition.

[0379] Risk Management and Notification

[0380] The server uses a generative AI model to predict potential risks based on the subject's emotional and physiological data. Based on the results, the server generates specific countermeasures and response instructions and notifies the device via push notifications or in-app messages.

[0381] Specific examples

[0382] Example 1: Security guard

[0383] A wearable device worn by security guards collects physiological data such as heart rate and exercise volume. A smartphone app receives this data, and the security guards enter a diary entry about their activities and emotional state for the day. If the emotion analysis engine determines from the diary data that the guard is feeling "high stress," the server receives this data and uses a generative AI model to predict risk. Specific advice, such as "reduce your alert level today and take a moderate break," is generated and sent to the guard's smartphone.

[0384] Prompt Sentence Examples

[0385] Using the user's physiological data, dietary data, diary data, and related emotional data as input, predict risks for today and the next 24 hours, and generate appropriate advice and incident response instructions based on the results.

[0386] This system allows for a comprehensive assessment of the user's health status, allowing for early detection of risks and the implementation of appropriate measures.

[0387] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0388] Step 1: Data collection

[0389] The user wears a wearable device to collect physiological data such as heart rate, exercise volume, and sleep information. This data is synchronized to the user's device via Bluetooth or Wi-Fi. The input physiological data are heart rate, steps, and sleep duration and quality, which are recorded in real time. The output is physiological data stored on the device.

[0390] Step 2: Enter user data

[0391] The user uses a terminal to input dietary data and diary data. Dietary data includes the contents of meals and calorie intake, while diary data records information about the user's emotional state and physical condition for that day. The input is data manually entered by the user, which is received and integrated by the terminal. The output is recorded data on the terminal that reflects the input.

[0392] Step 3: Sentiment Analysis

[0393] The device uses an emotion analysis engine to analyze the text of the diary data and extract emotional data. The input is the text information of the diary data, and the emotional state is extracted through text analysis using natural language processing. Specifically, emotions (joy, sadness, anger, surprise, etc.) are identified using Google Cloud Natural Language API, etc. The output is the extracted emotional data.

[0394] Step 4: Data integration and transmission

[0395] The device integrates the collected physiological data, dietary data, and analyzed emotional data to generate transmission data. The generated transmission data is then sent to the server. The input is physiological data, dietary data, and emotional data, which are processed to integrate them. The output is the integrated transmission data.

[0396] Step 5: Save Data

[0397] The server stores the aggregated data received from the terminals in a database. The input is the aggregated data that is stored in the database. The output is the stored database entry.

[0398] Step 6: Health Prediction

[0399] The server uses a generative AI model with data stored in a database to predict the user's physical condition. The input is integrated data including past physiological data, dietary data, and emotional data, and the physical condition is predicted through machine learning using the generative AI model. Specifically, Google Vertex AI and OpenAI GPT-4 are used to predict future physical condition and risks. The output is the physical condition prediction result.

[0400] Step 7: Risk prediction

[0401] The server predicts potential risks based on the health prediction results. The input is the health prediction results, and a generative AI model is applied to evaluate the presence and level of risk. The output is the risk prediction results.

[0402] Step 8: Advice Generation

[0403] The server generates specific advice and countermeasures for improving health status based on the results of health condition prediction and risk prediction. The input is the risk prediction result, and appropriate advice is generated using a generative AI model. The output is the generated advice.

[0404] Step 9: Notification

[0405] The server notifies the device of the generated advice. The device then communicates the advice to the user using push notifications or in-app messages. The input is the generated advice, which is sent to the device as a notification. The output is a notification message to the user.

[0406] Through this process, the system can comprehensively assess the user's health status, detect risks early, and take necessary measures.

[0407] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0418] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0419] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0422] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0423] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[0424] Overall system configuration

[0425] Wearable devices

[0426] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[0427] Terminal

[0428] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the dietary and diary data entered by the user. This application integrates the physiological data received from the wearable device and the dietary and diary data entered by the user, and prepares it for transmission to the server.

[0429] server

[0430] The server receives data sent from the device and stores it in a database. Based on the stored data, a generative AI model is used to predict the user's physical condition and generate specific advice for improvement.

[0431] Program processing

[0432] Data collection and integration

[0433] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application running on the device receives this data, and also incorporates dietary and diary data entered by the user, and combines them to generate a single transmission data packet.

[0434] Sending data

[0435] The terminal sends the generated transmission data to the server automatically, but the user can also trigger the transmission manually if necessary.

[0436] Data storage and analysis

[0437] The server stores the received data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[0438] Advice generation and notification

[0439] The server generates specific advice to improve the user's health based on the results of the health prediction. The advice is sent to the device, which then notifies the user via push notification or in-app message. This allows the user to take actions that will contribute to improving their lifestyle the next day.

[0440] Specific examples

[0441] Example 1: For a general user

[0442] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. At night, the device consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you go to bed early and relax today," and the device notifies User A of this advice.

[0443] Example 2: For a company

[0444] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0445] The above is a specific embodiment for carrying out the present invention. This system can provide more effective health management and improvement for both individual users and companies.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[0449] Step 2:

[0450] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[0451] Step 3:

[0452] The terminal periodically receives data from the wearable device and temporarily stores it. An application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[0453] Step 4:

[0454] The user uses an application on the device to input diary data about the day's diet and physical condition, specifically, what they ate for breakfast, lunch, and dinner, as well as changes in their mood.

[0455] Step 5:

[0456] The terminal combines the physiological data received from the wearable device with the dietary and diary data entered by the user to generate a single transmission data packet, which includes time series information and the user ID.

[0457] Step 6:

[0458] The terminal transmits the generated transmission data to the server. This transmission is usually automatic, but can also be triggered manually by the user.

[0459] Step 7:

[0460] The server stores the received data in a database using encryption technology to ensure data security.

[0461] Step 8:

[0462] The server uses a generative AI model to analyze the data stored in the database, which uses machine learning algorithms to predict the user's physical condition.

[0463] Step 9:

[0464] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[0465] Step 10:

[0466] The server predicts the user's health condition for the next day based on the predicted physical condition and generates specific advice for improving health, such as ensuring adequate sleep and recommending light exercise.

[0467] Step 11:

[0468] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[0469] Step 12:

[0470] The server analyzes the aggregated employee health data and generates reports for companies, including recommendations for improving employee benefits, which can be used to support corporate health management programs.

[0471] Example 1

[0472] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0473] In modern society, individuals are in need of ways to efficiently manage and improve their own health. However, conventional systems have difficulty integrating users' physiological data, dietary data, and diary data to provide health predictions and health improvement advice. Furthermore, companies lack systems that can effectively monitor the health status of their employees and provide improvement measures for employee benefits.

[0474] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0475] In this invention, the server includes a means for automatically or manually transmitting user data from the device to the server, a means for successively training the generative AI model based on new data to improve prediction accuracy, and a means for notifying the user of the generated advice via push notification or in-app message. This allows users to centrally manage their own physiological data, dietary data, and diary data and easily receive health predictions and health improvement advice. Companies can also aggregate employee health data and provide employee benefit improvement measures based on their health status.

[0476] A "wearable device" is a portable device used to collect physiological data such as a user's heart rate, exercise volume, and sleep information.

[0477] A "terminal" is an electronic device that has the function of receiving data from a wearable device, integrating the dietary data and diary data entered by the user, and transmitting the data to a server.

[0478] "Physiological data" is data that indicates the physiological state of the body, such as the user's heart rate, amount of exercise, and sleep time.

[0479] "Dietary data" refers to data that indicates information about the contents of meals consumed by the user.

[0480] "Diary data" is data entered by the user that records the user's physical condition and activities for that day.

[0481] "Transmission data" refers to data generated by integrating physiological data collected by the terminal from the wearable device, dietary data entered by the user, and diary data.

[0482] The "server" is a device that receives data sent from the device, stores it in a database, and uses a generative AI model to generate health predictions and health improvement advice.

[0483] A "database" is a collection of information that allows a server to systematically manage and store data received.

[0484] A "generative AI model" is an artificial intelligence model that generates predictions about a user's physical condition and health advice based on stored data.

[0485] "Health prediction" refers to the use of a generative AI model to predict a user's current and future health status.

[0486] "Advice for improving health condition" refers to specific suggestions and instructions for improving the user's health that are provided based on the predicted physical condition.

[0487] "Incremental learning" is the process by which a generative AI model incorporates new data and learns repeatedly to improve its prediction accuracy.

[0488] "Push notification" is a feature that allows an application to send a message directly to a user's device and provide specific information.

[0489] "Automatic transmission" is a function that allows a terminal to automatically transmit data to a server based on specific times or conditions.

[0490] "Manual transmission" is a function that allows the terminal to transmit data to the server in response to a user operation.

[0491] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[0492] Overall system configuration

[0493] The embodiment for implementing this system is configured as follows.

[0494] Wearable devices

[0495] Users wear wearable devices to collect physiological data such as heart rate, exercise volume (number of steps), and sleep information (quality and duration). The devices synchronize data with a terminal via Bluetooth or Wi-Fi. Specifically, users wear small devices (e.g., smartwatches) that fit on their wrists and can collect data throughout the day.

[0496] Terminal

[0497] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the meal data and diary data entered by the user. This application integrates the physiological data received from the wearable device with the meal data and diary data entered by the user and prepares it to be sent to the server. For example, when a user enters "Breakfast: tamagoyaki, salad, coffee" into the app, the meal data is imported.

[0498] server

[0499] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition and generate specific advice for improving their health. Furthermore, the server can continuously train the generative AI model based on new data to improve prediction accuracy. For example, it can generate advice such as, "Based on yesterday's data, you should increase your exercise today."

[0500] Specific examples

[0501] An embodiment of the system will be specifically described below.

[0502] Example 1: For a general user

[0503] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives this data from the wearable device, and User A enters a diary entry about the day's meals and physical condition into the app. That night, the device consolidates this data and sends it to the server. Late at night, the server stores the received data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you drink plenty of water and do some light exercise today," and the device notifies User A of this advice.

[0504] Example 2: For a company

[0505] All employees of a company wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report suggesting improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0506] Prompt Sentence Examples

[0507] Below are some example prompts that can be used as input to a generative AI model:

[0508] "User A's average heart rate yesterday was 60 beats per minute, the number of steps taken was 8,000, and the amount of sleep was 7 hours. Please predict his / her physical condition today and generate appropriate health improvement advice."

[0509] "Use employee health data to suggest ways to improve employee benefits for companies."

[0510] This system can provide more effective health management and improvement for both individuals and businesses.

[0511] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0512] Step 1: Data collection

[0513] The user wears a wearable device to collect physiological data such as heart rate, exercise amount (number of steps), and sleep information. The input data includes heart rate, number of steps, and sleep information.

[0514] The wearable device collects this physiological data 24 hours a day and stores it in its internal memory. Specifically, the device measures heart rate at regular intervals and calculates the amount of exercise.

[0515] Step 2: Synchronize data

[0516] The terminal periodically synchronizes with the wearable device via Bluetooth or Wi-Fi and receives the collected physiological data. The input is physiological data from the wearable device, and the output is data stored in a database within the terminal.

[0517] Specifically, the terminal starts communicating with the wearable device every hour and downloads new data to the terminal.

[0518] Step 3: Entering food and diary data

[0519] The user uses an application installed on their smartphone to enter diary data about their diet and their physical condition for that day. The input is done manually by the user, and the output is saved in a database on the device.

[0520] As a concrete example, a user enters "Breakfast: toast, coffee" into a text field in an app.

[0521] Step 4: Integrate the data

[0522] The terminal integrates physiological data received from the wearable device and dietary and diary data entered by the user. The inputs are physiological data, dietary data, and diary data, and the output is an integrated data packet.

[0523] Specifically, the application in the device organizes each piece of data in chronological order and packs it into a single JSON data packet.

[0524] Step 5: Sending data

[0525] The terminal automatically transmits the combined data packet to the server, or the user can transmit it manually. The input is the combined data packet, and the output is the completion status of transmission to the server.

[0526] For example, a scheduled job runs overnight and sends a data packet as an HTTP POST request to a server's API endpoint.

[0527] Step 6: Save your data

[0528] The server stores the received data packet in a database. The input is the data packet from the terminal, and the output is the status of successful storage in the database.

[0529] Specifically, the server-side script receives the received data and performs an INSERT operation on the database.

[0530] Step 7: Analyze the data

[0531] The server uses the stored data as input to run the generative AI model and analyze the user's physical condition prediction and health status. The input is the data stored in the database, and the output is the physical condition prediction result.

[0532] Specifically, the server runs a generative AI model implemented in Python as a scheduled task, and calculates a health prediction based on features (e.g., heart rate, amount of exercise, sleep time, etc.).

[0533] Step 8: Generating Advice

[0534] The server generates advice for improving health based on the health prediction results. The input is the health prediction results, and the output is health advice.

[0535] For example, if the AI ​​model predicts that the user is feeling fatigued, the server will generate advice such as, "Try to do some light exercise today and get plenty of rest."

[0536] Step 9: Advice Notification

[0537] The device uses push notification and in-app messaging functions to notify the user of the advice received from the server. The input is the health advice from the server, and the output is the completion status of the notification to the user.

[0538] Specifically, the device's notification system will push a message to the user saying, "Today's advice: Try to do some light exercise and get plenty of rest."

[0539] (Application example 1)

[0540] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0541] Traditionally, employee health management and work efficiency improvement at logistics centers have been limited to fragmented data collection and individual measures, making it difficult to achieve effective and integrated management.In addition, it has been difficult to provide specific advice in real time that responds to changes in each employee's physical condition, resulting in problems that make it difficult to optimize employee performance and health.

[0542] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0543] In this invention, the server includes: means for collecting physiological data of a user using a wearable device; means for generating transmission data by integrating the physiological data collected from the wearable device and dietary data and diary data entered by the user using a terminal; means for receiving the transmission data and storing it in a database; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving health based on the physical condition prediction; means for notifying the terminal of the generated advice; and means for collecting physiological data, dietary data, and work records of employees at a logistics center and providing a physical condition prediction and advice for improving work performance based on the generative AI model. This makes it possible to individually manage the physical condition and work performance of each employee working at a logistics center and provide specific advice for improving health and work efficiency in real time.

[0544] A "wearable device" is a device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[0545] A "terminal" is a device that receives physiological data from a wearable device, imports dietary data and diary data entered by the user, and is an electronic device such as a smartphone or tablet that integrates this data to generate transmission data.

[0546] "Transmission data" refers to a data packet generated by integrating physiological data, dietary data, and diary data collected from the wearable device and the terminal, and is the entire data transmitted to the server.

[0547] The "server" is a computer system that receives data sent from the device, stores the data in a database, uses a generative AI model to predict the user's physical condition, and generates advice for improving their health.

[0548] The "generative AI model" is an artificial intelligence model that predicts a user's physical condition based on collected physiological data, dietary data, and diary data, and generates appropriate health improvement advice.

[0549] "Health prediction" is the process of using a generative AI model to predict a user's current and future health status, and to identify changes and risks in health based on analyzed data.

[0550] "Advice generation" is the process of generating specific guidelines and suggestions for improving the user's health based on the results of the health prediction.

[0551] A "logistics center" is a facility where operations such as storing, sorting, and preparing products for delivery are carried out, and is a work environment where employees work intensively.

[0552] "Employee physiological data" refers to physical data about employees, such as heart rate, activity level, and sleep information, that is collected by wearable devices.

[0553] "Work performance improvement advice" refers to specific suggestions and instructions for improving work efficiency and job performance based on employees' physiological data and work records.

[0554] This invention is a system aimed at managing the health and performance of employees working at logistics centers. It uses wearable devices, terminals (e.g., smartphones), and a server to collect and integrate employees' physiological data, dietary data, and work records, and uses a generative AI model to predict their physical condition and provide advice to improve their work performance.

[0555] Hardware and software used

[0556] Hardware

[0557] Wearable devices: Collect physiological data such as heart rate, exercise, and sleep information 24 hours a day.

[0558] Smartphone (or tablet): Receives data from the wearable device and runs an application that allows the user to enter food and diary data.

[0559] software

[0560] Server system: Utilizing a database and generative AI models, the system analyzes data and generates health predictions and health improvement advice.

[0561] Database system (e.g. MySQL, MongoDB): stores the data submitted by users.

[0562] Generative AI model (e.g., TensorFlow, PyTorch): Predicts the user's physical condition and generates advice.

[0563] Data collection

[0564] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume, and sleep information. A smartphone app receives this data from the wearable device and also incorporates dietary and diary data entered by the user. This integrated data is sent to a server as a data packet.

[0565] Data analysis

[0566] The server receives the transmitted data and stores it in a database. The generative AI model predicts the user's physical condition based on the stored data and generates specific advice for improving their health. For example, if the user's heart rate is high and the number of steps taken is low, advice such as "Take a break and take a deep breath" will be generated.

[0567] Advice Notice

[0568] The server sends the generated advice to a smartphone app and notifies the user, allowing the user to receive specific advice on improving their health and work efficiency in real time.

[0569] Specific examples

[0570] While User A is working at a logistics center, a wearable device collects data such as a heart rate of 130, steps taken 4,500, and sleep quality of 0.3. User A enters his / her breakfast "salad and yogurt," lunch "chicken and rice," and dinner "fish and vegetables" in a smartphone app, and writes in his / her diary, "I feel good today. Work is going smoothly." Using this data, the server uses a generative AI model to generate specific advice such as "Your heart rate is high, so take a break and take a deep breath. Walk a little more. I recommend you go to bed earlier tonight," and notifies the smartphone.

[0571] Prompt Sentence Examples

[0572] User: 32-year-old male, Occupation: Logistics center worker. Current heart rate: 130, steps: 4500, sleep quality: 0.3.

[0573] Food notes: Breakfast: Salad and yogurt, Lunch: Chicken and rice, Dinner: Fish and vegetables.

[0574] Health diary: I feel good today. Work is progressing smoothly.

[0575] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0576] Step 1:

[0577] The user wears a wearable device to collect physiological data. Specifically, the wearable device continuously records heart rate, physical activity (number of steps), and sleep information (quality and duration of sleep). This data is sent to a terminal in real time.

[0578] Input: Wearable device

[0579] Output: Physiological data (heart rate, steps, sleep information)

[0580] Step 2:

[0581] The terminal receives physiological data from the wearable device, and at the same time, the user inputs food and diary data using the terminal application, thereby collecting the user's daily health information.

[0582] Input: physiological data, dietary data, diary data

[0583] Output: Integrated data

[0584] Step 3:

[0585] The device combines the physiological data received with the dietary and diary data entered by the user to generate a single data packet for transmission. Specifically, each data field is compiled in a unified format to form a data packet.

[0586] Input: Integrated data

[0587] Output: Transmitted data packets

[0588] Step 4:

[0589] The terminal generates and transmits the transmitted data packets to the server, which can be transmitted in real time or at regular intervals.

[0590] Input: Transmit data packet

[0591] Output: Sending data packet (server side)

[0592] Step 5:

[0593] The server receives the transmitted data packets and stores them in a database, storing each piece of data in a corresponding field along with metadata such as the date and user ID.

[0594] Input: Transmit data packet

[0595] Output: Saved data (database)

[0596] Step 6:

[0597] The server uses the generative AI model to predict physical condition based on the stored data. Specifically, the server inputs the stored physiological data, dietary data, and diary data into the generative AI model and executes the prediction algorithm.

[0598] Input: Stored data (database)

[0599] Output: Health prediction results

[0600] Step 7:

[0601] The server generates specific advice for improving health based on the health prediction results. Using a generative AI model, the prediction results are analyzed and optimal advice is created for the user.

[0602] Input: Health prediction result

[0603] Output: Health improvement advice

[0604] Step 8:

[0605] The server sends the generated advice to the device, which receives it and displays it to the user as a push notification or in-app message.

[0606] Input: Health Improvement Advice

[0607] Output: Advice notified (terminal side)

[0608] The above are the specific processing steps for realizing this invention, which make it possible to manage the physical condition and work performance of each employee working at a logistics center in real time and provide appropriate advice.

[0609] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0610] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[0611] Overall system configuration

[0612] Wearable devices

[0613] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[0614] Terminal

[0615] The terminal (e.g., a smartphone) receives data from the wearable device and runs an application that incorporates the dietary and diary data entered by the user, as well as the emotion data analyzed by the emotion engine. This application then integrates this data and prepares it for transmission to the server.

[0616] Emotion Engine

[0617] The emotion engine analyzes the user's diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis techniques to extract emotions from the diary content.

[0618] server

[0619] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate. Furthermore, the server generates specific advice to improve the user's health.

[0620] Program processing

[0621] Data collection and integration

[0622] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application on the device receives this data and integrates it with dietary data and diary data entered by the user, and emotional data analyzed by an emotion engine.

[0623] Sending data

[0624] The device transmits the consolidated data to the server automatically, but can also be triggered manually by the user.

[0625] Data storage and analysis

[0626] The server stores the received integrated data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and their health condition for the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[0627] Advice generation and notification

[0628] Based on the results of the health prediction, the server generates specific advice to improve the user's health. This advice also takes into account emotional data, so it includes consideration of emotional aspects, such as "Today, it would be good to do some light exercise to change your mood."

[0629] The generated advice is sent to the device, which then notifies the user via push notifications or in-app messages, allowing the user to review and incorporate the advice into their daily lives.

[0630] Specific examples

[0631] Example 1: For a general user

[0632] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[0633] Example 2: For a company

[0634] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. An emotion engine analyzes the diary data and extracts emotional data. The devices send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0635] The above is a specific embodiment of the present invention that combines an emotion engine. This system allows both individual users and companies to more effectively manage and improve their health conditions.

[0636] The processing flow will be explained below.

[0637] Step 1:

[0638] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[0639] Step 2:

[0640] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[0641] Step 3:

[0642] The terminal periodically receives data from the wearable device and temporarily stores it. At the same time, an application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[0643] Step 4:

[0644] The user uses an application on the device to enter diary data about the day's diet and physical condition, specifically recording what they ate for breakfast, lunch, and dinner, as well as changes in their emotions and notable events.

[0645] Step 5:

[0646] The emotion engine analyzes the diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis technology to extract and classify emotions from the diary content.

[0647] Step 6:

[0648] The terminal combines the physiological data received from the wearable device with the dietary data and diary data entered by the user, and the emotional data analyzed by the emotion engine, to generate a single transmission data packet, which includes time series information and the user ID.

[0649] Step 7:

[0650] The terminal sends the generated transmission data packets to the server, usually automatically, but can also be triggered manually by the user.

[0651] Step 8:

[0652] The server stores the received data in a database using encryption technology to ensure data security.

[0653] Step 9:

[0654] The server uses a generative AI model to analyze the data stored in the database. This AI model uses machine learning algorithms to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate.

[0655] Step 10:

[0656] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[0657] Step 11:

[0658] The server predicts the user's health condition for the next day based on the physical condition prediction and generates specific health improvement advice. For example, based on the prediction results, it may generate a suggestion such as "Today, it would be good to incorporate deep breathing and light exercise to relax."

[0659] Step 12:

[0660] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[0661] Step 13:

[0662] The server analyzes the aggregated employee health data and generates reports for companies that include recommendations for improving employee benefits. These reports can be used to support corporate health management programs, and may include recommendations such as introducing yoga classes or meditation sessions.

[0663] The above is the specific processing flow of the system that combines the emotion engine. This system enables more accurate health management and improvement that also takes into account the user's emotional state.

[0664] Example 2

[0665] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0666] In modern society, personal health management and improving corporate employee benefits are important issues. However, conventional health management systems rely on limited information sources, such as physiological and dietary data, making it difficult to provide comprehensive health predictions and advice that reflect users' emotions and daily events. It is also difficult to collect and analyze data in real time and provide appropriate advice to individual users. Furthermore, systems that enable companies to effectively aggregate employee health data and propose measures to improve employee benefits are insufficient.

[0667] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0668] In this invention, the server includes: means for collecting a user's physiological data using a wearable device; means for integrating the physiological data collected from the wearable device and dietary and diary data entered by the user via a terminal, and generating transmission data including emotion data analyzed by an emotion engine; means for transmitting the transmission data to the server; means for receiving the transmission data and storing it in a database; means for using the data stored in the database to use a generative AI model to predict the user's physical condition based on a prompt; means for generating advice for improving the user's health condition based on the predicted physical condition; and means for notifying the terminal of the generated advice. This enables integrated management of a user's personal physiological data, dietary data, diary data, and emotion data, and provides comprehensive health predictions and individual health improvement advice. Furthermore, companies can effectively aggregate employee health data and propose specific data-based improvements to employee benefits.

[0669] A "wearable device" is a device worn by a user that measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via a communication means.

[0670] A "terminal" is a device that manages physiological data collected from a wearable device, as well as dietary data and diary data entered by the user, integrates them to generate transmission data, and transmits this data to a server, including emotional data analyzed by an emotion engine.

[0671] The "emotion engine" is software that analyzes a user's diary data, recognizes their emotional state using text analysis technology, and extracts emotional data.

[0672] The "server" is a system that receives data sent from the device, stores it in a database, predicts physical condition using a generative AI model, generates advice for improving health, and notifies the device.

[0673] "Physiological data" refers to data relating to the user's physical condition, such as heart rate, amount of exercise, and sleep information.

[0674] "Dietary data" refers to data relating to the type, amount, and time of food intake by the user.

[0675] "Diary data" is text data in which a user describes daily events, emotions, physical condition, and the like.

[0676] "Emotion data" is data relating to the user's emotional state that is extracted by the emotion engine by analyzing the diary data.

[0677] A "generative AI model" is an artificial intelligence model that predicts physical condition based on stored data and generates health improvement advice, and includes models with sequential learning capabilities.

[0678] A "prompt sentence" is a sentence input into the generative AI model that specifically describes instructions for predicting physical condition and generating advice.

[0679] A "database" is a storage device that stores data received by the server and is used for subsequent analysis and learning.

[0680] "Advice" is a specific suggestion for improving the user's health based on the health predictions made by the generative AI model.

[0681] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[0682] Hardware and software used

[0683] Wearable device: A device that collects physiological data such as a user's heart rate, exercise amount (e.g., number of steps), and sleep information (e.g., quality and duration of sleep) 24 hours a day.

[0684] Terminal (e.g., smartphone): A device that runs an application that receives data from a wearable device and integrates the food and diary data entered by the user with the emotion data analyzed by the emotion engine.

[0685] Server: A device that receives data sent from the device, stores it in a database, predicts the user's physical condition using a generative AI model, and generates health improvement advice.

[0686] Emotion engine: Software that analyzes the user's diary data and recognizes their emotional state (e.g., joy, sadness, anger, surprise).

[0687] Data collection and integration

[0688] The user puts on a wearable device. The device measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via Bluetooth or Wi-Fi. The user uses the terminal's application to enter food data (e.g., one apple, two slices of toast, coffee) and diary data (e.g., "Today was a stressful day"). The emotion engine analyzes the diary data and extracts the emotion data, such as "stressful." This data is then integrated into the terminal.

[0689] Data transmission and storage

[0690] The device sends the integrated data to the server, which can be done automatically or manually by the user, and the server stores the received data in a database.

[0691] Health prediction using generative AI models

[0692] The server inputs the data stored in the database into a generative AI model to predict the user's physical condition for the day and the next day. For example, a prompt might be used: "Based on user A's heart rate data, exercise data, sleep data, dietary data, diary data, and emotion data, please predict tomorrow's physical condition and generate specific health improvement advice."

[0693] Generate and notify health improvement advice

[0694] The server generates specific advice to improve the user's health based on the generative AI model. This advice also takes into account emotional data, so it may include, for example, "Today, it would be good to incorporate deep breathing and light exercise to relax." The generated advice is sent to the device, which then notifies the user via push notification or in-app message.

[0695] Specific examples

[0696] For general users

[0697] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[0698] The system allows both individuals and businesses to more effectively manage and improve their health.

[0699] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0700] Step 1:

[0701] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day. The collected data is temporarily stored in the device's memory.

[0702] Input: User's heart rate, exercise, and sleep information

[0703] Output: Physiological data from a wearable device

[0704] Step 2:

[0705] The wearable device uses Bluetooth or Wi-Fi to transmit the collected physiological data to a terminal, which receives the data through a dedicated application.

[0706] Input: Physiological data from a wearable device

[0707] Output: Physiological data to the device

[0708] Step 3:

[0709] The user uses the device's application to input meal data (date, time, and food eaten) and diary data (diary contents), which are then stored in a database on the device.

[0710] Input: User's meal data, diary data

[0711] Output: Meal data and diary data stored on the device

[0712] Step 4:

[0713] The device application uses an emotion engine to analyze the diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Emotional data is extracted and integrated into the device's database.

[0714] Input: Diary data

[0715] Output: Emotion data

[0716] Step 5:

[0717] The terminal integrates physiological data from the wearable device, dietary data entered by the user, diary data, and emotion data generated by the emotion engine to generate transmission data, which is then sent to the server.

[0718] Input: physiological data, dietary data, diary data, emotional data

[0719] Output: Data sent to the server

[0720] Step 6:

[0721] The server receives the integrated data sent from the devices and stores it in a database, which is used for subsequent analysis and learning.

[0722] Input: Send data

[0723] Output: Data saved to database

[0724] Step 7:

[0725] The server inputs the integrated data stored in the database into the generative AI model to predict the user's physical condition on that day and the next day. The output of the generative AI model is stored in the database as the physical condition prediction result.

[0726] Input: Prompt: "Please predict tomorrow's physical condition based on user A's heart rate data, exercise amount data, sleep data, dietary data, diary data, and emotional data, and generate specific health improvement advice."

[0727] Output: Health prediction results

[0728] Step 8:

[0729] The server generates specific advice for improving health based on the health prediction results of the AI ​​model. This advice is created taking into account emotional data.

[0730] Input: Health prediction result

[0731] Output: Health improvement advice

[0732] Step 9:

[0733] The server generates health improvement advice and sends it to the device. The device notifies the user of this advice via push notifications or in-app messages. The user can then check the advice content on their device.

[0734] Input: Health Improvement Advice

[0735] Output: Notification information to the user

[0736] Through the above steps, a system is realized that manages a user's personal physiological data, dietary data, diary data, and emotional data in an integrated manner, and provides comprehensive health predictions and individual advice on improving health.

[0737] (Application example 2)

[0738] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0739] Conventional health management systems often collect and analyze users' physiological, dietary, and emotional data separately, and systems that manage and analyze this information in an integrated manner are rare. Furthermore, particularly in security services where risk management is crucial, risk prediction based on changes in the user's emotions and physical condition is currently insufficient. This makes it difficult to comprehensively evaluate a user's health status, detect risks early, and take countermeasures. Therefore, there is a need for a new system that can comprehensively analyze a user's physiological and emotional data and provide specific advice for risk management and health improvement, as well as incident response.

[0740] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting physiological data of the user using a wearable device; means for integrating the physiological data collected from the wearable device and the dietary data and diary data entered by the user by a terminal to generate transmission data; means for receiving the transmission data and storing it in a database by the server; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving the health condition based on the physical condition prediction; means for notifying the terminal of the generated advice; means for analyzing the diary data using an emotion analysis engine and extracting emotion data; means for predicting potential risks based on the subject's emotion data and physiological data; and means for generating specific countermeasures and response instructions based on the risk prediction and notifying the terminal. This enables a comprehensive evaluation of the user's health condition, enabling early detection of risks, and the implementation of countermeasures.

[0741] A "wearable device" is an electronic device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[0742] A "terminal" is an electronic device that receives data from a wearable device, integrates the meal data and diary data entered by the user, and generates transmission data, and includes smartphones and tablets.

[0743] An "emotion analysis engine" is a software component that uses text analysis technology to recognize emotions from text data such as a user's diary data and extract emotion data.

[0744] A "generative AI model" is a machine learning model that uses integrated data as input to predict a user's physical condition and risks, and improves prediction accuracy by successively learning based on new data.

[0745] The "server" is an electronic device that receives data sent from the device, stores it in a database, and processes it using a generative AI model to analyze the data and predict the user's health condition.

[0746] "Database" means an information management system for storing integrated data received by the server, and for enabling efficient search and utilization of required information.

[0747] "Notification means" is a function for notifying the user of advice and risk countermeasure instructions generated by the server, and is done through push notifications or in-app messages.

[0748] "Physiological data" refers to data relating to the user's physical condition, such as the user's heart rate, amount of exercise, and sleep information, and is collected by a wearable device.

[0749] "Emotion data" is data relating to the user's emotional state extracted from text such as diary data by an emotion analysis engine, and includes emotions such as joy, sadness, anger, and surprise.

[0750] "Risk prediction" refers to predictions made by a generative AI model based on emotional and physiological data to estimate the user's health and safety risks.

[0751] The "advice generation means" is a function that generates specific advice and measures to improve the user's health condition based on the results of physical condition prediction and risk prediction.

[0752] This invention is a system for predicting and improving health status by integrating and managing a user's physiological data, dietary data, diary data, and emotional data. This system is composed of a wearable device, a terminal, a server, an emotion analysis engine, and a generative AI model.

[0753] Wearable devices

[0754] Wearable devices collect physiological data such as the user's heart rate, activity, and sleep information 24 hours a day. For example, they measure heart rate, steps, and sleep quality. The collected data is synchronized to a device via Bluetooth or Wi-Fi. Examples of specific devices that use this include smartwatches and fitness trackers.

[0755] Terminal

[0756] The device, which is typically a smartphone or tablet, collects physiological data received from the wearable device and integrates it with dietary and diary data entered by the user. Emotional data analyzed by an emotion analysis engine is also collected. The integrated data is then sent to a server, where the application generates advice and notifies users about risks based on the collected data.

[0757] Sentiment Analysis Engine

[0758] The sentiment analysis engine uses text analysis technology to analyze the user's diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Specifically, it extracts emotions from text using natural language processing tools such as Google Cloud Natural Language API and IBM Watson NLU. This emotional data is used to predict the user's physical condition and risks.

[0759] server

[0760] The server receives and stores the integrated data sent from the device. The server stores the received data in a database and uses a generative AI model to predict physical condition and risks. Specific examples of AI models used include Google Vertex AI and OpenAI GPT-4. Specific advice and countermeasures are generated based on the predicted risks and health condition.

[0761] Risk Management and Notification

[0762] The server uses a generative AI model to predict potential risks based on the subject's emotional and physiological data. Based on the results, the server generates specific countermeasures and response instructions and notifies the device via push notifications or in-app messages.

[0763] Specific examples

[0764] Example 1: Security guard

[0765] A wearable device worn by security guards collects physiological data such as heart rate and exercise volume. A smartphone app receives this data, and the security guards enter a diary entry about their activities and emotional state for the day. If the emotion analysis engine determines from the diary data that the guard is feeling "high stress," the server receives this data and uses a generative AI model to predict risk. Specific advice, such as "reduce your alert level today and take a moderate break," is generated and sent to the guard's smartphone.

[0766] Prompt Sentence Examples

[0767] Using the user's physiological data, dietary data, diary data, and related emotional data as input, predict risks for today and the next 24 hours, and generate appropriate advice and incident response instructions based on the results.

[0768] This system allows for a comprehensive assessment of the user's health status, allowing for early detection of risks and the implementation of appropriate measures.

[0769] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0770] Step 1: Data collection

[0771] The user wears a wearable device to collect physiological data such as heart rate, exercise volume, and sleep information. This data is synchronized to the user's device via Bluetooth or Wi-Fi. The input physiological data are heart rate, steps, and sleep duration and quality, which are recorded in real time. The output is physiological data stored on the device.

[0772] Step 2: Enter user data

[0773] The user uses a terminal to input dietary data and diary data. Dietary data includes the contents of meals and calorie intake, while diary data records information about the user's emotional state and physical condition for that day. The input is data manually entered by the user, which is received and integrated by the terminal. The output is recorded data on the terminal that reflects the input.

[0774] Step 3: Sentiment Analysis

[0775] The device uses an emotion analysis engine to analyze the text of the diary data and extract emotional data. The input is the text information of the diary data, and the emotional state is extracted through text analysis using natural language processing. Specifically, emotions (joy, sadness, anger, surprise, etc.) are identified using Google Cloud Natural Language API, etc. The output is the extracted emotional data.

[0776] Step 4: Data integration and transmission

[0777] The device integrates the collected physiological data, dietary data, and analyzed emotional data to generate transmission data. The generated transmission data is then sent to the server. The input is physiological data, dietary data, and emotional data, which are processed to integrate them. The output is the integrated transmission data.

[0778] Step 5: Save Data

[0779] The server stores the aggregated data received from the terminals in a database. The input is the aggregated data that is stored in the database. The output is the stored database entry.

[0780] Step 6: Health Prediction

[0781] The server uses a generative AI model with data stored in a database to predict the user's physical condition. The input is integrated data including past physiological data, dietary data, and emotional data, and the physical condition is predicted through machine learning using the generative AI model. Specifically, Google Vertex AI and OpenAI GPT-4 are used to predict future physical condition and risks. The output is the physical condition prediction result.

[0782] Step 7: Risk prediction

[0783] The server predicts potential risks based on the health prediction results. The input is the health prediction results, and a generative AI model is applied to evaluate the presence and level of risk. The output is the risk prediction results.

[0784] Step 8: Advice Generation

[0785] The server generates specific advice and countermeasures for improving health status based on the results of health condition prediction and risk prediction. The input is the risk prediction result, and appropriate advice is generated using a generative AI model. The output is the generated advice.

[0786] Step 9: Notification

[0787] The server notifies the device of the generated advice. The device then communicates the advice to the user using push notifications or in-app messages. The input is the generated advice, which is sent to the device as a notification. The output is a notification message to the user.

[0788] Through this process, the system can comprehensively assess the user's health status, detect risks early, and take necessary measures.

[0789] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0790] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0791] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0792] [Third embodiment]

[0793] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0794] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0795] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0796] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0797] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0798] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0799] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0800] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0801] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0802] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0803] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0804] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0805] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[0806] Overall system configuration

[0807] Wearable devices

[0808] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[0809] Terminal

[0810] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the dietary and diary data entered by the user. This application integrates the physiological data received from the wearable device and the dietary and diary data entered by the user, and prepares it for transmission to the server.

[0811] server

[0812] The server receives data sent from the device and stores it in a database. Based on the stored data, a generative AI model is used to predict the user's physical condition and generate specific advice for improvement.

[0813] Program processing

[0814] Data collection and integration

[0815] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application running on the device receives this data, and also incorporates dietary and diary data entered by the user, and combines them to generate a single transmission data packet.

[0816] Sending data

[0817] The terminal sends the generated transmission data to the server automatically, but the user can also trigger the transmission manually if necessary.

[0818] Data storage and analysis

[0819] The server stores the received data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[0820] Advice generation and notification

[0821] The server generates specific advice to improve the user's health based on the results of the health prediction. The advice is sent to the device, which then notifies the user via push notification or in-app message. This allows the user to take actions that will contribute to improving their lifestyle the next day.

[0822] Specific examples

[0823] Example 1: For a general user

[0824] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. At night, the device consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you go to bed early and relax today," and the device notifies User A of this advice.

[0825] Example 2: For a company

[0826] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0827] The above is a specific embodiment for carrying out the present invention. This system can provide more effective health management and improvement for both individual users and companies.

[0828] The processing flow will be explained below.

[0829] Step 1:

[0830] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[0831] Step 2:

[0832] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[0833] Step 3:

[0834] The terminal periodically receives data from the wearable device and temporarily stores it. An application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[0835] Step 4:

[0836] The user uses an application on the device to input diary data about the day's diet and physical condition, specifically, what they ate for breakfast, lunch, and dinner, as well as changes in their mood.

[0837] Step 5:

[0838] The terminal combines the physiological data received from the wearable device with the dietary and diary data entered by the user to generate a single transmission data packet, which includes time series information and the user ID.

[0839] Step 6:

[0840] The terminal transmits the generated transmission data to the server. This transmission is usually automatic, but can also be triggered manually by the user.

[0841] Step 7:

[0842] The server stores the received data in a database using encryption technology to ensure data security.

[0843] Step 8:

[0844] The server uses a generative AI model to analyze the data stored in the database, which uses machine learning algorithms to predict the user's physical condition.

[0845] Step 9:

[0846] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[0847] Step 10:

[0848] The server predicts the user's health condition for the next day based on the predicted physical condition and generates specific advice for improving health, such as ensuring adequate sleep and recommending light exercise.

[0849] Step 11:

[0850] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[0851] Step 12:

[0852] The server analyzes the aggregated employee health data and generates reports for companies, including recommendations for improving employee benefits, which can be used to support corporate health management programs.

[0853] Example 1

[0854] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0855] In modern society, individuals are in need of ways to efficiently manage and improve their own health. However, conventional systems have difficulty integrating users' physiological data, dietary data, and diary data to provide health predictions and health improvement advice. Furthermore, companies lack systems that can effectively monitor the health status of their employees and provide improvement measures for employee benefits.

[0856] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0857] In this invention, the server includes a means for automatically or manually transmitting user data from the device to the server, a means for successively training the generative AI model based on new data to improve prediction accuracy, and a means for notifying the user of the generated advice via push notification or in-app message. This allows users to centrally manage their own physiological data, dietary data, and diary data and easily receive health predictions and health improvement advice. Companies can also aggregate employee health data and provide employee benefit improvement measures based on their health status.

[0858] A "wearable device" is a portable device used to collect physiological data such as a user's heart rate, exercise volume, and sleep information.

[0859] A "terminal" is an electronic device that has the function of receiving data from a wearable device, integrating the dietary data and diary data entered by the user, and transmitting the data to a server.

[0860] "Physiological data" is data that indicates the physiological state of the body, such as the user's heart rate, amount of exercise, and sleep time.

[0861] "Dietary data" refers to data that indicates information about the contents of meals consumed by the user.

[0862] "Diary data" is data entered by the user that records the user's physical condition and activities for that day.

[0863] "Transmission data" refers to data generated by integrating physiological data collected by the terminal from the wearable device, dietary data entered by the user, and diary data.

[0864] The "server" is a device that receives data sent from the device, stores it in a database, and uses a generative AI model to generate health predictions and health improvement advice.

[0865] A "database" is a collection of information that allows a server to systematically manage and store data received.

[0866] A "generative AI model" is an artificial intelligence model that generates predictions about a user's physical condition and health advice based on stored data.

[0867] "Health prediction" refers to the use of a generative AI model to predict a user's current and future health status.

[0868] "Advice for improving health condition" refers to specific suggestions and instructions for improving the user's health that are provided based on the predicted physical condition.

[0869] "Incremental learning" is the process by which a generative AI model incorporates new data and learns repeatedly to improve its prediction accuracy.

[0870] "Push notification" is a feature that allows an application to send a message directly to a user's device and provide specific information.

[0871] "Automatic transmission" is a function that allows a terminal to automatically transmit data to a server based on specific times or conditions.

[0872] "Manual transmission" is a function that allows the terminal to transmit data to the server in response to a user operation.

[0873] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[0874] Overall system configuration

[0875] The embodiment for implementing this system is configured as follows.

[0876] Wearable devices

[0877] Users wear wearable devices to collect physiological data such as heart rate, exercise volume (number of steps), and sleep information (quality and duration). The devices synchronize data with a terminal via Bluetooth or Wi-Fi. Specifically, users wear small devices (e.g., smartwatches) that fit on their wrists and can collect data throughout the day.

[0878] Terminal

[0879] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the meal data and diary data entered by the user. This application integrates the physiological data received from the wearable device with the meal data and diary data entered by the user and prepares it to be sent to the server. For example, when a user enters "Breakfast: tamagoyaki, salad, coffee" into the app, the meal data is imported.

[0880] server

[0881] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition and generate specific advice for improving their health. Furthermore, the server can continuously train the generative AI model based on new data to improve prediction accuracy. For example, it can generate advice such as, "Based on yesterday's data, you should increase your exercise today."

[0882] Specific examples

[0883] An embodiment of the system will be specifically described below.

[0884] Example 1: For a general user

[0885] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives this data from the wearable device, and User A enters a diary entry about the day's meals and physical condition into the app. That night, the device consolidates this data and sends it to the server. Late at night, the server stores the received data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you drink plenty of water and do some light exercise today," and the device notifies User A of this advice.

[0886] Example 2: For a company

[0887] All employees of a company wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report suggesting improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[0888] Prompt Sentence Examples

[0889] Below are some example prompts that can be used as input to a generative AI model:

[0890] "User A's average heart rate yesterday was 60 beats per minute, the number of steps taken was 8,000, and the amount of sleep was 7 hours. Please predict his / her physical condition today and generate appropriate health improvement advice."

[0891] "Use employee health data to suggest ways to improve employee benefits for companies."

[0892] This system can provide more effective health management and improvement for both individuals and businesses.

[0893] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0894] Step 1: Data collection

[0895] The user wears a wearable device to collect physiological data such as heart rate, exercise amount (number of steps), and sleep information. The input data includes heart rate, number of steps, and sleep information.

[0896] The wearable device collects this physiological data 24 hours a day and stores it in its internal memory. Specifically, the device measures heart rate at regular intervals and calculates the amount of exercise.

[0897] Step 2: Synchronize data

[0898] The terminal periodically synchronizes with the wearable device via Bluetooth or Wi-Fi and receives the collected physiological data. The input is physiological data from the wearable device, and the output is data stored in a database within the terminal.

[0899] Specifically, the terminal starts communicating with the wearable device every hour and downloads new data to the terminal.

[0900] Step 3: Entering food and diary data

[0901] The user uses an application installed on their smartphone to enter diary data about their diet and their physical condition for that day. The input is done manually by the user, and the output is saved in a database on the device.

[0902] As a concrete example, a user enters "Breakfast: toast, coffee" into a text field in an app.

[0903] Step 4: Integrate the data

[0904] The terminal integrates physiological data received from the wearable device and dietary and diary data entered by the user. The inputs are physiological data, dietary data, and diary data, and the output is an integrated data packet.

[0905] Specifically, the application in the device organizes each piece of data in chronological order and packs it into a single JSON data packet.

[0906] Step 5: Sending data

[0907] The terminal automatically transmits the combined data packet to the server, or the user can transmit it manually. The input is the combined data packet, and the output is the completion status of transmission to the server.

[0908] For example, a scheduled job runs overnight and sends a data packet as an HTTP POST request to a server's API endpoint.

[0909] Step 6: Save your data

[0910] The server stores the received data packet in a database. The input is the data packet from the terminal, and the output is the status of successful storage in the database.

[0911] Specifically, the server-side script receives the received data and performs an INSERT operation on the database.

[0912] Step 7: Analyze the data

[0913] The server uses the stored data as input to run the generative AI model and analyze the user's physical condition prediction and health status. The input is the data stored in the database, and the output is the physical condition prediction result.

[0914] Specifically, the server runs a generative AI model implemented in Python as a scheduled task, and calculates a health prediction based on features (e.g., heart rate, amount of exercise, sleep time, etc.).

[0915] Step 8: Generating Advice

[0916] The server generates advice for improving health based on the health prediction results. The input is the health prediction results, and the output is health advice.

[0917] For example, if the AI ​​model predicts that the user is feeling fatigued, the server will generate advice such as, "Try to do some light exercise today and get plenty of rest."

[0918] Step 9: Advice Notification

[0919] The device uses push notification and in-app messaging functions to notify the user of the advice received from the server. The input is the health advice from the server, and the output is the completion status of the notification to the user.

[0920] Specifically, the device's notification system will push a message to the user saying, "Today's advice: Try to do some light exercise and get plenty of rest."

[0921] (Application example 1)

[0922] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0923] Traditionally, employee health management and work efficiency improvement at logistics centers have been limited to fragmented data collection and individual measures, making it difficult to achieve effective and integrated management.In addition, it has been difficult to provide specific advice in real time that responds to changes in each employee's physical condition, resulting in problems that make it difficult to optimize employee performance and health.

[0924] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0925] In this invention, the server includes: means for collecting physiological data of a user using a wearable device; means for generating transmission data by integrating the physiological data collected from the wearable device and dietary data and diary data entered by the user using a terminal; means for receiving the transmission data and storing it in a database; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving health based on the physical condition prediction; means for notifying the terminal of the generated advice; and means for collecting physiological data, dietary data, and work records of employees at a logistics center and providing a physical condition prediction and advice for improving work performance based on the generative AI model. This makes it possible to individually manage the physical condition and work performance of each employee working at a logistics center and provide specific advice for improving health and work efficiency in real time.

[0926] A "wearable device" is a device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[0927] A "terminal" is a device that receives physiological data from a wearable device, imports dietary data and diary data entered by the user, and is an electronic device such as a smartphone or tablet that integrates this data to generate transmission data.

[0928] "Transmission data" refers to a data packet generated by integrating physiological data, dietary data, and diary data collected from the wearable device and the terminal, and is the entire data transmitted to the server.

[0929] The "server" is a computer system that receives data sent from the device, stores the data in a database, uses a generative AI model to predict the user's physical condition, and generates advice for improving their health.

[0930] The "generative AI model" is an artificial intelligence model that predicts a user's physical condition based on collected physiological data, dietary data, and diary data, and generates appropriate health improvement advice.

[0931] "Health prediction" is the process of using a generative AI model to predict a user's current and future health status, and to identify changes and risks in health based on analyzed data.

[0932] "Advice generation" is the process of generating specific guidelines and suggestions for improving the user's health based on the results of the health prediction.

[0933] A "logistics center" is a facility where operations such as storing, sorting, and preparing products for delivery are carried out, and is a work environment where employees work intensively.

[0934] "Employee physiological data" refers to physical data about employees, such as heart rate, activity level, and sleep information, that is collected by wearable devices.

[0935] "Work performance improvement advice" refers to specific suggestions and instructions for improving work efficiency and job performance based on employees' physiological data and work records.

[0936] This invention is a system aimed at managing the health and performance of employees working at logistics centers. It uses wearable devices, terminals (e.g., smartphones), and a server to collect and integrate employees' physiological data, dietary data, and work records, and uses a generative AI model to predict their physical condition and provide advice to improve their work performance.

[0937] Hardware and software used

[0938] Hardware

[0939] Wearable devices: Collect physiological data such as heart rate, exercise, and sleep information 24 hours a day.

[0940] Smartphone (or tablet): Receives data from the wearable device and runs an application that allows the user to enter food and diary data.

[0941] software

[0942] Server system: Utilizing a database and generative AI models, the system analyzes data and generates health predictions and health improvement advice.

[0943] Database system (e.g. MySQL, MongoDB): stores the data submitted by users.

[0944] Generative AI model (e.g., TensorFlow, PyTorch): Predicts the user's physical condition and generates advice.

[0945] Data collection

[0946] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume, and sleep information. A smartphone app receives this data from the wearable device and also incorporates dietary and diary data entered by the user. This integrated data is sent to a server as a data packet.

[0947] Data analysis

[0948] The server receives the transmitted data and stores it in a database. The generative AI model predicts the user's physical condition based on the stored data and generates specific advice for improving their health. For example, if the user's heart rate is high and the number of steps taken is low, advice such as "Take a break and take a deep breath" will be generated.

[0949] Advice Notice

[0950] The server sends the generated advice to a smartphone app and notifies the user, allowing the user to receive specific advice on improving their health and work efficiency in real time.

[0951] Specific examples

[0952] While User A is working at a logistics center, a wearable device collects data such as a heart rate of 130, steps taken 4,500, and sleep quality of 0.3. User A enters his / her breakfast "salad and yogurt," lunch "chicken and rice," and dinner "fish and vegetables" in a smartphone app, and writes in his / her diary, "I feel good today. Work is going smoothly." Using this data, the server uses a generative AI model to generate specific advice such as "Your heart rate is high, so take a break and take a deep breath. Walk a little more. I recommend you go to bed earlier tonight," and notifies the smartphone.

[0953] Prompt Sentence Examples

[0954] User: 32-year-old male, Occupation: Logistics center worker. Current heart rate: 130, steps: 4500, sleep quality: 0.3.

[0955] Food notes: Breakfast: Salad and yogurt, Lunch: Chicken and rice, Dinner: Fish and vegetables.

[0956] Health diary: I feel good today. Work is progressing smoothly.

[0957] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0958] Step 1:

[0959] The user wears a wearable device to collect physiological data. Specifically, the wearable device continuously records heart rate, physical activity (number of steps), and sleep information (quality and duration of sleep). This data is sent to a terminal in real time.

[0960] Input: Wearable device

[0961] Output: Physiological data (heart rate, steps, sleep information)

[0962] Step 2:

[0963] The terminal receives physiological data from the wearable device, and at the same time, the user inputs food and diary data using the terminal application, thereby collecting the user's daily health information.

[0964] Input: physiological data, dietary data, diary data

[0965] Output: Integrated data

[0966] Step 3:

[0967] The device combines the physiological data received with the dietary and diary data entered by the user to generate a single data packet for transmission. Specifically, each data field is compiled in a unified format to form a data packet.

[0968] Input: Integrated data

[0969] Output: Transmitted data packets

[0970] Step 4:

[0971] The terminal generates and transmits the transmitted data packets to the server, which can be transmitted in real time or at regular intervals.

[0972] Input: Transmit data packet

[0973] Output: Sending data packet (server side)

[0974] Step 5:

[0975] The server receives the transmitted data packets and stores them in a database, storing each piece of data in a corresponding field along with metadata such as the date and user ID.

[0976] Input: Transmit data packet

[0977] Output: Saved data (database)

[0978] Step 6:

[0979] The server uses the generative AI model to predict physical condition based on the stored data. Specifically, the server inputs the stored physiological data, dietary data, and diary data into the generative AI model and executes the prediction algorithm.

[0980] Input: Stored data (database)

[0981] Output: Health prediction results

[0982] Step 7:

[0983] The server generates specific advice for improving health based on the health prediction results. Using a generative AI model, the prediction results are analyzed and optimal advice is created for the user.

[0984] Input: Health prediction result

[0985] Output: Health improvement advice

[0986] Step 8:

[0987] The server sends the generated advice to the device, which receives it and displays it to the user as a push notification or in-app message.

[0988] Input: Health Improvement Advice

[0989] Output: Advice notified (terminal side)

[0990] The above are the specific processing steps for realizing this invention, which make it possible to manage the physical condition and work performance of each employee working at a logistics center in real time and provide appropriate advice.

[0991] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0992] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[0993] Overall system configuration

[0994] Wearable devices

[0995] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[0996] Terminal

[0997] The terminal (e.g., a smartphone) receives data from the wearable device and runs an application that incorporates the dietary and diary data entered by the user, as well as the emotion data analyzed by the emotion engine. This application then integrates this data and prepares it for transmission to the server.

[0998] Emotion Engine

[0999] The emotion engine analyzes the user's diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis techniques to extract emotions from the diary content.

[1000] server

[1001] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate. Furthermore, the server generates specific advice to improve the user's health.

[1002] Program processing

[1003] Data collection and integration

[1004] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application on the device receives this data and integrates it with dietary data and diary data entered by the user, and emotional data analyzed by an emotion engine.

[1005] Sending data

[1006] The device transmits the consolidated data to the server automatically, but can also be triggered manually by the user.

[1007] Data storage and analysis

[1008] The server stores the received integrated data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and their health condition for the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[1009] Advice generation and notification

[1010] Based on the results of the health prediction, the server generates specific advice to improve the user's health. This advice also takes into account emotional data, so it includes consideration of emotional aspects, such as "Today, it would be good to do some light exercise to change your mood."

[1011] The generated advice is sent to the device, which then notifies the user via push notifications or in-app messages, allowing the user to review and incorporate the advice into their daily lives.

[1012] Specific examples

[1013] Example 1: For a general user

[1014] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[1015] Example 2: For a company

[1016] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. An emotion engine analyzes the diary data and extracts emotional data. The devices send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[1017] The above is a specific embodiment of the present invention that combines an emotion engine. This system allows both individual users and companies to more effectively manage and improve their health conditions.

[1018] The processing flow will be explained below.

[1019] Step 1:

[1020] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[1021] Step 2:

[1022] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[1023] Step 3:

[1024] The terminal periodically receives data from the wearable device and temporarily stores it. At the same time, an application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[1025] Step 4:

[1026] The user uses an application on the device to enter diary data about the day's diet and physical condition, specifically recording what they ate for breakfast, lunch, and dinner, as well as changes in their emotions and notable events.

[1027] Step 5:

[1028] The emotion engine analyzes the diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis technology to extract and classify emotions from the diary content.

[1029] Step 6:

[1030] The terminal combines the physiological data received from the wearable device with the dietary data and diary data entered by the user, and the emotional data analyzed by the emotion engine, to generate a single transmission data packet, which includes time series information and the user ID.

[1031] Step 7:

[1032] The terminal sends the generated transmission data packets to the server, usually automatically, but can also be triggered manually by the user.

[1033] Step 8:

[1034] The server stores the received data in a database using encryption technology to ensure data security.

[1035] Step 9:

[1036] The server uses a generative AI model to analyze the data stored in the database. This AI model uses machine learning algorithms to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate.

[1037] Step 10:

[1038] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[1039] Step 11:

[1040] The server predicts the user's health condition for the next day based on the physical condition prediction and generates specific health improvement advice. For example, based on the prediction results, it may generate a suggestion such as "Today, it would be good to incorporate deep breathing and light exercise to relax."

[1041] Step 12:

[1042] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[1043] Step 13:

[1044] The server analyzes the aggregated employee health data and generates reports for companies that include recommendations for improving employee benefits. These reports can be used to support corporate health management programs, and may include recommendations such as introducing yoga classes or meditation sessions.

[1045] The above is the specific processing flow of the system that combines the emotion engine. This system enables more accurate health management and improvement that also takes into account the user's emotional state.

[1046] Example 2

[1047] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1048] In modern society, personal health management and improving corporate employee benefits are important issues. However, conventional health management systems rely on limited information sources, such as physiological and dietary data, making it difficult to provide comprehensive health predictions and advice that reflect users' emotions and daily events. It is also difficult to collect and analyze data in real time and provide appropriate advice to individual users. Furthermore, systems that enable companies to effectively aggregate employee health data and propose measures to improve employee benefits are insufficient.

[1049] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1050] In this invention, the server includes: means for collecting a user's physiological data using a wearable device; means for integrating the physiological data collected from the wearable device and dietary and diary data entered by the user via a terminal, and generating transmission data including emotion data analyzed by an emotion engine; means for transmitting the transmission data to the server; means for receiving the transmission data and storing it in a database; means for using the data stored in the database to use a generative AI model to predict the user's physical condition based on a prompt; means for generating advice for improving the user's health condition based on the predicted physical condition; and means for notifying the terminal of the generated advice. This enables integrated management of a user's personal physiological data, dietary data, diary data, and emotion data, and provides comprehensive health predictions and individual health improvement advice. Furthermore, companies can effectively aggregate employee health data and propose specific data-based improvements to employee benefits.

[1051] A "wearable device" is a device worn by a user that measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via a communication means.

[1052] A "terminal" is a device that manages physiological data collected from a wearable device, as well as dietary data and diary data entered by the user, integrates them to generate transmission data, and transmits this data to a server, including emotional data analyzed by an emotion engine.

[1053] The "emotion engine" is software that analyzes a user's diary data, recognizes their emotional state using text analysis technology, and extracts emotional data.

[1054] The "server" is a system that receives data sent from the device, stores it in a database, predicts physical condition using a generative AI model, generates advice for improving health, and notifies the device.

[1055] "Physiological data" refers to data relating to the user's physical condition, such as heart rate, amount of exercise, and sleep information.

[1056] "Dietary data" refers to data relating to the type, amount, and time of food intake by the user.

[1057] "Diary data" is text data in which a user describes daily events, emotions, physical condition, and the like.

[1058] "Emotion data" is data relating to the user's emotional state that is extracted by the emotion engine by analyzing the diary data.

[1059] A "generative AI model" is an artificial intelligence model that predicts physical condition based on stored data and generates health improvement advice, and includes models with sequential learning capabilities.

[1060] A "prompt sentence" is a sentence input into the generative AI model that specifically describes instructions for predicting physical condition and generating advice.

[1061] A "database" is a storage device that stores data received by the server and is used for subsequent analysis and learning.

[1062] "Advice" is a specific suggestion for improving the user's health based on the health predictions made by the generative AI model.

[1063] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[1064] Hardware and software used

[1065] Wearable device: A device that collects physiological data such as a user's heart rate, exercise amount (e.g., number of steps), and sleep information (e.g., quality and duration of sleep) 24 hours a day.

[1066] Terminal (e.g., smartphone): A device that runs an application that receives data from a wearable device and integrates the food and diary data entered by the user with the emotion data analyzed by the emotion engine.

[1067] Server: A device that receives data sent from the device, stores it in a database, predicts the user's physical condition using a generative AI model, and generates health improvement advice.

[1068] Emotion engine: Software that analyzes the user's diary data and recognizes their emotional state (e.g., joy, sadness, anger, surprise).

[1069] Data collection and integration

[1070] The user puts on a wearable device. The device measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via Bluetooth or Wi-Fi. The user uses the terminal's application to enter food data (e.g., one apple, two slices of toast, coffee) and diary data (e.g., "Today was a stressful day"). The emotion engine analyzes the diary data and extracts the emotion data, such as "stressful." This data is then integrated into the terminal.

[1071] Data transmission and storage

[1072] The device sends the integrated data to the server, which can be done automatically or manually by the user, and the server stores the received data in a database.

[1073] Health prediction using generative AI models

[1074] The server inputs the data stored in the database into a generative AI model to predict the user's physical condition for the day and the next day. For example, a prompt might be used: "Based on user A's heart rate data, exercise data, sleep data, dietary data, diary data, and emotion data, please predict tomorrow's physical condition and generate specific health improvement advice."

[1075] Generate and notify health improvement advice

[1076] The server generates specific advice to improve the user's health based on the generative AI model. This advice also takes into account emotional data, so it may include, for example, "Today, it would be good to incorporate deep breathing and light exercise to relax." The generated advice is sent to the device, which then notifies the user via push notification or in-app message.

[1077] Specific examples

[1078] For general users

[1079] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[1080] The system allows both individuals and businesses to more effectively manage and improve their health.

[1081] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1082] Step 1:

[1083] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day. The collected data is temporarily stored in the device's memory.

[1084] Input: User's heart rate, exercise, and sleep information

[1085] Output: Physiological data from a wearable device

[1086] Step 2:

[1087] The wearable device uses Bluetooth or Wi-Fi to transmit the collected physiological data to a terminal, which receives the data through a dedicated application.

[1088] Input: Physiological data from a wearable device

[1089] Output: Physiological data to the device

[1090] Step 3:

[1091] The user uses the device's application to input meal data (date, time, and food eaten) and diary data (diary contents), which are then stored in a database on the device.

[1092] Input: User's meal data, diary data

[1093] Output: Meal data and diary data stored on the device

[1094] Step 4:

[1095] The device application uses an emotion engine to analyze the diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Emotional data is extracted and integrated into the device's database.

[1096] Input: Diary data

[1097] Output: Emotion data

[1098] Step 5:

[1099] The terminal integrates physiological data from the wearable device, dietary data entered by the user, diary data, and emotion data generated by the emotion engine to generate transmission data, which is then sent to the server.

[1100] Input: physiological data, dietary data, diary data, emotional data

[1101] Output: Data sent to the server

[1102] Step 6:

[1103] The server receives the integrated data sent from the devices and stores it in a database, which is used for subsequent analysis and learning.

[1104] Input: Send data

[1105] Output: Data saved to database

[1106] Step 7:

[1107] The server inputs the integrated data stored in the database into the generative AI model to predict the user's physical condition on that day and the next day. The output of the generative AI model is stored in the database as the physical condition prediction result.

[1108] Input: Prompt: "Please predict tomorrow's physical condition based on user A's heart rate data, exercise amount data, sleep data, dietary data, diary data, and emotional data, and generate specific health improvement advice."

[1109] Output: Health prediction results

[1110] Step 8:

[1111] The server generates specific advice for improving health based on the health prediction results of the AI ​​model. This advice is created taking into account emotional data.

[1112] Input: Health prediction result

[1113] Output: Health improvement advice

[1114] Step 9:

[1115] The server generates health improvement advice and sends it to the device. The device notifies the user of this advice via push notifications or in-app messages. The user can then check the advice content on their device.

[1116] Input: Health Improvement Advice

[1117] Output: Notification information to the user

[1118] Through the above steps, a system is realized that manages a user's personal physiological data, dietary data, diary data, and emotional data in an integrated manner, and provides comprehensive health predictions and individual advice on improving health.

[1119] (Application example 2)

[1120] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1121] Conventional health management systems often collect and analyze users' physiological, dietary, and emotional data separately, and systems that manage and analyze this information in an integrated manner are rare. Furthermore, particularly in security services where risk management is crucial, risk prediction based on changes in the user's emotions and physical condition is currently insufficient. This makes it difficult to comprehensively evaluate a user's health status, detect risks early, and take countermeasures. Therefore, there is a need for a new system that can comprehensively analyze a user's physiological and emotional data and provide specific advice for risk management and health improvement, as well as incident response.

[1122] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting physiological data of the user using a wearable device; means for integrating the physiological data collected from the wearable device and the dietary data and diary data entered by the user by a terminal to generate transmission data; means for receiving the transmission data and storing it in a database by the server; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving the health condition based on the physical condition prediction; means for notifying the terminal of the generated advice; means for analyzing the diary data using an emotion analysis engine and extracting emotion data; means for predicting potential risks based on the subject's emotion data and physiological data; and means for generating specific countermeasures and response instructions based on the risk prediction and notifying the terminal. This enables a comprehensive evaluation of the user's health condition, enabling early detection of risks, and the implementation of countermeasures.

[1123] A "wearable device" is an electronic device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[1124] A "terminal" is an electronic device that receives data from a wearable device, integrates the meal data and diary data entered by the user, and generates transmission data, and includes smartphones and tablets.

[1125] An "emotion analysis engine" is a software component that uses text analysis technology to recognize emotions from text data such as a user's diary data and extract emotion data.

[1126] A "generative AI model" is a machine learning model that uses integrated data as input to predict a user's physical condition and risks, and improves prediction accuracy by successively learning based on new data.

[1127] The "server" is an electronic device that receives data sent from the device, stores it in a database, and processes it using a generative AI model to analyze the data and predict the user's health condition.

[1128] "Database" means an information management system for storing integrated data received by the server, and for enabling efficient search and utilization of required information.

[1129] "Notification means" is a function for notifying the user of advice and risk countermeasure instructions generated by the server, and is done through push notifications or in-app messages.

[1130] "Physiological data" refers to data relating to the user's physical condition, such as the user's heart rate, amount of exercise, and sleep information, and is collected by a wearable device.

[1131] "Emotion data" is data relating to the user's emotional state extracted from text such as diary data by an emotion analysis engine, and includes emotions such as joy, sadness, anger, and surprise.

[1132] "Risk prediction" refers to predictions made by a generative AI model based on emotional and physiological data to estimate the user's health and safety risks.

[1133] The "advice generation means" is a function that generates specific advice and measures to improve the user's health condition based on the results of physical condition prediction and risk prediction.

[1134] This invention is a system for predicting and improving health status by integrating and managing a user's physiological data, dietary data, diary data, and emotional data. This system is composed of a wearable device, a terminal, a server, an emotion analysis engine, and a generative AI model.

[1135] Wearable devices

[1136] Wearable devices collect physiological data such as the user's heart rate, activity, and sleep information 24 hours a day. For example, they measure heart rate, steps, and sleep quality. The collected data is synchronized to a device via Bluetooth or Wi-Fi. Examples of specific devices that use this include smartwatches and fitness trackers.

[1137] Terminal

[1138] The device, which is typically a smartphone or tablet, collects physiological data received from the wearable device and integrates it with dietary and diary data entered by the user. Emotional data analyzed by an emotion analysis engine is also collected. The integrated data is then sent to a server, where the application generates advice and notifies users about risks based on the collected data.

[1139] Sentiment Analysis Engine

[1140] The sentiment analysis engine uses text analysis technology to analyze the user's diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Specifically, it extracts emotions from text using natural language processing tools such as Google Cloud Natural Language API and IBM Watson NLU. This emotional data is used to predict the user's physical condition and risks.

[1141] server

[1142] The server receives and stores the integrated data sent from the device. The server stores the received data in a database and uses a generative AI model to predict physical condition and risks. Specific examples of AI models used include Google Vertex AI and OpenAI GPT-4. Specific advice and countermeasures are generated based on the predicted risks and health condition.

[1143] Risk Management and Notification

[1144] The server uses a generative AI model to predict potential risks based on the subject's emotional and physiological data. Based on the results, the server generates specific countermeasures and response instructions and notifies the device via push notifications or in-app messages.

[1145] Specific examples

[1146] Example 1: Security guard

[1147] A wearable device worn by security guards collects physiological data such as heart rate and exercise volume. A smartphone app receives this data, and the security guards enter a diary entry about their activities and emotional state for the day. If the emotion analysis engine determines from the diary data that the guard is feeling "high stress," the server receives this data and uses a generative AI model to predict risk. Specific advice, such as "reduce your alert level today and take a moderate break," is generated and sent to the guard's smartphone.

[1148] Prompt Sentence Examples

[1149] Using the user's physiological data, dietary data, diary data, and related emotional data as input, predict risks for today and the next 24 hours, and generate appropriate advice and incident response instructions based on the results.

[1150] This system allows for a comprehensive assessment of the user's health status, allowing for early detection of risks and the implementation of appropriate measures.

[1151] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1152] Step 1: Data collection

[1153] The user wears a wearable device to collect physiological data such as heart rate, exercise volume, and sleep information. This data is synchronized to the user's device via Bluetooth or Wi-Fi. The input physiological data are heart rate, steps, and sleep duration and quality, which are recorded in real time. The output is physiological data stored on the device.

[1154] Step 2: Enter user data

[1155] The user uses a terminal to input dietary data and diary data. Dietary data includes the contents of meals and calorie intake, while diary data records information about the user's emotional state and physical condition for that day. The input is data manually entered by the user, which is received and integrated by the terminal. The output is recorded data on the terminal that reflects the input.

[1156] Step 3: Sentiment Analysis

[1157] The device uses an emotion analysis engine to analyze the text of the diary data and extract emotional data. The input is the text information of the diary data, and the emotional state is extracted through text analysis using natural language processing. Specifically, emotions (joy, sadness, anger, surprise, etc.) are identified using Google Cloud Natural Language API, etc. The output is the extracted emotional data.

[1158] Step 4: Data integration and transmission

[1159] The device integrates the collected physiological data, dietary data, and analyzed emotional data to generate transmission data. The generated transmission data is then sent to the server. The input is physiological data, dietary data, and emotional data, which are processed to integrate them. The output is the integrated transmission data.

[1160] Step 5: Save Data

[1161] The server stores the aggregated data received from the terminals in a database. The input is the aggregated data that is stored in the database. The output is the stored database entry.

[1162] Step 6: Health Prediction

[1163] The server uses a generative AI model with data stored in a database to predict the user's physical condition. The input is integrated data including past physiological data, dietary data, and emotional data, and the physical condition is predicted through machine learning using the generative AI model. Specifically, Google Vertex AI and OpenAI GPT-4 are used to predict future physical condition and risks. The output is the physical condition prediction result.

[1164] Step 7: Risk prediction

[1165] The server predicts potential risks based on the health prediction results. The input is the health prediction results, and a generative AI model is applied to evaluate the presence and level of risk. The output is the risk prediction results.

[1166] Step 8: Advice Generation

[1167] The server generates specific advice and countermeasures for improving health status based on the results of health condition prediction and risk prediction. The input is the risk prediction result, and appropriate advice is generated using a generative AI model. The output is the generated advice.

[1168] Step 9: Notification

[1169] The server notifies the device of the generated advice. The device then communicates the advice to the user using push notifications or in-app messages. The input is the generated advice, which is sent to the device as a notification. The output is a notification message to the user.

[1170] Through this process, the system can comprehensively assess the user's health status, detect risks early, and take necessary measures.

[1171] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1172] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1173] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1174] [Fourth embodiment]

[1175] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1176] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1177] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1178] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1179] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1180] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1181] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1182] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1183] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1184] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1185] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1186] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1187] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1188] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[1189] Overall system configuration

[1190] Wearable devices

[1191] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[1192] Terminal

[1193] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the dietary and diary data entered by the user. This application integrates the physiological data received from the wearable device and the dietary and diary data entered by the user, and prepares it for transmission to the server.

[1194] server

[1195] The server receives data sent from the device and stores it in a database. Based on the stored data, a generative AI model is used to predict the user's physical condition and generate specific advice for improvement.

[1196] Program processing

[1197] Data collection and integration

[1198] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application running on the device receives this data, and also incorporates dietary and diary data entered by the user, and combines them to generate a single transmission data packet.

[1199] Sending data

[1200] The terminal sends the generated transmission data to the server automatically, but the user can also trigger the transmission manually if necessary.

[1201] Data storage and analysis

[1202] The server stores the received data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[1203] Advice generation and notification

[1204] The server generates specific advice to improve the user's health based on the results of the health prediction. The advice is sent to the device, which then notifies the user via push notification or in-app message. This allows the user to take actions that will contribute to improving their lifestyle the next day.

[1205] Specific examples

[1206] Example 1: For a general user

[1207] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. At night, the device consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you go to bed early and relax today," and the device notifies User A of this advice.

[1208] Example 2: For a company

[1209] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[1210] The above is a specific embodiment for carrying out the present invention. This system can provide more effective health management and improvement for both individual users and companies.

[1211] The processing flow will be explained below.

[1212] Step 1:

[1213] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[1214] Step 2:

[1215] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[1216] Step 3:

[1217] The terminal periodically receives data from the wearable device and temporarily stores it. An application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[1218] Step 4:

[1219] The user uses an application on the device to input diary data about the day's diet and physical condition, specifically, what they ate for breakfast, lunch, and dinner, as well as changes in their mood.

[1220] Step 5:

[1221] The terminal combines the physiological data received from the wearable device with the dietary and diary data entered by the user to generate a single transmission data packet, which includes time series information and the user ID.

[1222] Step 6:

[1223] The terminal transmits the generated transmission data to the server. This transmission is usually automatic, but can also be triggered manually by the user.

[1224] Step 7:

[1225] The server stores the received data in a database using encryption technology to ensure data security.

[1226] Step 8:

[1227] The server uses a generative AI model to analyze the data stored in the database, which uses machine learning algorithms to predict the user's physical condition.

[1228] Step 9:

[1229] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[1230] Step 10:

[1231] The server predicts the user's health condition for the next day based on the predicted physical condition and generates specific advice for improving health, such as ensuring adequate sleep and recommending light exercise.

[1232] Step 11:

[1233] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[1234] Step 12:

[1235] The server analyzes the aggregated employee health data and generates reports for companies, including recommendations for improving employee benefits, which can be used to support corporate health management programs.

[1236] Example 1

[1237] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1238] In modern society, individuals are in need of ways to efficiently manage and improve their own health. However, conventional systems have difficulty integrating users' physiological data, dietary data, and diary data to provide health predictions and health improvement advice. Furthermore, companies lack systems that can effectively monitor the health status of their employees and provide improvement measures for employee benefits.

[1239] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1240] In this invention, the server includes a means for automatically or manually transmitting user data from the device to the server, a means for successively training the generative AI model based on new data to improve prediction accuracy, and a means for notifying the user of the generated advice via push notification or in-app message. This allows users to centrally manage their own physiological data, dietary data, and diary data and easily receive health predictions and health improvement advice. Companies can also aggregate employee health data and provide employee benefit improvement measures based on their health status.

[1241] A "wearable device" is a portable device used to collect physiological data such as a user's heart rate, exercise volume, and sleep information.

[1242] A "terminal" is an electronic device that has the function of receiving data from a wearable device, integrating the dietary data and diary data entered by the user, and transmitting the data to a server.

[1243] "Physiological data" is data that indicates the physiological state of the body, such as the user's heart rate, amount of exercise, and sleep time.

[1244] "Dietary data" refers to data that indicates information about the contents of meals consumed by the user.

[1245] "Diary data" is data entered by the user that records the user's physical condition and activities for that day.

[1246] "Transmission data" refers to data generated by integrating physiological data collected by the terminal from the wearable device, dietary data entered by the user, and diary data.

[1247] The "server" is a device that receives data sent from the device, stores it in a database, and uses a generative AI model to generate health predictions and health improvement advice.

[1248] A "database" is a collection of information that allows a server to systematically manage and store data received.

[1249] A "generative AI model" is an artificial intelligence model that generates predictions about a user's physical condition and health advice based on stored data.

[1250] "Health prediction" refers to the use of a generative AI model to predict a user's current and future health status.

[1251] "Advice for improving health condition" refers to specific suggestions and instructions for improving the user's health that are provided based on the predicted physical condition.

[1252] "Incremental learning" is the process by which a generative AI model incorporates new data and learns repeatedly to improve its prediction accuracy.

[1253] "Push notification" is a feature that allows an application to send a message directly to a user's device and provide specific information.

[1254] "Automatic transmission" is a function that allows a terminal to automatically transmit data to a server based on specific times or conditions.

[1255] "Manual transmission" is a function that allows the terminal to transmit data to the server in response to a user operation.

[1256] The present invention relates to a system that uses a wearable device, a terminal, and a server to manage a user's physiological data, dietary data, and diary data in an integrated manner, and provides health predictions and advice on improving health.

[1257] Overall system configuration

[1258] The embodiment for implementing this system is configured as follows.

[1259] Wearable devices

[1260] Users wear wearable devices to collect physiological data such as heart rate, exercise volume (number of steps), and sleep information (quality and duration). The devices synchronize data with a terminal via Bluetooth or Wi-Fi. Specifically, users wear small devices (e.g., smartwatches) that fit on their wrists and can collect data throughout the day.

[1261] Terminal

[1262] The terminal (e.g., a smartphone) runs an application that receives data from the wearable device and imports the meal data and diary data entered by the user. This application integrates the physiological data received from the wearable device with the meal data and diary data entered by the user and prepares it to be sent to the server. For example, when a user enters "Breakfast: tamagoyaki, salad, coffee" into the app, the meal data is imported.

[1263] server

[1264] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition and generate specific advice for improving their health. Furthermore, the server can continuously train the generative AI model based on new data to improve prediction accuracy. For example, it can generate advice such as, "Based on yesterday's data, you should increase your exercise today."

[1265] Specific examples

[1266] An embodiment of the system will be specifically described below.

[1267] Example 1: For a general user

[1268] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the device receives this data from the wearable device, and User A enters a diary entry about the day's meals and physical condition into the app. That night, the device consolidates this data and sends it to the server. Late at night, the server stores the received data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "It is recommended that you drink plenty of water and do some light exercise today," and the device notifies User A of this advice.

[1269] Example 2: For a company

[1270] All employees of a company wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. The devices then send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report suggesting improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[1271] Prompt Sentence Examples

[1272] Below are some example prompts that can be used as input to a generative AI model:

[1273] "User A's average heart rate yesterday was 60 beats per minute, the number of steps taken was 8,000, and the amount of sleep was 7 hours. Please predict his / her physical condition today and generate appropriate health improvement advice."

[1274] "Use employee health data to suggest ways to improve employee benefits for companies."

[1275] This system can provide more effective health management and improvement for both individuals and businesses.

[1276] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1277] Step 1: Data collection

[1278] The user wears a wearable device to collect physiological data such as heart rate, exercise amount (number of steps), and sleep information. The input data includes heart rate, number of steps, and sleep information.

[1279] The wearable device collects this physiological data 24 hours a day and stores it in its internal memory. Specifically, the device measures heart rate at regular intervals and calculates the amount of exercise.

[1280] Step 2: Synchronize data

[1281] The terminal periodically synchronizes with the wearable device via Bluetooth or Wi-Fi and receives the collected physiological data. The input is physiological data from the wearable device, and the output is data stored in a database within the terminal.

[1282] Specifically, the terminal starts communicating with the wearable device every hour and downloads new data to the terminal.

[1283] Step 3: Entering food and diary data

[1284] The user uses an application installed on their smartphone to enter diary data about their diet and their physical condition for that day. The input is done manually by the user, and the output is saved in a database on the device.

[1285] As a concrete example, a user enters "Breakfast: toast, coffee" into a text field in an app.

[1286] Step 4: Integrate the data

[1287] The terminal integrates physiological data received from the wearable device and dietary and diary data entered by the user. The inputs are physiological data, dietary data, and diary data, and the output is an integrated data packet.

[1288] Specifically, the application in the device organizes each piece of data in chronological order and packs it into a single JSON data packet.

[1289] Step 5: Sending data

[1290] The terminal automatically transmits the combined data packet to the server, or the user can transmit it manually. The input is the combined data packet, and the output is the completion status of transmission to the server.

[1291] For example, a scheduled job runs overnight and sends a data packet as an HTTP POST request to a server's API endpoint.

[1292] Step 6: Save your data

[1293] The server stores the received data packet in a database. The input is the data packet from the terminal, and the output is the status of successful storage in the database.

[1294] Specifically, the server-side script receives the received data and performs an INSERT operation on the database.

[1295] Step 7: Analyze the data

[1296] The server uses the stored data as input to run the generative AI model and analyze the user's physical condition prediction and health status. The input is the data stored in the database, and the output is the physical condition prediction result.

[1297] Specifically, the server runs a generative AI model implemented in Python as a scheduled task, and calculates a health prediction based on features (e.g., heart rate, amount of exercise, sleep time, etc.).

[1298] Step 8: Generating Advice

[1299] The server generates advice for improving health based on the health prediction results. The input is the health prediction results, and the output is health advice.

[1300] For example, if the AI ​​model predicts that the user is feeling fatigued, the server will generate advice such as, "Try to do some light exercise today and get plenty of rest."

[1301] Step 9: Advice Notification

[1302] The device uses push notification and in-app messaging functions to notify the user of the advice received from the server. The input is the health advice from the server, and the output is the completion status of the notification to the user.

[1303] Specifically, the device's notification system will push a message to the user saying, "Today's advice: Try to do some light exercise and get plenty of rest."

[1304] (Application example 1)

[1305] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1306] Traditionally, employee health management and work efficiency improvement at logistics centers have been limited to fragmented data collection and individual measures, making it difficult to achieve effective and integrated management.In addition, it has been difficult to provide specific advice in real time that responds to changes in each employee's physical condition, resulting in problems that make it difficult to optimize employee performance and health.

[1307] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1308] In this invention, the server includes: means for collecting physiological data of a user using a wearable device; means for generating transmission data by integrating the physiological data collected from the wearable device and dietary data and diary data entered by the user using a terminal; means for receiving the transmission data and storing it in a database; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving health based on the physical condition prediction; means for notifying the terminal of the generated advice; and means for collecting physiological data, dietary data, and work records of employees at a logistics center and providing a physical condition prediction and advice for improving work performance based on the generative AI model. This makes it possible to individually manage the physical condition and work performance of each employee working at a logistics center and provide specific advice for improving health and work efficiency in real time.

[1309] A "wearable device" is a device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[1310] A "terminal" is a device that receives physiological data from a wearable device, imports dietary data and diary data entered by the user, and is an electronic device such as a smartphone or tablet that integrates this data to generate transmission data.

[1311] "Transmission data" refers to a data packet generated by integrating physiological data, dietary data, and diary data collected from the wearable device and the terminal, and is the entire data transmitted to the server.

[1312] The "server" is a computer system that receives data sent from the device, stores the data in a database, uses a generative AI model to predict the user's physical condition, and generates advice for improving their health.

[1313] The "generative AI model" is an artificial intelligence model that predicts a user's physical condition based on collected physiological data, dietary data, and diary data, and generates appropriate health improvement advice.

[1314] "Health prediction" is the process of using a generative AI model to predict a user's current and future health status, and to identify changes and risks in health based on analyzed data.

[1315] "Advice generation" is the process of generating specific guidelines and suggestions for improving the user's health based on the results of the health prediction.

[1316] A "logistics center" is a facility where operations such as storing, sorting, and preparing products for delivery are carried out, and is a work environment where employees work intensively.

[1317] "Employee physiological data" refers to physical data about employees, such as heart rate, activity level, and sleep information, that is collected by wearable devices.

[1318] "Work performance improvement advice" refers to specific suggestions and instructions for improving work efficiency and job performance based on employees' physiological data and work records.

[1319] This invention is a system aimed at managing the health and performance of employees working at logistics centers. It uses wearable devices, terminals (e.g., smartphones), and a server to collect and integrate employees' physiological data, dietary data, and work records, and uses a generative AI model to predict their physical condition and provide advice to improve their work performance.

[1320] Hardware and software used

[1321] Hardware

[1322] Wearable devices: Collect physiological data such as heart rate, exercise, and sleep information 24 hours a day.

[1323] Smartphone (or tablet): Receives data from the wearable device and runs an application that allows the user to enter food and diary data.

[1324] software

[1325] Server system: Utilizing a database and generative AI models, the system analyzes data and generates health predictions and health improvement advice.

[1326] Database system (e.g. MySQL, MongoDB): stores the data submitted by users.

[1327] Generative AI model (e.g., TensorFlow, PyTorch): Predicts the user's physical condition and generates advice.

[1328] Data collection

[1329] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume, and sleep information. A smartphone app receives this data from the wearable device and also incorporates dietary and diary data entered by the user. This integrated data is sent to a server as a data packet.

[1330] Data analysis

[1331] The server receives the transmitted data and stores it in a database. The generative AI model predicts the user's physical condition based on the stored data and generates specific advice for improving their health. For example, if the user's heart rate is high and the number of steps taken is low, advice such as "Take a break and take a deep breath" will be generated.

[1332] Advice Notice

[1333] The server sends the generated advice to a smartphone app and notifies the user, allowing the user to receive specific advice on improving their health and work efficiency in real time.

[1334] Specific examples

[1335] While User A is working at a logistics center, a wearable device collects data such as a heart rate of 130, steps taken 4,500, and sleep quality of 0.3. User A enters his / her breakfast "salad and yogurt," lunch "chicken and rice," and dinner "fish and vegetables" in a smartphone app, and writes in his / her diary, "I feel good today. Work is going smoothly." Using this data, the server uses a generative AI model to generate specific advice such as "Your heart rate is high, so take a break and take a deep breath. Walk a little more. I recommend you go to bed earlier tonight," and notifies the smartphone.

[1336] Prompt Sentence Examples

[1337] User: 32-year-old male, Occupation: Logistics center worker. Current heart rate: 130, steps: 4500, sleep quality: 0.3.

[1338] Food notes: Breakfast: Salad and yogurt, Lunch: Chicken and rice, Dinner: Fish and vegetables.

[1339] Health diary: I feel good today. Work is progressing smoothly.

[1340] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1341] Step 1:

[1342] The user wears a wearable device to collect physiological data. Specifically, the wearable device continuously records heart rate, physical activity (number of steps), and sleep information (quality and duration of sleep). This data is sent to a terminal in real time.

[1343] Input: Wearable device

[1344] Output: Physiological data (heart rate, steps, sleep information)

[1345] Step 2:

[1346] The terminal receives physiological data from the wearable device, and at the same time, the user inputs food and diary data using the terminal application, thereby collecting the user's daily health information.

[1347] Input: physiological data, dietary data, diary data

[1348] Output: Integrated data

[1349] Step 3:

[1350] The device combines the physiological data received with the dietary and diary data entered by the user to generate a single data packet for transmission. Specifically, each data field is compiled in a unified format to form a data packet.

[1351] Input: Integrated data

[1352] Output: Transmitted data packets

[1353] Step 4:

[1354] The terminal generates and transmits the transmitted data packets to the server, which can be transmitted in real time or at regular intervals.

[1355] Input: Transmit data packet

[1356] Output: Sending data packet (server side)

[1357] Step 5:

[1358] The server receives the transmitted data packets and stores them in a database, storing each piece of data in a corresponding field along with metadata such as the date and user ID.

[1359] Input: Transmit data packet

[1360] Output: Saved data (database)

[1361] Step 6:

[1362] The server uses the generative AI model to predict physical condition based on the stored data. Specifically, the server inputs the stored physiological data, dietary data, and diary data into the generative AI model and executes the prediction algorithm.

[1363] Input: Stored data (database)

[1364] Output: Health prediction results

[1365] Step 7:

[1366] The server generates specific advice for improving health based on the health prediction results. Using a generative AI model, the prediction results are analyzed and optimal advice is created for the user.

[1367] Input: Health prediction result

[1368] Output: Health improvement advice

[1369] Step 8:

[1370] The server sends the generated advice to the device, which receives it and displays it to the user as a push notification or in-app message.

[1371] Input: Health Improvement Advice

[1372] Output: Advice notified (terminal side)

[1373] The above are the specific processing steps for realizing this invention, which make it possible to manage the physical condition and work performance of each employee working at a logistics center in real time and provide appropriate advice.

[1374] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1375] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[1376] Overall system configuration

[1377] Wearable devices

[1378] Wearable devices collect physiological data such as the user's heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 / 7. The devices synchronize data with the user's mobile device via Bluetooth or Wi-Fi.

[1379] Terminal

[1380] The terminal (e.g., a smartphone) receives data from the wearable device and runs an application that incorporates the dietary and diary data entered by the user, as well as the emotion data analyzed by the emotion engine. This application then integrates this data and prepares it for transmission to the server.

[1381] Emotion Engine

[1382] The emotion engine analyzes the user's diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis techniques to extract emotions from the diary content.

[1383] server

[1384] The server receives data sent from the device and stores it in a database. Based on the stored data, it uses a generative AI model to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate. Furthermore, the server generates specific advice to improve the user's health.

[1385] Program processing

[1386] Data collection and integration

[1387] When a user wears a wearable device, physiological data such as heart rate, exercise volume, and sleep information is collected. In parallel, an application on the device receives this data and integrates it with dietary data and diary data entered by the user, and emotional data analyzed by an emotion engine.

[1388] Sending data

[1389] The device transmits the consolidated data to the server automatically, but can also be triggered manually by the user.

[1390] Data storage and analysis

[1391] The server stores the received integrated data in a database. The generative AI model takes the stored data as input and predicts the user's physical condition on that day and their health condition for the next day. The model's incremental learning function allows it to learn from new data and improve its prediction accuracy.

[1392] Advice generation and notification

[1393] Based on the results of the health prediction, the server generates specific advice to improve the user's health. This advice also takes into account emotional data, so it includes consideration of emotional aspects, such as "Today, it would be good to do some light exercise to change your mood."

[1394] The generated advice is sent to the device, which then notifies the user via push notifications or in-app messages, allowing the user to review and incorporate the advice into their daily lives.

[1395] Specific examples

[1396] Example 1: For a general user

[1397] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[1398] Example 2: For a company

[1399] All company employees wear wearable devices, and the devices collect physiological, dietary, and diary data from each employee. An emotion engine analyzes the diary data and extracts emotional data. The devices send this data to a server, which then uses the aggregated data to analyze health trends. The generative AI model predicts employees' health status and generates a report proposing improvements to the company's employee benefits. For example, the report may include suggestions such as "introducing yoga classes and meditation time is recommended." This report serves as a guideline for companies to effectively manage their employees' health.

[1400] The above is a specific embodiment of the present invention that combines an emotion engine. This system allows both individual users and companies to more effectively manage and improve their health conditions.

[1401] The processing flow will be explained below.

[1402] Step 1:

[1403] The user wears a wearable device, which collects physiological data such as heart rate, physical activity (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day.

[1404] Step 2:

[1405] The wearable device transmits the collected physiological data to a terminal (smartphone) via Bluetooth or Wi-Fi.

[1406] Step 3:

[1407] The terminal periodically receives data from the wearable device and temporarily stores it. At the same time, an application running on the terminal provides a user interface and prompts the user to input meal data and diary data.

[1408] Step 4:

[1409] The user uses an application on the device to enter diary data about the day's diet and physical condition, specifically recording what they ate for breakfast, lunch, and dinner, as well as changes in their emotions and notable events.

[1410] Step 5:

[1411] The emotion engine analyzes the diary data and recognizes the user's emotional state (e.g., joy, sadness, anger, surprise). The emotion engine uses text analysis technology to extract and classify emotions from the diary content.

[1412] Step 6:

[1413] The terminal combines the physiological data received from the wearable device with the dietary data and diary data entered by the user, and the emotional data analyzed by the emotion engine, to generate a single transmission data packet, which includes time series information and the user ID.

[1414] Step 7:

[1415] The terminal sends the generated transmission data packets to the server, usually automatically, but can also be triggered manually by the user.

[1416] Step 8:

[1417] The server stores the received data in a database using encryption technology to ensure data security.

[1418] Step 9:

[1419] The server uses a generative AI model to analyze the data stored in the database. This AI model uses machine learning algorithms to predict the user's physical condition. This prediction also includes emotional data, which is expected to be more accurate.

[1420] Step 10:

[1421] The generative AI model learns incrementally from new data to improve its prediction accuracy, and the server manages this process automatically.

[1422] Step 11:

[1423] The server predicts the user's health condition for the next day based on the physical condition prediction and generates specific health improvement advice. For example, based on the prediction results, it may generate a suggestion such as "Today, it would be good to incorporate deep breathing and light exercise to relax."

[1424] Step 12:

[1425] The device will notify the user of the health improvement advice received from the server via push notifications or in-app messages, allowing the user to check the advice and incorporate it into their daily lives.

[1426] Step 13:

[1427] The server analyzes the aggregated employee health data and generates reports for companies that include recommendations for improving employee benefits. These reports can be used to support corporate health management programs, and may include recommendations such as introducing yoga classes or meditation sessions.

[1428] The above is the specific processing flow of the system that combines the emotion engine. This system enables more accurate health management and improvement that also takes into account the user's emotional state.

[1429] Example 2

[1430] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1431] In modern society, personal health management and improving corporate employee benefits are important issues. However, conventional health management systems rely on limited information sources, such as physiological and dietary data, making it difficult to provide comprehensive health predictions and advice that reflect users' emotions and daily events. It is also difficult to collect and analyze data in real time and provide appropriate advice to individual users. Furthermore, systems that enable companies to effectively aggregate employee health data and propose measures to improve employee benefits are insufficient.

[1432] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1433] In this invention, the server includes: means for collecting a user's physiological data using a wearable device; means for integrating the physiological data collected from the wearable device and dietary and diary data entered by the user via a terminal, and generating transmission data including emotion data analyzed by an emotion engine; means for transmitting the transmission data to the server; means for receiving the transmission data and storing it in a database; means for using the data stored in the database to use a generative AI model to predict the user's physical condition based on a prompt; means for generating advice for improving the user's health condition based on the predicted physical condition; and means for notifying the terminal of the generated advice. This enables integrated management of a user's personal physiological data, dietary data, diary data, and emotion data, and provides comprehensive health predictions and individual health improvement advice. Furthermore, companies can effectively aggregate employee health data and propose specific data-based improvements to employee benefits.

[1434] A "wearable device" is a device worn by a user that measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via a communication means.

[1435] A "terminal" is a device that manages physiological data collected from a wearable device, as well as dietary data and diary data entered by the user, integrates them to generate transmission data, and transmits this data to a server, including emotional data analyzed by an emotion engine.

[1436] The "emotion engine" is software that analyzes a user's diary data, recognizes their emotional state using text analysis technology, and extracts emotional data.

[1437] The "server" is a system that receives data sent from the device, stores it in a database, predicts physical condition using a generative AI model, generates advice for improving health, and notifies the device.

[1438] "Physiological data" refers to data relating to the user's physical condition, such as heart rate, amount of exercise, and sleep information.

[1439] "Dietary data" refers to data relating to the type, amount, and time of food intake by the user.

[1440] "Diary data" is text data in which a user describes daily events, emotions, physical condition, and the like.

[1441] "Emotion data" is data relating to the user's emotional state that is extracted by the emotion engine by analyzing the diary data.

[1442] A "generative AI model" is an artificial intelligence model that predicts physical condition based on stored data and generates health improvement advice, and includes models with sequential learning capabilities.

[1443] A "prompt sentence" is a sentence input into the generative AI model that specifically describes instructions for predicting physical condition and generating advice.

[1444] A "database" is a storage device that stores data received by the server and is used for subsequent analysis and learning.

[1445] "Advice" is a specific suggestion for improving the user's health based on the health predictions made by the generative AI model.

[1446] This invention relates to a system that combines a wearable device, a terminal, and a server with an emotion engine that recognizes the user's emotions to comprehensively manage a user's physiological data, dietary data, diary data, and emotion data, and provide more accurate health predictions and health improvement advice.

[1447] Hardware and software used

[1448] Wearable device: A device that collects physiological data such as a user's heart rate, exercise amount (e.g., number of steps), and sleep information (e.g., quality and duration of sleep) 24 hours a day.

[1449] Terminal (e.g., smartphone): A device that runs an application that receives data from a wearable device and integrates the food and diary data entered by the user with the emotion data analyzed by the emotion engine.

[1450] Server: A device that receives data sent from the device, stores it in a database, predicts the user's physical condition using a generative AI model, and generates health improvement advice.

[1451] Emotion engine: Software that analyzes the user's diary data and recognizes their emotional state (e.g., joy, sadness, anger, surprise).

[1452] Data collection and integration

[1453] The user puts on a wearable device. The device measures physiological data such as heart rate, exercise volume, and sleep information, and transmits the data to a terminal via Bluetooth or Wi-Fi. The user uses the terminal's application to enter food data (e.g., one apple, two slices of toast, coffee) and diary data (e.g., "Today was a stressful day"). The emotion engine analyzes the diary data and extracts the emotion data, such as "stressful." This data is then integrated into the terminal.

[1454] Data transmission and storage

[1455] The device sends the integrated data to the server, which can be done automatically or manually by the user, and the server stores the received data in a database.

[1456] Health prediction using generative AI models

[1457] The server inputs the data stored in the database into a generative AI model to predict the user's physical condition for the day and the next day. For example, a prompt might be used: "Based on user A's heart rate data, exercise data, sleep data, dietary data, diary data, and emotion data, please predict tomorrow's physical condition and generate specific health improvement advice."

[1458] Generate and notify health improvement advice

[1459] The server generates specific advice to improve the user's health based on the generative AI model. This advice also takes into account emotional data, so it may include, for example, "Today, it would be good to incorporate deep breathing and light exercise to relax." The generated advice is sent to the device, which then notifies the user via push notification or in-app message.

[1460] Specific examples

[1461] For general users

[1462] User A wears a wearable device and collects physiological data such as heart rate, number of steps, and sleep information throughout the day. In the evening, the terminal receives the data from the wearable device, and User A enters a diary entry about the day's meals and physical condition. The emotion engine analyzes the diary data and extracts emotional data such as "I'm stressed today." In the evening, the terminal consolidates this data and sends it to the server. Late at night, the server stores the data and predicts User A's physical condition using a generative AI model. The next morning, based on the prediction results, the server generates specific advice such as "Today, it would be good to incorporate deep breathing and light exercise to relax," and the terminal notifies User A of this advice.

[1463] The system allows both individuals and businesses to more effectively manage and improve their health.

[1464] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1465] Step 1:

[1466] The user wears a wearable device, which collects physiological data such as heart rate, exercise volume (e.g., number of steps), and sleep information (e.g., sleep quality and duration) 24 hours a day. The collected data is temporarily stored in the device's memory.

[1467] Input: User's heart rate, exercise, and sleep information

[1468] Output: Physiological data from a wearable device

[1469] Step 2:

[1470] The wearable device uses Bluetooth or Wi-Fi to transmit the collected physiological data to a terminal, which receives the data through a dedicated application.

[1471] Input: Physiological data from a wearable device

[1472] Output: Physiological data to the device

[1473] Step 3:

[1474] The user uses the device's application to input meal data (date, time, and food eaten) and diary data (diary contents), which are then stored in a database on the device.

[1475] Input: User's meal data, diary data

[1476] Output: Meal data and diary data stored on the device

[1477] Step 4:

[1478] The device application uses an emotion engine to analyze the diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Emotional data is extracted and integrated into the device's database.

[1479] Input: Diary data

[1480] Output: Emotion data

[1481] Step 5:

[1482] The terminal integrates physiological data from the wearable device, dietary data entered by the user, diary data, and emotion data generated by the emotion engine to generate transmission data, which is then sent to the server.

[1483] Input: physiological data, dietary data, diary data, emotional data

[1484] Output: Data sent to the server

[1485] Step 6:

[1486] The server receives the integrated data sent from the devices and stores it in a database, which is used for subsequent analysis and learning.

[1487] Input: Send data

[1488] Output: Data saved to database

[1489] Step 7:

[1490] The server inputs the integrated data stored in the database into the generative AI model to predict the user's physical condition on that day and the next day. The output of the generative AI model is stored in the database as the physical condition prediction result.

[1491] Input: Prompt: "Please predict tomorrow's physical condition based on user A's heart rate data, exercise amount data, sleep data, dietary data, diary data, and emotional data, and generate specific health improvement advice."

[1492] Output: Health prediction results

[1493] Step 8:

[1494] The server generates specific advice for improving health based on the health prediction results of the AI ​​model. This advice is created taking into account emotional data.

[1495] Input: Health prediction result

[1496] Output: Health improvement advice

[1497] Step 9:

[1498] The server generates health improvement advice and sends it to the device. The device notifies the user of this advice via push notifications or in-app messages. The user can then check the advice content on their device.

[1499] Input: Health Improvement Advice

[1500] Output: Notification information to the user

[1501] Through the above steps, a system is realized that manages a user's personal physiological data, dietary data, diary data, and emotional data in an integrated manner, and provides comprehensive health predictions and individual advice on improving health.

[1502] (Application example 2)

[1503] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1504] Conventional health management systems often collect and analyze users' physiological, dietary, and emotional data separately, and systems that manage and analyze this information in an integrated manner are rare. Furthermore, particularly in security services where risk management is crucial, risk prediction based on changes in the user's emotions and physical condition is currently insufficient. This makes it difficult to comprehensively evaluate a user's health status, detect risks early, and take countermeasures. Therefore, there is a need for a new system that can comprehensively analyze a user's physiological and emotional data and provide specific advice for risk management and health improvement, as well as incident response.

[1505] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for collecting physiological data of the user using a wearable device; means for integrating the physiological data collected from the wearable device and the dietary data and diary data entered by the user by a terminal to generate transmission data; means for receiving the transmission data and storing it in a database by the server; means for predicting a physical condition using a generative AI model using the data stored in the database; means for generating advice for improving the health condition based on the physical condition prediction; means for notifying the terminal of the generated advice; means for analyzing the diary data using an emotion analysis engine and extracting emotion data; means for predicting potential risks based on the subject's emotion data and physiological data; and means for generating specific countermeasures and response instructions based on the risk prediction and notifying the terminal. This enables a comprehensive evaluation of the user's health condition, enabling early detection of risks, and the implementation of countermeasures.

[1506] A "wearable device" is an electronic device worn by a user to collect physiological data, such as heart rate, exercise volume, and sleep information, 24 hours a day.

[1507] A "terminal" is an electronic device that receives data from a wearable device, integrates the meal data and diary data entered by the user, and generates transmission data, and includes smartphones and tablets.

[1508] An "emotion analysis engine" is a software component that uses text analysis technology to recognize emotions from text data such as a user's diary data and extract emotion data.

[1509] A "generative AI model" is a machine learning model that uses integrated data as input to predict a user's physical condition and risks, and improves prediction accuracy by successively learning based on new data.

[1510] The "server" is an electronic device that receives data sent from the device, stores it in a database, and processes it using a generative AI model to analyze the data and predict the user's health condition.

[1511] "Database" means an information management system for storing integrated data received by the server, and for enabling efficient search and utilization of required information.

[1512] "Notification means" is a function for notifying the user of advice and risk countermeasure instructions generated by the server, and is done through push notifications or in-app messages.

[1513] "Physiological data" refers to data relating to the user's physical condition, such as the user's heart rate, amount of exercise, and sleep information, and is collected by a wearable device.

[1514] "Emotion data" is data relating to the user's emotional state extracted from text such as diary data by an emotion analysis engine, and includes emotions such as joy, sadness, anger, and surprise.

[1515] "Risk prediction" refers to predictions made by a generative AI model based on emotional and physiological data to estimate the user's health and safety risks.

[1516] The "advice generation means" is a function that generates specific advice and measures to improve the user's health condition based on the results of physical condition prediction and risk prediction.

[1517] This invention is a system for predicting and improving health status by integrating and managing a user's physiological data, dietary data, diary data, and emotional data. This system is composed of a wearable device, a terminal, a server, an emotion analysis engine, and a generative AI model.

[1518] Wearable devices

[1519] Wearable devices collect physiological data such as the user's heart rate, activity, and sleep information 24 hours a day. For example, they measure heart rate, steps, and sleep quality. The collected data is synchronized to a device via Bluetooth or Wi-Fi. Examples of specific devices that use this include smartwatches and fitness trackers.

[1520] Terminal

[1521] The device, which is typically a smartphone or tablet, collects physiological data received from the wearable device and integrates it with dietary and diary data entered by the user. Emotional data analyzed by an emotion analysis engine is also collected. The integrated data is then sent to a server, where the application generates advice and notifies users about risks based on the collected data.

[1522] Sentiment Analysis Engine

[1523] The sentiment analysis engine uses text analysis technology to analyze the user's diary data and recognize the user's emotional state (e.g., joy, sadness, anger, surprise). Specifically, it extracts emotions from text using natural language processing tools such as Google Cloud Natural Language API and IBM Watson NLU. This emotional data is used to predict the user's physical condition and risks.

[1524] server

[1525] The server receives and stores the integrated data sent from the device. The server stores the received data in a database and uses a generative AI model to predict physical condition and risks. Specific examples of AI models used include Google Vertex AI and OpenAI GPT-4. Specific advice and countermeasures are generated based on the predicted risks and health condition.

[1526] Risk Management and Notification

[1527] The server uses a generative AI model to predict potential risks based on the subject's emotional and physiological data. Based on the results, the server generates specific countermeasures and response instructions and notifies the device via push notifications or in-app messages.

[1528] Specific examples

[1529] Example 1: Security guard

[1530] A wearable device worn by security guards collects physiological data such as heart rate and exercise volume. A smartphone app receives this data, and the security guards enter a diary entry about their activities and emotional state for the day. If the emotion analysis engine determines from the diary data that the guard is feeling "high stress," the server receives this data and uses a generative AI model to predict risk. Specific advice, such as "reduce your alert level today and take a moderate break," is generated and sent to the guard's smartphone.

[1531] Prompt Sentence Examples

[1532] Using the user's physiological data, dietary data, diary data, and related emotional data as input, predict risks for today and the next 24 hours, and generate appropriate advice and incident response instructions based on the results.

[1533] This system allows for a comprehensive assessment of the user's health status, allowing for early detection of risks and the implementation of appropriate measures.

[1534] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1535] Step 1: Data collection

[1536] The user wears a wearable device to collect physiological data such as heart rate, exercise volume, and sleep information. This data is synchronized to the user's device via Bluetooth or Wi-Fi. The input physiological data are heart rate, steps, and sleep duration and quality, which are recorded in real time. The output is physiological data stored on the device.

[1537] Step 2: Enter user data

[1538] The user uses a terminal to input dietary data and diary data. Dietary data includes the contents of meals and calorie intake, while diary data records information about the user's emotional state and physical condition for that day. The input is data manually entered by the user, which is received and integrated by the terminal. The output is recorded data on the terminal that reflects the input.

[1539] Step 3: Sentiment Analysis

[1540] The device uses an emotion analysis engine to analyze the text of the diary data and extract emotional data. The input is the text information of the diary data, and the emotional state is extracted through text analysis using natural language processing. Specifically, emotions (joy, sadness, anger, surprise, etc.) are identified using Google Cloud Natural Language API, etc. The output is the extracted emotional data.

[1541] Step 4: Data integration and transmission

[1542] The device integrates the collected physiological data, dietary data, and analyzed emotional data to generate transmission data. The generated transmission data is then sent to the server. The input is physiological data, dietary data, and emotional data, which are processed to integrate them. The output is the integrated transmission data.

[1543] Step 5: Save Data

[1544] The server stores the aggregated data received from the terminals in a database. The input is the aggregated data that is stored in the database. The output is the stored database entry.

[1545] Step 6: Health Prediction

[1546] The server uses a generative AI model with data stored in a database to predict the user's physical condition. The input is integrated data including past physiological data, dietary data, and emotional data, and the physical condition is predicted through machine learning using the generative AI model. Specifically, Google Vertex AI and OpenAI GPT-4 are used to predict future physical condition and risks. The output is the physical condition prediction result.

[1547] Step 7: Risk prediction

[1548] The server predicts potential risks based on the health prediction results. The input is the health prediction results, and a generative AI model is applied to evaluate the presence and level of risk. The output is the risk prediction results.

[1549] Step 8: Advice Generation

[1550] The server generates specific advice and countermeasures for improving health status based on the results of health condition prediction and risk prediction. The input is the risk prediction result, and appropriate advice is generated using a generative AI model. The output is the generated advice.

[1551] Step 9: Notification

[1552] The server notifies the device of the generated advice. The device then communicates the advice to the user using push notifications or in-app messages. The input is the generated advice, which is sent to the device as a notification. The output is a notification message to the user.

[1553] Through this process, the system can comprehensively assess the user's health status, detect risks early, and take necessary measures.

[1554] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1555] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1556] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1557] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1558] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1559] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1560] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1561] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1562] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1563] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1564] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1565] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1566] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1567] 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.

[1568] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1569] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1570] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1571] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1572] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1573] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1574] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1575] The following is further disclosed regarding the above embodiment.

[1576] (Claim 1)

[1577] means for collecting physiological data of a user by a wearable device;

[1578] a means for integrating the physiological data collected from the wearable device and the dietary data and diary data input by the user by a terminal to generate transmission data;

[1579] a means for receiving the transmitted data by a server and storing the data in a database;

[1580] A means for predicting physical condition using a generation AI model using data stored in the database;

[1581] means for generating advice for improving health conditions based on the predicted physical condition;

[1582] means for notifying a terminal of the generated advice;

[1583] A system including:

[1584] (Claim 2)

[1585] 2. The system of claim 1, further comprising means for the generative AI model to improve prediction accuracy through incremental learning.

[1586] (Claim 3)

[1587] 10. The system of claim 1, further comprising means for aggregating health data of company employees and providing company benefits improvements.

[1588] "Example 1"

[1589] (Claim 1)

[1590] means for collecting physiological data of a user by a wearable device;

[1591] a means for integrating the physiological data collected from the wearable device and the dietary data and diary data input by the user by a terminal to generate transmission data;

[1592] a means for receiving the transmitted data by a server and storing the data in a database;

[1593] A means for predicting a physical condition using a generation AI model based on the data stored in the database and generating advice for improving the health condition;

[1594] means for notifying a terminal of the generated advice;

[1595] A means for the server to improve prediction accuracy by sequentially training the generative AI model based on new data, and

[1596] A means for the terminal to automatically or manually transmit user data to the server;

[1597] A system including:

[1598] (Claim 2)

[1599] The system of claim 1, further comprising means for the generative AI model to improve prediction accuracy through incremental learning and notify the user of the generated advice via push notification or in-app message.

[1600] (Claim 3)

[1601] 10. The system of claim 1, further comprising means for aggregating health data of employees of a company and providing improvements to company benefits.

[1602] "Application Example 1"

[1603] (Claim 1)

[1604] means for collecting physiological data of a user by a wearable device;

[1605] a means for integrating the physiological data collected from the wearable device and the dietary data and diary data input by the user by a terminal to generate transmission data;

[1606] a means for receiving the transmitted data by a server and storing the data in a database;

[1607] A means for predicting physical condition using a generation AI model using data stored in the database;

[1608] means for generating advice for improving health conditions based on the predicted physical condition;

[1609] means for notifying a terminal of the generated advice;

[1610] A means for collecting physiological data, dietary data, and work records of employees at a logistics center and providing employee health predictions and work performance improvement advice based on the generated AI model;

[1611] A system including:

[1612] (Claim 2)

[1613] 2. The system of claim 1, further comprising means for the generative AI model to improve prediction accuracy through incremental learning.

[1614] (Claim 3)

[1615] 10. The system of claim 1, further comprising means for aggregating health data of company employees and providing company benefits improvements.

[1616] "Example 2: Combining Emotion Engines"

[1617] (Claim 1)

[1618] means for collecting physiological data of a user by a wearable device;

[1619] a means for integrating the physiological data collected from the wearable device and the dietary data and diary data input by the user by a terminal, and generating transmission data including emotion data analyzed by an emotion engine;

[1620] means for transmitting the transmission data to a server;

[1621] a means for receiving the transmitted data by a server and storing the data in a database;

[1622] A means for predicting a physical condition based on a prompt sentence by using a generative AI model using the data stored in the database;

[1623] means for generating advice for improving health conditions based on the predicted physical condition;

[1624] means for notifying a terminal of the generated advice;

[1625] A system including:

[1626] (Claim 2)

[1627] 2. The system of claim 1, further comprising means for the generative AI model to improve prediction accuracy through incremental learning.

[1628] (Claim 3)

[1629] 10. The system of claim 1, further comprising means for aggregating health data of company employees and providing company benefits improvements.

[1630] "Application example 2 when combining emotion engines"

[1631] (Claim 1)

[1632] means for collecting physiological data of a user by a wearable device;

[1633] a means for integrating physiological data collected by a terminal from the wearable device and dietary data and diary data input by a user to generate transmission data;

[1634] a means for receiving the transmitted data by a server and storing the data in a database;

[1635] A means for predicting physical condition using a generation AI model using data stored in the database;

[1636] means for generating advice for improving health conditions based on the predicted physical condition;

[1637] means for notifying a terminal of the generated advice;

[1638] A means for analyzing diary data using an emotion analysis engine and extracting emotion data;

[1639] A means of predicting potential risks based on the subject's emotional and physiological data;

[1640] means for generating specific countermeasures and response instructions based on the risk prediction and notifying the terminal;

[1641] A system including:

[1642] (Claim 2)

[1643] 2. The system of claim 1, further comprising means for the generative AI model to improve prediction accuracy through incremental learning.

[1644] (Claim 3)

[1645] 10. The system of claim 1, further comprising means for aggregating health data of company employees and providing company benefits improvements. [Explanation of symbols]

[1646] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting physiological data of a user by a wearable device; a means for integrating the physiological data collected from the wearable device and the dietary data and diary data input by the user by a terminal to generate transmission data; a means for receiving the transmitted data by a server and storing the data in a database; A means for predicting physical condition using a generation AI model using data stored in the database; means for generating advice for improving health conditions based on the predicted physical condition; means for notifying a terminal of the generated advice; A system including:

2. The system of claim 1 , further comprising means for the generative AI model to improve prediction accuracy through incremental learning.

3. The system of claim 1 further comprising means for aggregating health data of company employees and providing company benefits improvements.

Images