System

Abstract

A system is provided.SOLUTION: A system includes a means for collecting lifestyle habit data of a user, a means for transmitting the collected lifestyle habit data to a server, a means for analyzing the collected lifestyle habit data in the server to detect a sign of a pre-disease, a means for generating an individually optimized preventive measure based on the sign of the pre-disease, a means for notifying the user of the generated preventive measure, a means for collecting feedback data from the user, and a means for updating a machine learning model based on the collected feedback data.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] Busy modern people tend to neglect their own health management, increasing the risk of lifestyle-related and stress-related diseases. Furthermore, many people find it difficult to take appropriate preventive measures before illness sets in, creating a need for specific, individually tailored information to improve their lifestyles. However, most current health management services only provide uniform information and are unable to provide effective preventive measures tailored to individual users. Therefore, there is a need for a system that can suggest precise and effective preventive measures in real time based on each user's individual lifestyle habits and feedback, and support lifestyle improvements. [Means for solving the problem]

[0005] In order to solve the above problems, the present invention provides a system including the following means.

[0006] A means of collecting lifestyle data of users;

[0007] A means for transmitting the collected lifestyle habit data to a server;

[0008] A means for analyzing collected lifestyle habit data and detecting signs of pre-disease in the server;

[0009] A means for generating individually optimized preventive measures based on pre-disease signs;

[0010] a means for notifying the user of the generated preventative measures;

[0011] a means of collecting user feedback data;

[0012] means for updating the machine learning model based on the collected feedback data;

[0013] The server further includes a means for validating the collected lifestyle habit data and detecting and correcting abnormal values ​​and missing data;

[0014] The system also includes a means for using natural language generation technology to generate preventive measures in a natural language that is easy for the user to understand.

[0015] This allows users to receive personalized, optimal preventive measures in real time based on their lifestyle habits and activity logs, enabling them to manage their health more effectively and improve their lifestyle.

[0016] "Lifestyle data" refers to information related to a user's daily activities and health, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary habits.

[0017] "Pre-disease signs" are abnormal patterns or symptoms that are detected before the disease manifests, and are extracted from lifestyle data.

[0018] A "server" is a computer system that collects, stores, analyzes, and presents data over a network.

[0019] "Preventive measures" are specific behavioral or lifestyle changes suggested to prevent the user's health from deteriorating.

[0020] "Feedback data" refers to information such as user reactions, evaluations, and opinions regarding proposed preventive measures.

[0021] A "machine learning model" is an algorithm that learns using large amounts of data and makes predictions and classifications for unknown data.

[0022] "Natural language generation technology" is a technology that allows machines to generate human language in order to provide information to users in a format that is easy to understand.

[0023] "Validation" is the process of checking whether collected data is accurate and correcting or eliminating inaccurate data.

[0024] "Push notification" is a technology that sends notifications from a server to a device in real time to convey specific information to the user. [Brief explanation of the drawings]

[0025] [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

[0026] 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.

[0027] First, the terms used in the following description will be explained.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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."

[0033] [First embodiment]

[0034] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0035] 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.

[0036] 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).

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0042] 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.

[0043] 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.

[0044] 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.

[0045] 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."

[0046] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of illness, and proposes individually optimized preventative measures. This system realizes effective health management by incorporating feedback into the data. Specific program processing is explained below in natural language.

[0047] Data collection and transmission

[0048] Terminal

[0049] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0050] Receiving and storing data

[0051] server

[0052] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[0053] Detecting signs of pre-disease

[0054] server

[0055] Machine learning models are applied to the stored data to detect abnormal patterns in step counts, heart rate, etc. A number of health indicators are calculated to detect signs of illness, such as a significant decrease in recent step counts compared to historical averages or an increase in heart rate variability.

[0056] Preventive measures generation and notification

[0057] server

[0058] Based on the detected signs of illness, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice such as "Your exercise volume has decreased recently. Try walking 30 minutes every day" is generated.

[0059] Terminal

[0060] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0061] Gathering feedback and updating the model

[0062] User

[0063] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0064] server

[0065] It receives and analyzes user feedback, which is then reflected in the next preventative measures suggested to the machine learning model, allowing the system to continually adapt its suggestions to the user's behavior and habits.

[0066] Specific examples

[0067] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. The server generates a preventive measure, suggesting, "Your physical activity has decreased, so try walking for 30 minutes on the weekend." and notifies the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server uses that feedback to update the model and provide a more optimized preventive measure next time.

[0068] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and supports continuous health management.

[0069] The processing flow will be explained below.

[0070] Step 1:

[0071] Device:

[0072] Smartphones and wearable devices use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications provide users with the option to manually input dietary information.

[0073] Step 2:

[0074] Device:

[0075] The collected lifestyle data is sent to the server at regular intervals (e.g., every hour or every day). If a network connection is unavailable, the data is sent in batches the next time a connection is made.

[0076] Step 3:

[0077] server:

[0078] It receives JSON format data sent from the device, records the received data in a log, and saves the data in a database for subsequent processing.

[0079] Step 4:

[0080] server:

[0081] Data validation is performed to detect missing data and outliers. Data correction is performed as necessary to ensure data quality. The corrected data is converted into a format for analysis.

[0082] Step 5:

[0083] server:

[0084] It uses machine learning models to analyze lifestyle data and detect signs of pre-disease, including abnormal patterns such as a sudden decrease in step count or increased heart rate variability.

[0085] Step 6:

[0086] server:

[0087] Based on the detected signs of illness, the system generates personalized and optimized preventive measures, and uses natural language generation (NLG) technology to create messages in a format that is easy for users to understand.

[0088] Step 7:

[0089] server:

[0090] The generated preventive action message is sent to the user's device in the form of a push notification, along with metadata (such as the importance of the preventive action and when it should be taken).

[0091] Step 8:

[0092] Device:

[0093] The received message will be displayed in the user interface, and the user will be prompted to review and take action on preventative measures through the application.

[0094] Step 9:

[0095] User:

[0096] Enter your feedback on the suggested preventative measures. The application asks a simple question (e.g., "Did this suggestion help you?") and collects your response.

[0097] Step 10:

[0098] Device:

[0099] User feedback data is sent to the server, including the usefulness of the proposal and the difficulty of its implementation.

[0100] Step 11:

[0101] server:

[0102] The received feedback data is analyzed and the machine learning model is updated, which makes the next preventative measures recommendations more accurate.

[0103] Step 12:

[0104] server:

[0105] It will continue to operate updated machine learning models and pre-disease sign detection algorithms, which will continuously monitor user data and provide individually optimized preventative measures in a timely manner.

[0106] Example 1

[0107] 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."

[0108] Conventional health management systems have struggled to effectively collect and analyze a user's lifestyle data and propose individually optimized preventive measures. Furthermore, it has been difficult to effectively collect feedback on the proposed preventive measures and reflect it in the system, resulting in insufficient continuous health management. The present invention aims to solve these problems by providing a system that achieves effective health management by performing detailed analysis and proposing preventive measures based on a user's lifestyle data and updating the model based on the feedback.

[0109] 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.

[0110] In this invention, the server includes a means for collecting data related to the user's health, a means for transmitting the collected health data to the communication device, and a means for analyzing the collected health data and detecting signs of pre-disease in the communication device. This makes it possible to effectively collect and analyze the user's lifestyle data, generate individually optimized preventive measures, and update the machine learning model based on the feedback.

[0111] "User" means an individual who utilizes the system to manage their health status and provide feedback.

[0112] "Health data" refers to information about a user's health and lifestyle, such as the number of steps taken, heart rate, sleep patterns, and dietary information.

[0113] "Means of collection" refers to the functions and processes that collect user health data using devices such as smartphones and wearable devices.

[0114] "Communication device" refers to a server or computer system that processes, stores, analyzes, and notifies data received from a user's device.

[0115] "Means of analysis" refers to the functions and processes that use machine learning models and statistical analysis techniques to evaluate collected data and detect signs of pre-disease.

[0116] "Pre-illness signs" are early symptoms or signs of abnormalities that appear before the user's health condition deteriorates.

[0117] "Individually optimized preventive measures" refer to preventive measures and advice that are optimal for each user, proposed based on the user's personal health data and analysis results.

[0118] "Generation means" refers to the function or process that uses natural language generation techniques or algorithms to generate preventative measures to notify users.

[0119] "Means of notification" refers to the function or process that sends the generated preventative measures to the user's device in the form of a push notification or alert.

[0120] "Feedback data" refers to information entered into the system by users regarding their impressions of proposed preventive measures and the results of their implementation.

[0121] "Means for updating machine learning models" refers to the functions and processes that optimize and improve the prevention generation algorithms and models based on feedback data collected from users.

[0122] MODE FOR CARRYING OUT THE INVENTION

[0123] This invention is a system that collects and analyzes lifestyle data from users to detect pre-disease symptoms and proposes individually optimized preventive measures. By incorporating feedback into the system, this system achieves effective health management.

[0124] Data collection and transmission

[0125] Device:

[0126] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0127] As a specific example, if a user uses a smartphone and a wearable device, the device records data on the number of steps taken and heart rate in real time, and at night the smartphone automatically sends the data for the day to a server.

[0128] Receiving and storing data

[0129] server:

[0130] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected.

[0131] As a concrete example, we use a Python script on the server to format the data, run an outlier detection algorithm on it, and then store the formatted data in a database.

[0132] Detecting signs of pre-disease

[0133] server:

[0134] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to detect signs of illness.

[0135] As a concrete example, the server analyzes step count data from the past month using a machine learning library (e.g., scikit-learn) and detects that the average number of steps has decreased significantly in the last week.

[0136] Preventive measures generation and notification

[0137] server:

[0138] Based on the detected pre-disease signs, the system generates optimal preventive measures for each individual user, using natural language generation technology to create messages in a format that is easy for users to understand.

[0139] As a concrete example, a generative AI model is used to generate a message such as, "Your exercise volume has decreased recently. Try walking 30 minutes every day."

[0140] Device:

[0141] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0142] Gathering feedback and updating the model

[0143] User:

[0144] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0145] server:

[0146] It receives and analyzes user feedback, which is then used to update the machine learning model to reflect the feedback in the next preventative action recommendations.

[0147] As a specific example, when the server receives feedback data, it evaluates the feedback with analytical algorithms and adjusts the weights and parameters of the model.

[0148] Prompt Sentence Examples

[0149] "Your daily step count has decreased significantly compared to average. To increase your exercise, try walking 30 minutes every day. Even walking three times a week will be effective, so try to continue within your limits."

[0150] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle data and supports continuous health management.

[0151] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0152] Specific processing steps of the program

[0153] Step 1:

[0154] The device collects health data (such as the number of steps taken, heart rate, sleep patterns, and dietary information) from the user using a dedicated application or wearable device. Specifically, the device uses sensors to record data in real time, and the smartphone application allows the user to manually enter dietary information.

[0155] Input: User's health data

[0156] Output: A set of collected health data

[0157] Step 2:

[0158] The device sends the collected health data to a server at regular intervals via an internet connection. The specific data transmission operation involves the device automatically uploading data to the server at night or at a set time.

[0159] Input: A set of collected health data

[0160] Output: Data sent to the server

[0161] Step 3:

[0162] The server receives the health data sent from the device and stores it in a dedicated database. The specific operations of receiving and storing data involve the server first validating the data (e.g., detecting missing data and outliers), correcting it into an appropriate format, and then storing it in the database.

[0163] Input: Submitted health data

[0164] Output: Data stored in the database

[0165] Step 4:

[0166] The server applies machine learning models to the stored health data to detect signs of illness. This process involves using algorithms to calculate health indicators (e.g., steps taken, heart rate variability) and identify abnormal patterns. Specific operations include running analysis scripts using Python libraries.

[0167] Input: Data stored in a database

[0168] Output: Detected signs of pre-disease

[0169] Step 5:

[0170] The server generates individually optimized preventive measures based on the detected pre-disease signs. This generation utilizes a generative AI model and natural language generation technology. Specifically, the generative AI model generates a message that is easy for the user to understand.

[0171] Input: Detected signs of illness

[0172] Output: Generated preventative action message

[0173] Step 6:

[0174] The device notifies the user of the preventive measures message sent from the server. This can be done via push notification or in-app messaging. Specifically, the device receives the notification and displays details when the user opens the app.

[0175] Input: Generated precaution message

[0176] Output: Preventive measures communicated to the user

[0177] Step 7:

[0178] The user inputs feedback on the proposed preventive measures through the application. Specifically, a feedback form is displayed in the application for inputting impressions and effects.

[0179] Input: User feedback on preventative measures

[0180] Output: Collected feedback data

[0181] Step 8:

[0182] The server receives and analyzes feedback data from users. The specific operation of the feedback analysis is to evaluate their impressions and implementation results and update the machine learning model to reflect these in the next proposal.

[0183] Input: Collected feedback data

[0184] Output: Updated machine learning model

[0185] In this way, by explaining in detail the specific input, data processing, data calculation, and output that take place at each step, the processing flow of the entire system can be clearly understood.

[0186] (Application example 1)

[0187] 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."

[0188] Conventional health management systems are limited to detecting pre-disease signs and proposing preventive measures based solely on the user's lifestyle data, and do not achieve individual optimization that fully considers individual lifestyle patterns and economic activities (e.g., dietary content and use of fitness services).Therefore, there is a need for highly accurate detection of pre-disease signs and proposing preventive measures by including activity data that is closely related to the user's health condition.

[0189] 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.

[0190] In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to the server, means for collecting electronic payment data, means for analyzing the collected lifestyle habit data and electronic payment data in the server to detect pre-disease signs, means for generating individually optimized preventive measures based on the pre-disease signs, means for generating the preventive measures in natural language that is easy for the user to understand using a generative AI model and prompt sentences, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data. This enables highly accurate detection of pre-disease signs and provision of individually optimized preventive measures that take into account both the user's lifestyle habit data and electronic payment data.

[0191] "User" means an individual who uses the health care system.

[0192] "Lifestyle data" refers to data related to a user's daily health and behavior, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[0193] A "server" is a computer system that stores and analyzes collected data.

[0194] "Electronic payment data" refers to transaction data related to electronic payments made by users, and specifically includes health food purchase history and fitness service usage history.

[0195] "Pre-disease signs" are data patterns or indicators that indicate a user may be currently healthy but may develop illness in the future.

[0196] "Individually optimized preventive measures" are specific suggestions and measures for optimal health management and disease prevention for each individual user, based on the user's lifestyle and electronic payment data.

[0197] A "generative AI model" is an artificial intelligence model that uses natural language generation technology to automatically generate messages for users.

[0198] A "prompt sentence" is an input sentence that instructs the generative AI model to generate a message.

[0199] "Feedback data" refers to information provided by users about their impressions of preventive measures and the results of their implementation.

[0200] A "machine learning model" is an algorithm or data model used to improve the accuracy of analysis and preventative measures suggested based on collected data and feedback.

[0201] The present invention is a system that collects a user's lifestyle data and electronic payment data, analyzes them to detect signs of illness, and proposes individually optimized preventive measures. The following hardware and software are used to implement the present invention.

[0202] Hardware

[0203] Smartphone: Collects data on the user's daily habits (e.g., steps, heart rate, sleep patterns).

[0204] Server: Stores and analyzes collected data.

[0205] software

[0206] Requests library: Communicate with the API to obtain transaction data and feedback.

[0207] Pandas library: Used to read and manage data.

[0208] Scikit-learn library: Used for data normalization and outlier detection (Isolation Forest algorithm).

[0209] Overview of data processing and calculation

[0210] 1. Data collection (device side): Applications installed on smartphones collect lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Transaction data related to electronic payments made by users is also collected.

[0211] 2. Data transmission (from terminal to server): Collected lifestyle data and electronic payment data are sent to the server at regular intervals.

[0212] 3. Data storage and validation (server side): The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data.

[0213] 4. Pre-disease sign detection (server side): Using the validated data, the Isolation Forest algorithm is applied to detect abnormal patterns. Pre-disease signs are found based on step counts, heart rate, and transaction data.

[0214] 5. Generate personalized preventive measures (server-side): Based on the detected signs of illness, preventive measures are generated using generative AI models and prompts. The generated preventive measures are written for the user in natural language.

[0215] 6. Notification (from server to device): The generated preventive measures are notified to the user via push notifications on the smartphone.

[0216] 7. Feedback collection (terminal side): Users enter their thoughts on the proposed preventive measures and the results of their implementation as feedback through the application.

[0217] 8. Feedback analysis and model update (server side): Based on the collected feedback data, the machine learning model is updated and reflected in future preventive measures.

[0218] Specific examples

[0219] When a user uses a smartphone and a fitness tracker, the user's step count data and electronic payment data (e.g., food purchase history or fitness center usage history) are collected and sent to a server. The server compares this data with past data and detects a decrease in exercise volume. As a result, a preventive measure is generated, such as "Your exercise volume has decreased recently. Try walking every day," and a notification is sent to the user's device. After the user has completed the exercise, the user provides feedback, saying, "This amount of exercise was just right," and the server updates the model based on that feedback.

[0220] Prompt Sentence Examples

[0221] An example of a prompt sentence to be input to the generative AI model is, "Create an application that collects user transaction data, detects signs of pre-illness based on health indicators (number of steps, heart rate, sleep patterns), and suggests optimal preventive measures. Use the Isolation Forest algorithm to detect anomalies, and use natural language generation technology to generate a message that is easy for the user to understand. For example, a message such as, 'Your exercise volume has decreased recently. Try walking 30 minutes every day.'"

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] Data collection (terminal side)

[0225] An application installed on a smartphone uses sensors to collect lifestyle data (number of steps, heart rate, sleep patterns), and electronic payment data. This input data is then periodically organized and saved within the app.

[0226] Step 2:

[0227] Data transmission (from device to server)

[0228] The application periodically transmits the collected lifestyle and electronic payment data to a server. The transmission is via an internet connection and the data is encrypted, ensuring data security. The transmitted data also includes metadata such as collection timestamps and device identifiers.

[0229] Step 3:

[0230] Data storage and validation (server side)

[0231] The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data. This validation uses the Pandas library to shape and clean the data. For example, an anomaly detection algorithm using standard deviation is applied to detect outliers.

[0232] Step 4:

[0233] Detecting signs of illness (server side)

[0234] The server analyzes the validated data and uses the Isolation Forest algorithm to detect signs of pre-disease. Past lifestyle habits and electronic payment data are used as input data. The output is a list of data points containing abnormal patterns. The Scikit-learn library is used for the analysis.

[0235] Step 5:

[0236] Individually optimized preventive measures generation (server side)

[0237] The server generates preventive measures based on the detected signs of illness using a generative AI model and prompts. Natural language generation technology is used to generate messages in a format that is easy for users to understand. The generated messages are in natural language rather than JSON format, making them easy for users to understand.

[0238] Step 6:

[0239] Notification (from server to device)

[0240] The generated preventive measures are notified to the user via the smartphone's push notification function. The server selects notification recipients based on the user's identification information and sends the notification via API. The notification includes specific actions for the preventive measures (e.g., a suggestion to walk daily).

[0241] Step 7:

[0242] Feedback collection (device side)

[0243] Users can enter feedback on the proposed preventive measures through the application. The feedback includes the results of implementing the preventive measures and their impressions. This feedback data is temporarily stored on the device and sent to the server the next time data is transmitted.

[0244] Step 8:

[0245] Feedback analysis and model updates (server side)

[0246] The server analyzes the received feedback data and updates the machine learning model. Past feedback data is also used in the analysis, and adjustments are made to improve the accuracy of the model. For example, the hyperparameters of the anomaly detection algorithm are readjusted based on the feedback results. This allows for more personalized optimization of preventive measures proposed from the next time onwards.

[0247] 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.

[0248] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect pre-disease signs, and proposes individually optimized preventative measures. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it achieves more precise and effective health management. This system continues to achieve effective health management by incorporating user feedback. The specific program processing is explained below in natural language.

[0249] Data collection and transmission

[0250] Device:

[0251] The user's smartphone or wearable device uses sensors to collect daily lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0252] Receiving and storing data

[0253] server:

[0254] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[0255] Pre-disease sign detection and emotion analysis

[0256] server:

[0257] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. Numerous health indicators are calculated to identify signs of illness. An emotion engine also analyzes user feedback and other emotional data (e.g., text messages and tone of voice) to recognize the user's current emotional state.

[0258] Preventive measures generation and notification

[0259] server:

[0260] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice is generated such as, "You've been getting less exercise lately. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0261] Device:

[0262] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0263] Gathering feedback and updating the model

[0264] User:

[0265] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0266] Device:

[0267] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[0268] server:

[0269] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[0270] Specific examples

[0271] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. Furthermore, the emotion engine analyzes the user's text messages for signs of stress. The server generates a preventive measure, suggesting, "Since your physical activity has decreased, try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine." The server then sends a notification to the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server updates the model based on that feedback and emotion data, and provides a more optimized preventive measure next time.

[0272] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and emotional state, and supports continuous health management.

[0273] The processing flow will be explained below.

[0274] Step 1:

[0275] Device:

[0276] The user's smartphone or wearable device uses sensors to collect lifestyle data such as steps taken, heart rate, and sleep patterns. The user can manually enter dietary information through a smartphone application. The device records the data at regular intervals.

[0277] Step 2:

[0278] Device:

[0279] The device sends the lifestyle data collected to the server at preset intervals. If the network connection is unstable, the data will be sent in batches the next time the device connects.

[0280] Step 3:

[0281] server:

[0282] The server receives the data sent from the terminal and stores it in a database. The received data is validated to detect missing data and abnormal values. This data is then corrected.

[0283] Step 4:

[0284] server:

[0285] Based on the saved data, a machine learning model is applied to analyze lifestyle data, using health indicators such as the number of steps taken, heart rate, and sleep patterns, and comparing them with past data to detect signs of illness.

[0286] Step 5:

[0287] server:

[0288] Once a pre-illness sign is detected, the emotion engine analyzes the user's emotional data, which is collected from feedback, text messages, voice data, etc. The emotion engine determines the user's current emotional state.

[0289] Step 6:

[0290] server:

[0291] It generates individually optimized preventive measures based on pre-disease signs and emotional state. It uses natural language generation technology to create messages in a format that is easy for users to understand. For example, it generates specific advice such as, "You've been getting less exercise lately. Try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine."

[0292] Step 7:

[0293] server:

[0294] The generated preventive action message is sent to the user's device as a push notification, along with metadata including the timing and severity of the preventive action.

[0295] Step 8:

[0296] Device:

[0297] The device will display the preventive measures message it receives on the user interface (UI). The user is prompted to acknowledge the notification and take action. The notification is displayed in the form of an alert, so users will not miss it.

[0298] Step 9:

[0299] User:

[0300] Users can then implement the suggested preventative measures and provide feedback about their results through the application, with options such as "helpful" or "difficult," or they can enter detailed thoughts in text format.

[0301] Step 10:

[0302] Device:

[0303] The device sends user feedback data, including the user's emotional state, to the server, which records how the user felt.

[0304] Step 11:

[0305] server:

[0306] The server analyzes the received feedback data and sentiment data, which are then used to update the machine learning model and sentiment engine, allowing the system to further optimize its next preventative action suggestions.

[0307] Step 12:

[0308] server:

[0309] Using updated machine learning models and an emotion engine, it continuously monitors users' lifestyle data and provides individually optimized preventative measures at the appropriate time.

[0310] In this way, the system analyzes the user's lifestyle data and emotional state in real time and continuously suggests optimized preventive measures, supporting effective health management.

[0311] Example 2

[0312] 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."

[0313] In recent years, the importance of health management has increased, with particular attention being paid to early detection and prevention of pre-disease. However, conventional systems have insufficient collection and analysis of users' lifestyle data, making it difficult to provide personalized preventative measures. Furthermore, health management often fails to take into account the user's emotional state, making it difficult to effectively incorporate user feedback. As a result, the preventative measures provided by the system do not match the user's actual needs, resulting in problems with insufficient continuous health management.

[0314] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to a remote server, means for analyzing the collected lifestyle habit data in the remote server to detect signs of abnormal health, means for generating individually optimized preventive measures based on the signs of abnormal health, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data and emotion analysis data. This makes it possible to provide individually optimized preventive measures that comprehensively consider the user's lifestyle habits and emotional state.

[0315] "User" refers to an individual who uses the health care system.

[0316] "Lifestyle data" refers to information about a user's daily activities and conditions, including the number of steps taken, heart rate, sleep patterns, and dietary information.

[0317] "Collection means" refers to the method of collecting user lifestyle data using sensors, applications, etc.

[0318] "Remote Server" refers to a computer system over a network that receives, stores, and analyzes collected data.

[0319] "Validation" refers to the process of checking the accuracy and completeness of collected data.

[0320] "Correction" refers to the process of correcting data that contains deficiencies or anomalies and preparing it in a format that can be analyzed.

[0321] "Signs of abnormal health" refers to indicators or patterns that are recognized as potential health problems based on a user's lifestyle data.

[0322] "Analysis tools" refers to algorithms and software tools used to detect signs of health abnormalities based on collected lifestyle data.

[0323] "Preventive measures" refer to specific actions or measures suggested to users to improve symptoms of an abnormal health condition.

[0324] "Generation means" refers to the method of creating preventive measures based on collected data and analysis results.

[0325] "Notification Method" refers to the communication method used to inform users of the created preventative measures, including push notifications, emails, and SMS.

[0326] "Feedback Data" refers to information provided by users, including their impressions of and results of implementing preventive measures.

[0327] "Emotional Analysis Data" refers to information representing a user's emotional state extracted from user feedback and other data.

[0328] A "machine learning model" refers to an algorithm that learns from collected data to optimize preventive measures and detect new anomalies.

[0329] This invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of health abnormalities, and proposes individually optimized preventative measures. Furthermore, by combining this with emotion analysis, more precise and effective health management is realized. This system incorporates user feedback to continuously provide effective health management.

[0330] The terminal collects lifestyle data using the user's smartphone or wearable device. The devices used include, for example, smartphones and wearable devices. Users can also manually enter dietary information through a smartphone application. This data is automatically sent to a server at regular intervals. Specifically, for example, a smartphone and fitness tracker are used to send data to the server every night at midnight.

[0331] The server receives the data sent from the device and stores it in a dedicated database (e.g., Amazon RDS, DynamoDB). The data is first validated, and if outliers or missing data are detected, they are corrected using a correction algorithm. For example, if there is an outlier in the heart rate data, the data before and after is referenced and corrected using the average value.

[0332] The server applies machine learning models (e.g., TENSORFLOW®, scikit-learn) using programming languages ​​such as Python to the stored data to detect signs of abnormal health. It analyzes whether there are any abnormal patterns based on specific health indicators. It also uses a sentiment analysis engine (e.g., IBM Watson®'s Natural Language Understanding API) to analyze the emotional state from user feedback and text messages. For example, if a user's text messages contain many of the words "tired" and "stressed," it will recognize this as a state of stress.

[0333] The server generates personalized preventive measures based on the detected health symptoms and emotional state. It uses natural language generation technology (e.g., OpenAI® GPT-3®) to create a message that is easy for the user to understand. For example, it generates a message that reads, "Your exercise volume has decreased recently. Try walking 30 minutes a day. Also, try practicing deep breathing to relax."

[0334] The generated message is sent to the user's device as a push notification. The user is expected to check the notification through the application and take action. For example, the notification may say, "Your physical activity is decreasing. See details."

[0335] The user can provide feedback on the proposed preventive measures through the application, for example, by inputting their thoughts such as, "This amount of exercise was just right." The device then sends this feedback data to the server.

[0336] The server receives and analyzes feedback and emotion data from users. The machine learning model is updated based on the feedback and emotion data, allowing future preventive measures to be more optimized for each user.

[0337] Prompt Sentence Examples

[0338] "Analyze step count data collected from users' fitness trackers to detect abnormal patterns. Also, determine users' emotional state from their text messages and generate appropriate health precautions."

[0339] A system configured in this way makes it possible to provide individually optimized preventive measures that comprehensively take into account the user's lifestyle habits and emotional state.

[0340] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0341] Step 1:

[0342] Data collection and transmission

[0343] Device:

[0344] A user's smartphone or wearable device collects lifestyle data such as step count, heart rate, and sleep patterns. This data collection is performed using sensors built into the smartphone or the wearable device. The user can also manually input dietary information using a smartphone application. The collected data is automatically sent to a remote server at regular intervals or at the end of the day. Specific input data include step count data, heart rate data, sleep data, and dietary information, and these are output data to the server.

[0345] Step 2:

[0346] Receiving and storing data

[0347] server:

[0348] The data sent from the device is received and stored in a database such as Amazon RDS or DynamoDB. At this time, the data is validated, and if missing data or outliers are detected, they are corrected using an automatic correction algorithm. For example, if the heart rate data contains an outlier, it is corrected using the average value of the heart rate data before and after. The input data is the collected lifestyle habit data, and the output data is the normalized data that has been validated and corrected.

[0349] Step 3:

[0350] Pre-disease sign detection and emotion analysis

[0351] server:

[0352] A machine learning model using Python (e.g., TensorFlow, scikit-learn) is applied to the saved normalized data. This detects abnormal patterns from step count data, heart rate data, etc. In addition, a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) is used to determine the user's emotional state from their text messages and feedback. The specific input data are the normalized lifestyle data and text messages, and the output data are the detected abnormal patterns and emotional state.

[0353] Step 4:

[0354] Preventive measures generation and notification

[0355] server:

[0356] Based on the detected abnormal patterns and emotional state, the system generates individually optimized preventive measures. Natural language generation technology (e.g., OpenAI GPT-3) is used to create messages that are easy for users to understand. The specific input data is the abnormal patterns and emotional state, and the output data is the preventive measure message. For example, a message may be generated that reads, "Your exercise volume has decreased recently. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0357] Device:

[0358] The generated preventive action message is sent to the user's device as a push notification. The user is expected to acknowledge the notification and take action through the application. The input data is the preventive action message, and the output data is the user's action or confirmation.

[0359] Step 5:

[0360] Gathering feedback and updating the model

[0361] User:

[0362] Feedback regarding the proposed preventive measures and the results of their implementation is entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided. The input data is the feedback information, and the output data is the feedback content.

[0363] Device:

[0364] The user's emotional state is also monitored in real time and sent to the server as emotional data as appropriate. A sudden increase in heart rate, for example, is sent as emotional analysis data. The input data is emotional state data such as heart rate data, and the output data is the sent emotional analysis data.

[0365] server:

[0366] It receives and analyzes feedback and sentiment data from users, which updates the machine learning model and further optimizes preventive measures for future visits. The input data is the feedback and sentiment data, and the output data is the updated machine learning model. For example, the model is updated weekly, and new suggestions are generated.

[0367] (Application example 2)

[0368] 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."

[0369] Conventional health management systems mainly monitor health status and suggest preventative measures based on users' lifestyle data, but do not provide precise health management that takes emotional states into account. Furthermore, particularly in security services, there is a lack of mechanisms for monitoring the health status of security guards in real time, who work long hours and in high-stress environments, and providing appropriate rest and support. This can lead to accumulated stress and overwork among security guards, potentially reducing work efficiency and safety.

[0370] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0371] In this invention, the server includes means for analyzing the user's emotional state, means for analyzing collected lifestyle habit data to detect signs of illness, means for combining the emotional state and lifestyle habit data to generate individually optimized preventive measures, and means for displaying the analysis results and preventive measures using a visual display device worn by the user. This makes it possible to monitor the user's health and emotional state in real time and provide appropriate rest and support.

[0372] "Lifestyle data" refers to data related to the user's daily activities, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[0373] "Server" refers to a computer system for receiving, storing, and analyzing collected data.

[0374] "Pre-illness signs" refer to the precursors and symptoms of illness, and are data patterns that indicate changes or abnormalities in health status.

[0375] "Preventive measures" are specific actions and initiatives suggested based on signs of illness, and are measures to maintain health.

[0376] "Feedback data" refers to information provided by users regarding their impressions of proposed preventive measures and the results of their implementation.

[0377] A "machine learning model" is an algorithmic model used to improve the accuracy of data analysis and predictions, learning from data and using it for analysis.

[0378] The "emotion analysis function" is a technology for analyzing a user's emotional state, recognizing emotions based on data such as text messages, tone of voice, and facial expressions.

[0379] A "visual display device" is a device worn by a user that has the function of visually displaying information, and includes, for example, a head-mounted display (HMD).

[0380] "Natural language generation technology" is a technology that allows a computer to generate sentences in natural language to create preventive measures and notifications in a form that is easy for users to understand.

[0381] The present invention is a system for managing health by collecting lifestyle habit data of a user and taking into consideration the user's emotional state. An embodiment of this system will be described in detail below.

[0382] Data collection and transmission

[0383] 1. Device:

[0384] The smartphones and wearable devices that users use daily use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications also allow users to manually input dietary information.

[0385] The collected data is sent to the server at regular intervals using the MQTT protocol.

[0386] Receiving and storing data

[0387] 2. Server:

[0388] The data sent from the device is received and stored in a database such as Amazon DynamoDB. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This organizes the data into one suitable for analysis.

[0389] Pre-disease sign detection and emotion analysis

[0390] 3. Server:

[0391] A machine learning model using TensorFlow is applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to find signs of illness.

[0392] It also uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data to recognize the current emotional state.

[0393] Preventive measures generation and notification

[0394] 4. Server:

[0395] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user, and uses natural language generation technology to create messages in a format that is easy for the user to understand.

[0396] For example, specific advice may be generated such as, "You've been getting less exercise lately. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0397] 5. Terminal:

[0398] The generated message is sent as a push notification to the user's visual display device, such as a head-mounted display (HMD), and the user is expected to check it and take action.

[0399] Gathering feedback and updating the model

[0400] 6. Users:

[0401] Feedback regarding the proposed preventive measures and the results of their implementation can be entered via the HMD. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided.

[0402] 7. Terminal:

[0403] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[0404] 8. Server:

[0405] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[0406] Specific examples and prompts for the generative AI model

[0407] Situation setting:

[0408] A security guard receives the following data from an HMD worn by the guard during nighttime security surveillance:

[0409] Heart rate: 150 BPM

[0410] Steps: 12,000

[0411] Body temperature: 38℃

[0412] Run prompt:

[0413] The text prompt looks like this:

[0414] The following data is received from the HMD worn by the user during the night shift:

[0415] Heart rate: 150 BPM

[0416] Steps: 12,000

[0417] Body temperature: 38℃

[0418] Based on this data, stress signs are detected. A notification message should be generated and sent to the HMD, stating "Your stress level is high, please take a 5-minute break."

[0419] In this way, a system that analyzes a user's daily lifestyle data and emotional state and provides appropriate preventive measures is expected to be very useful in managing health conditions in actual work.

[0420] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0421] Step 1:

[0422] Data collection

[0423] The smartphone or wearable device worn by the user uses sensors to collect lifestyle data (e.g., number of steps, heart rate, sleep patterns, etc.). During this process, the input data is biometric data from various sensors, and the output is the collected raw data. The device prepares to send this data to a server at regular intervals.

[0424] Step 2:

[0425] Data transmission

[0426] The device sends the collected lifestyle habit data to a server using the MQTT protocol. The input data is the collected lifestyle habit data, and the output is the data sent to the server. During data transfer, the device monitors whether the communication is stable.

[0427] Step 3:

[0428] Data reception and storage

[0429] The server receives the data sent from the device and stores it in a database such as Amazon DynamoDB. The input data is the lifestyle habit data received from the device, and the output is the data stored in the database. The received data is first checked for format consistency and missing parts, and if abnormal or missing values ​​are detected, correction procedures are carried out.

[0430] Step 4:

[0431] Detecting signs of pre-disease

[0432] The server applies machine learning models to the stored data using TensorFlow to detect signs of pre-disease. The input data is lifestyle data after validation, and the output is information on abnormal patterns and signs of pre-disease. The data is analyzed through the machine learning model, and any abnormal patterns are recorded as signs.

[0433] Step 5:

[0434] Emotion analysis

[0435] The server uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data (e.g., tone of voice and text messages) to recognize the user's emotional state. The input data is the collected emotional data, and the output is the emotional state information resulting from the analysis. The emotion engine analyzes text and voice data to detect the user's current emotional state.

[0436] Step 6:

[0437] Generate preventative measures

[0438] The server uses natural language generation technology to generate optimal preventive measures for each individual user based on their pre-illness signs and emotional state. The input data is information about pre-illness signs and emotional state, and the output is a generated preventive measure message. For example, the generated advice might be, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0439] Step 7:

[0440] Preventive Measures Notice

[0441] The device displays the preventive measures message sent from the server as a push notification on a visual display device (e.g., a head-mounted display). The input data is the preventive measures message sent from the server, and the output is the notification displayed on the user's visual display device. The user is expected to confirm and implement the preventive measures through this.

[0442] Step 8:

[0443] Feedback collection

[0444] The user inputs feedback on the proposed preventive measures and the results of their implementation via a visual display device. The input data is the feedback information from the user, and the output is the feedback sent to the server. The user provides specific feedback, and the results are reflected in the next preventive measures.

[0445] Step 9:

[0446] Model Update

[0447] The server receives and analyzes user feedback and emotion data. The input data is the user feedback and emotion data, and the output is an updated machine learning model. This updates the machine learning model to reflect the next preventive action suggestion, allowing the system to continuously make suggestions adapted to the user's behavior and habits.

[0448] 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.

[0449] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0450] 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.

[0451] [Second embodiment]

[0452] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0453] 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.

[0454] 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).

[0455] 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.

[0456] 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.

[0457] 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).

[0458] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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.

[0463] 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."

[0464] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of illness, and proposes individually optimized preventative measures. This system realizes effective health management by incorporating feedback into the data. Specific program processing is explained below in natural language.

[0465] Data collection and transmission

[0466] Terminal

[0467] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0468] Receiving and storing data

[0469] server

[0470] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[0471] Detecting signs of pre-disease

[0472] server

[0473] Machine learning models are applied to the stored data to detect abnormal patterns in step counts, heart rate, etc. A number of health indicators are calculated to detect signs of illness, such as a significant decrease in recent step counts compared to historical averages or an increase in heart rate variability.

[0474] Preventive measures generation and notification

[0475] server

[0476] Based on the detected signs of illness, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice such as "Your exercise volume has decreased recently. Try walking 30 minutes every day" is generated.

[0477] Terminal

[0478] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0479] Gathering feedback and updating the model

[0480] User

[0481] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0482] server

[0483] It receives and analyzes user feedback, which is then reflected in the next preventative measures suggested to the machine learning model, allowing the system to continually adapt its suggestions to the user's behavior and habits.

[0484] Specific examples

[0485] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. The server generates a preventive measure, suggesting, "Your physical activity has decreased, so try walking for 30 minutes on the weekend." and notifies the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server uses that feedback to update the model and provide a more optimized preventive measure next time.

[0486] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and supports continuous health management.

[0487] The processing flow will be explained below.

[0488] Step 1:

[0489] Device:

[0490] Smartphones and wearable devices use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications provide users with the option to manually input dietary information.

[0491] Step 2:

[0492] Device:

[0493] The collected lifestyle data is sent to the server at regular intervals (e.g., every hour or every day). If a network connection is unavailable, the data is sent in batches the next time a connection is made.

[0494] Step 3:

[0495] server:

[0496] It receives JSON format data sent from the device, records the received data in a log, and saves the data in a database for subsequent processing.

[0497] Step 4:

[0498] server:

[0499] Data validation is performed to detect missing data and outliers. Data correction is performed as necessary to ensure data quality. The corrected data is converted into a format for analysis.

[0500] Step 5:

[0501] server:

[0502] It uses machine learning models to analyze lifestyle data and detect signs of pre-disease, including abnormal patterns such as a sudden decrease in step count or increased heart rate variability.

[0503] Step 6:

[0504] server:

[0505] Based on the detected signs of illness, the system generates personalized and optimized preventive measures, and uses natural language generation (NLG) technology to create messages in a format that is easy for users to understand.

[0506] Step 7:

[0507] server:

[0508] The generated preventive action message is sent to the user's device in the form of a push notification, along with metadata (such as the importance of the preventive action and when it should be taken).

[0509] Step 8:

[0510] Device:

[0511] The received message will be displayed in the user interface, and the user will be prompted to review and take action on preventative measures through the application.

[0512] Step 9:

[0513] User:

[0514] Enter your feedback on the suggested preventative measures. The application asks a simple question (e.g., "Did this suggestion help you?") and collects your response.

[0515] Step 10:

[0516] Device:

[0517] User feedback data is sent to the server, including the usefulness of the proposal and the difficulty of its implementation.

[0518] Step 11:

[0519] server:

[0520] The received feedback data is analyzed and the machine learning model is updated, which makes the next preventative measures recommendations more accurate.

[0521] Step 12:

[0522] server:

[0523] It will continue to operate updated machine learning models and pre-disease sign detection algorithms, which will continuously monitor user data and provide individually optimized preventative measures in a timely manner.

[0524] Example 1

[0525] 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."

[0526] Conventional health management systems have struggled to effectively collect and analyze a user's lifestyle data and propose individually optimized preventive measures. Furthermore, it has been difficult to effectively collect feedback on the proposed preventive measures and reflect it in the system, resulting in insufficient continuous health management. The present invention aims to solve these problems by providing a system that achieves effective health management by performing detailed analysis and proposing preventive measures based on a user's lifestyle data and updating the model based on the feedback.

[0527] 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.

[0528] In this invention, the server includes a means for collecting data related to the user's health, a means for transmitting the collected health data to the communication device, and a means for analyzing the collected health data and detecting signs of pre-disease in the communication device. This makes it possible to effectively collect and analyze the user's lifestyle data, generate individually optimized preventive measures, and update the machine learning model based on the feedback.

[0529] "User" means an individual who utilizes the system to manage their health status and provide feedback.

[0530] "Health data" refers to information about a user's health and lifestyle, such as the number of steps taken, heart rate, sleep patterns, and dietary information.

[0531] "Means of collection" refers to the functions and processes that collect user health data using devices such as smartphones and wearable devices.

[0532] "Communication device" refers to a server or computer system that processes, stores, analyzes, and notifies data received from a user's device.

[0533] "Means of analysis" refers to the functions and processes that use machine learning models and statistical analysis techniques to evaluate collected data and detect signs of pre-disease.

[0534] "Pre-illness signs" are early symptoms or signs of abnormalities that appear before the user's health condition deteriorates.

[0535] "Individually optimized preventive measures" refer to preventive measures and advice that are optimal for each user, proposed based on the user's personal health data and analysis results.

[0536] "Generation means" refers to the function or process that uses natural language generation techniques or algorithms to generate preventative measures to notify users.

[0537] "Means of notification" refers to the function or process that sends the generated preventative measures to the user's device in the form of a push notification or alert.

[0538] "Feedback data" refers to information entered into the system by users regarding their impressions of proposed preventive measures and the results of their implementation.

[0539] "Means for updating machine learning models" refers to the functions and processes that optimize and improve the prevention generation algorithms and models based on feedback data collected from users.

[0540] MODE FOR CARRYING OUT THE INVENTION

[0541] This invention is a system that collects and analyzes lifestyle data from users to detect pre-disease symptoms and proposes individually optimized preventive measures. By incorporating feedback into the system, this system achieves effective health management.

[0542] Data collection and transmission

[0543] Device:

[0544] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0545] As a specific example, if a user uses a smartphone and a wearable device, the device records data on the number of steps taken and heart rate in real time, and at night the smartphone automatically sends the data for the day to a server.

[0546] Receiving and storing data

[0547] server:

[0548] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected.

[0549] As a concrete example, we use a Python script on the server to format the data, run an outlier detection algorithm on it, and then store the formatted data in a database.

[0550] Detecting signs of pre-disease

[0551] server:

[0552] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to detect signs of illness.

[0553] As a concrete example, the server analyzes step count data from the past month using a machine learning library (e.g., scikit-learn) and detects that the average number of steps has decreased significantly in the last week.

[0554] Preventive measures generation and notification

[0555] server:

[0556] Based on the detected pre-disease signs, the system generates optimal preventive measures for each individual user, using natural language generation technology to create messages in a format that is easy for users to understand.

[0557] As a concrete example, a generative AI model is used to generate a message such as, "Your exercise volume has decreased recently. Try walking 30 minutes every day."

[0558] Device:

[0559] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0560] Gathering feedback and updating the model

[0561] User:

[0562] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0563] server:

[0564] It receives and analyzes user feedback, which is then used to update the machine learning model to reflect the feedback in the next preventative action recommendations.

[0565] As a specific example, when the server receives feedback data, it evaluates the feedback with analytical algorithms and adjusts the weights and parameters of the model.

[0566] Prompt Sentence Examples

[0567] "Your daily step count has decreased significantly compared to average. To increase your exercise, try walking 30 minutes every day. Even walking three times a week will be effective, so try to continue within your limits."

[0568] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle data and supports continuous health management.

[0569] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0570] Specific processing steps of the program

[0571] Step 1:

[0572] The device collects health data (such as the number of steps taken, heart rate, sleep patterns, and dietary information) from the user using a dedicated application or wearable device. Specifically, the device uses sensors to record data in real time, and the smartphone application allows the user to manually enter dietary information.

[0573] Input: User's health data

[0574] Output: A set of collected health data

[0575] Step 2:

[0576] The device sends the collected health data to a server at regular intervals via an internet connection. The specific data transmission operation involves the device automatically uploading data to the server at night or at a set time.

[0577] Input: A set of collected health data

[0578] Output: Data sent to the server

[0579] Step 3:

[0580] The server receives the health data sent from the device and stores it in a dedicated database. The specific operations of receiving and storing data involve the server first validating the data (e.g., detecting missing data and outliers), correcting it into an appropriate format, and then storing it in the database.

[0581] Input: Submitted health data

[0582] Output: Data stored in the database

[0583] Step 4:

[0584] The server applies machine learning models to the stored health data to detect signs of illness. This process involves using algorithms to calculate health indicators (e.g., steps taken, heart rate variability) and identify abnormal patterns. Specific operations include running analysis scripts using Python libraries.

[0585] Input: Data stored in a database

[0586] Output: Detected signs of pre-disease

[0587] Step 5:

[0588] The server generates individually optimized preventive measures based on the detected pre-disease signs. This generation utilizes a generative AI model and natural language generation technology. Specifically, the generative AI model generates a message that is easy for the user to understand.

[0589] Input: Detected signs of illness

[0590] Output: Generated preventative action message

[0591] Step 6:

[0592] The device notifies the user of the preventive measures message sent from the server. This can be done via push notification or in-app messaging. Specifically, the device receives the notification and displays details when the user opens the app.

[0593] Input: Generated precaution message

[0594] Output: Preventive measures communicated to the user

[0595] Step 7:

[0596] The user inputs feedback on the proposed preventive measures through the application. Specifically, a feedback form is displayed in the application for inputting impressions and effects.

[0597] Input: User feedback on preventative measures

[0598] Output: Collected feedback data

[0599] Step 8:

[0600] The server receives and analyzes feedback data from users. The specific operation of the feedback analysis is to evaluate their impressions and implementation results and update the machine learning model to reflect these in the next proposal.

[0601] Input: Collected feedback data

[0602] Output: Updated machine learning model

[0603] In this way, by explaining in detail the specific input, data processing, data calculation, and output that take place at each step, the processing flow of the entire system can be clearly understood.

[0604] (Application example 1)

[0605] 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."

[0606] Conventional health management systems are limited to detecting pre-disease signs and proposing preventive measures based solely on the user's lifestyle data, and do not achieve individual optimization that fully considers individual lifestyle patterns and economic activities (e.g., dietary content and use of fitness services).Therefore, there is a need for highly accurate detection of pre-disease signs and proposing preventive measures by including activity data that is closely related to the user's health condition.

[0607] 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.

[0608] In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to the server, means for collecting electronic payment data, means for analyzing the collected lifestyle habit data and electronic payment data in the server to detect pre-disease signs, means for generating individually optimized preventive measures based on the pre-disease signs, means for generating the preventive measures in natural language that is easy for the user to understand using a generative AI model and prompt sentences, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data. This enables highly accurate detection of pre-disease signs and provision of individually optimized preventive measures that take into account both the user's lifestyle habit data and electronic payment data.

[0609] "User" means an individual who uses the health care system.

[0610] "Lifestyle data" refers to data related to a user's daily health and behavior, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[0611] A "server" is a computer system that stores and analyzes collected data.

[0612] "Electronic payment data" refers to transaction data related to electronic payments made by users, and specifically includes health food purchase history and fitness service usage history.

[0613] "Pre-disease signs" are data patterns or indicators that indicate a user may be currently healthy but may develop illness in the future.

[0614] "Individually optimized preventive measures" are specific suggestions and measures for optimal health management and disease prevention for each individual user, based on the user's lifestyle and electronic payment data.

[0615] A "generative AI model" is an artificial intelligence model that uses natural language generation technology to automatically generate messages for users.

[0616] A "prompt sentence" is an input sentence that instructs the generative AI model to generate a message.

[0617] "Feedback data" refers to information provided by users about their impressions of preventive measures and the results of their implementation.

[0618] A "machine learning model" is an algorithm or data model used to improve the accuracy of analysis and preventative measures suggested based on collected data and feedback.

[0619] The present invention is a system that collects a user's lifestyle data and electronic payment data, analyzes them to detect signs of illness, and proposes individually optimized preventive measures. The following hardware and software are used to implement the present invention.

[0620] Hardware

[0621] Smartphone: Collects data on the user's daily habits (e.g., steps, heart rate, sleep patterns).

[0622] Server: Stores and analyzes collected data.

[0623] software

[0624] Requests library: Communicate with the API to obtain transaction data and feedback.

[0625] Pandas library: Used to read and manage data.

[0626] Scikit-learn library: Used for data normalization and outlier detection (Isolation Forest algorithm).

[0627] Overview of data processing and calculation

[0628] 1. Data collection (device side): Applications installed on smartphones collect lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Transaction data related to electronic payments made by users is also collected.

[0629] 2. Data transmission (from terminal to server): Collected lifestyle data and electronic payment data are sent to the server at regular intervals.

[0630] 3. Data storage and validation (server side): The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data.

[0631] 4. Pre-disease sign detection (server side): Using the validated data, the Isolation Forest algorithm is applied to detect abnormal patterns. Pre-disease signs are found based on step counts, heart rate, and transaction data.

[0632] 5. Generate personalized preventive measures (server-side): Based on the detected signs of illness, preventive measures are generated using generative AI models and prompts. The generated preventive measures are written for the user in natural language.

[0633] 6. Notification (from server to device): The generated preventive measures are notified to the user via push notifications on the smartphone.

[0634] 7. Feedback collection (terminal side): Users enter their thoughts on the proposed preventive measures and the results of their implementation as feedback through the application.

[0635] 8. Feedback analysis and model update (server side): Based on the collected feedback data, the machine learning model is updated and reflected in future preventive measures.

[0636] Specific examples

[0637] When a user uses a smartphone and a fitness tracker, the user's step count data and electronic payment data (e.g., food purchase history or fitness center usage history) are collected and sent to a server. The server compares this data with past data and detects a decrease in exercise volume. As a result, a preventive measure is generated, such as "Your exercise volume has decreased recently. Try walking every day," and a notification is sent to the user's device. After the user has completed the exercise, the user provides feedback, saying, "This amount of exercise was just right," and the server updates the model based on that feedback.

[0638] Prompt Sentence Examples

[0639] An example of a prompt sentence to be input to the generative AI model is, "Create an application that collects user transaction data, detects signs of pre-illness based on health indicators (number of steps, heart rate, sleep patterns), and suggests optimal preventive measures. Use the Isolation Forest algorithm to detect anomalies, and use natural language generation technology to generate a message that is easy for the user to understand. For example, a message such as, 'Your exercise volume has decreased recently. Try walking 30 minutes every day.'"

[0640] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0641] Step 1:

[0642] Data collection (terminal side)

[0643] An application installed on a smartphone uses sensors to collect lifestyle data (number of steps, heart rate, sleep patterns), and electronic payment data. This input data is then periodically organized and saved within the app.

[0644] Step 2:

[0645] Data transmission (from device to server)

[0646] The application periodically transmits the collected lifestyle and electronic payment data to a server. The transmission is via an internet connection and the data is encrypted, ensuring data security. The transmitted data also includes metadata such as collection timestamps and device identifiers.

[0647] Step 3:

[0648] Data storage and validation (server side)

[0649] The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data. This validation uses the Pandas library to shape and clean the data. For example, an anomaly detection algorithm using standard deviation is applied to detect outliers.

[0650] Step 4:

[0651] Detecting signs of illness (server side)

[0652] The server analyzes the validated data and uses the Isolation Forest algorithm to detect signs of pre-disease. Past lifestyle habits and electronic payment data are used as input data. The output is a list of data points containing abnormal patterns. The Scikit-learn library is used for the analysis.

[0653] Step 5:

[0654] Individually optimized preventive measures generation (server side)

[0655] The server generates preventive measures based on the detected signs of illness using a generative AI model and prompts. Natural language generation technology is used to generate messages in a format that is easy for users to understand. The generated messages are in natural language rather than JSON format, making them easy for users to understand.

[0656] Step 6:

[0657] Notification (from server to device)

[0658] The generated preventive measures are notified to the user via the smartphone's push notification function. The server selects notification recipients based on the user's identification information and sends the notification via API. The notification includes specific actions for the preventive measures (e.g., a suggestion to walk daily).

[0659] Step 7:

[0660] Feedback collection (device side)

[0661] Users can enter feedback on the proposed preventive measures through the application. The feedback includes the results of implementing the preventive measures and their impressions. This feedback data is temporarily stored on the device and sent to the server the next time data is transmitted.

[0662] Step 8:

[0663] Feedback analysis and model updates (server side)

[0664] The server analyzes the received feedback data and updates the machine learning model. Past feedback data is also used in the analysis, and adjustments are made to improve the accuracy of the model. For example, the hyperparameters of the anomaly detection algorithm are readjusted based on the feedback results. This allows for more personalized optimization of preventive measures proposed from the next time onwards.

[0665] 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.

[0666] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect pre-disease signs, and proposes individually optimized preventative measures. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it achieves more precise and effective health management. This system continues to achieve effective health management by incorporating user feedback. The specific program processing is explained below in natural language.

[0667] Data collection and transmission

[0668] Device:

[0669] The user's smartphone or wearable device uses sensors to collect daily lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0670] Receiving and storing data

[0671] server:

[0672] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[0673] Pre-disease sign detection and emotion analysis

[0674] server:

[0675] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. Numerous health indicators are calculated to identify signs of illness. An emotion engine also analyzes user feedback and other emotional data (e.g., text messages and tone of voice) to recognize the user's current emotional state.

[0676] Preventive measures generation and notification

[0677] server:

[0678] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice is generated such as, "You've been getting less exercise lately. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0679] Device:

[0680] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0681] Gathering feedback and updating the model

[0682] User:

[0683] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0684] Device:

[0685] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[0686] server:

[0687] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[0688] Specific examples

[0689] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. Furthermore, the emotion engine analyzes the user's text messages for signs of stress. The server generates a preventive measure, suggesting, "Since your physical activity has decreased, try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine." The server then sends a notification to the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server updates the model based on that feedback and emotion data, and provides a more optimized preventive measure next time.

[0690] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and emotional state, and supports continuous health management.

[0691] The processing flow will be explained below.

[0692] Step 1:

[0693] Device:

[0694] The user's smartphone or wearable device uses sensors to collect lifestyle data such as steps taken, heart rate, and sleep patterns. The user can manually enter dietary information through a smartphone application. The device records the data at regular intervals.

[0695] Step 2:

[0696] Device:

[0697] The device sends the lifestyle data collected to the server at preset intervals. If the network connection is unstable, the data will be sent in batches the next time the device connects.

[0698] Step 3:

[0699] server:

[0700] The server receives the data sent from the terminal and stores it in a database. The received data is validated to detect missing data and abnormal values. This data is then corrected.

[0701] Step 4:

[0702] server:

[0703] Based on the saved data, a machine learning model is applied to analyze lifestyle data, using health indicators such as the number of steps taken, heart rate, and sleep patterns, and comparing them with past data to detect signs of illness.

[0704] Step 5:

[0705] server:

[0706] Once a pre-illness sign is detected, the emotion engine analyzes the user's emotional data, which is collected from feedback, text messages, voice data, etc. The emotion engine determines the user's current emotional state.

[0707] Step 6:

[0708] server:

[0709] It generates individually optimized preventive measures based on pre-disease signs and emotional state. It uses natural language generation technology to create messages in a format that is easy for users to understand. For example, it generates specific advice such as, "You've been getting less exercise lately. Try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine."

[0710] Step 7:

[0711] server:

[0712] The generated preventive action message is sent to the user's device as a push notification, along with metadata including the timing and severity of the preventive action.

[0713] Step 8:

[0714] Device:

[0715] The device will display the preventive measures message it receives on the user interface (UI). The user is prompted to acknowledge the notification and take action. The notification is displayed in the form of an alert, so users will not miss it.

[0716] Step 9:

[0717] User:

[0718] Users can then implement the suggested preventative measures and provide feedback about their results through the application, with options such as "helpful" or "difficult," or they can enter detailed thoughts in text format.

[0719] Step 10:

[0720] Device:

[0721] The device sends user feedback data, including the user's emotional state, to the server, which records how the user felt.

[0722] Step 11:

[0723] server:

[0724] The server analyzes the received feedback data and sentiment data, which are then used to update the machine learning model and sentiment engine, allowing the system to further optimize its next preventative action suggestions.

[0725] Step 12:

[0726] server:

[0727] Using updated machine learning models and an emotion engine, it continuously monitors users' lifestyle data and provides individually optimized preventative measures at the appropriate time.

[0728] In this way, the system analyzes the user's lifestyle data and emotional state in real time and continuously suggests optimized preventive measures, supporting effective health management.

[0729] Example 2

[0730] 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."

[0731] In recent years, the importance of health management has increased, with particular attention being paid to early detection and prevention of pre-disease. However, conventional systems have insufficient collection and analysis of users' lifestyle data, making it difficult to provide personalized preventative measures. Furthermore, health management often fails to take into account the user's emotional state, making it difficult to effectively incorporate user feedback. As a result, the preventative measures provided by the system do not match the user's actual needs, resulting in problems with insufficient continuous health management.

[0732] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to a remote server, means for analyzing the collected lifestyle habit data in the remote server to detect signs of abnormal health, means for generating individually optimized preventive measures based on the signs of abnormal health, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data and emotion analysis data. This makes it possible to provide individually optimized preventive measures that comprehensively consider the user's lifestyle habits and emotional state.

[0733] "User" refers to an individual who uses the health care system.

[0734] "Lifestyle data" refers to information about a user's daily activities and conditions, including the number of steps taken, heart rate, sleep patterns, and dietary information.

[0735] "Collection means" refers to the method of collecting user lifestyle data using sensors, applications, etc.

[0736] "Remote Server" refers to a computer system over a network that receives, stores, and analyzes collected data.

[0737] "Validation" refers to the process of checking the accuracy and completeness of collected data.

[0738] "Correction" refers to the process of correcting data that contains deficiencies or anomalies and preparing it in a format that can be analyzed.

[0739] "Signs of abnormal health" refers to indicators or patterns that are recognized as potential health problems based on a user's lifestyle data.

[0740] "Analysis tools" refers to algorithms and software tools used to detect signs of health abnormalities based on collected lifestyle data.

[0741] "Preventive measures" refer to specific actions or measures suggested to users to improve symptoms of an abnormal health condition.

[0742] "Generation means" refers to the method of creating preventive measures based on collected data and analysis results.

[0743] "Notification Method" refers to the communication method used to inform users of the created preventative measures, including push notifications, emails, and SMS.

[0744] "Feedback Data" refers to information provided by users, including their impressions of and results of implementing preventive measures.

[0745] "Emotional Analysis Data" refers to information representing a user's emotional state extracted from user feedback and other data.

[0746] A "machine learning model" refers to an algorithm that learns from collected data to optimize preventive measures and detect new anomalies.

[0747] This invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of health abnormalities, and proposes individually optimized preventative measures. Furthermore, by combining this with emotion analysis, more precise and effective health management is realized. This system incorporates user feedback to continuously provide effective health management.

[0748] The terminal collects lifestyle data using the user's smartphone or wearable device. The devices used include, for example, smartphones and wearable devices. Users can also manually enter dietary information through a smartphone application. This data is automatically sent to a server at regular intervals. Specifically, for example, a smartphone and fitness tracker are used to send data to the server every night at midnight.

[0749] The server receives the data sent from the device and stores it in a dedicated database (e.g., Amazon RDS, DynamoDB). The data is first validated, and if outliers or missing data are detected, they are corrected using a correction algorithm. For example, if there is an outlier in the heart rate data, the data before and after is referenced and corrected using the average value.

[0750] The server applies machine learning models (e.g., TensorFlow, scikit-learn) using programming languages ​​such as Python to the stored data to detect signs of abnormal health. It analyzes whether there are any abnormal patterns based on specific health indicators. It also uses a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) to analyze the emotional state from user feedback and text messages. For example, if a user's text messages contain many of the words "tired" and "stressed," it will recognize this as a state of stress.

[0751] The server generates personalized preventive measures based on the detected health symptoms and emotional state. It uses natural language generation technology (e.g., OpenAI GPT-3) to create a message that is easy for the user to understand. For example, it generates a message that reads, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try practicing deep breathing to relax."

[0752] The generated message is sent to the user's device as a push notification. The user is expected to check the notification through the application and take action. For example, the notification may say, "Your physical activity is decreasing. See details."

[0753] The user can provide feedback on the proposed preventive measures through the application, for example, by inputting their thoughts such as, "This amount of exercise was just right." The device then sends this feedback data to the server.

[0754] The server receives and analyzes feedback and emotion data from users. The machine learning model is updated based on the feedback and emotion data, allowing future preventive measures to be more optimized for each user.

[0755] Prompt Sentence Examples

[0756] "Analyze step count data collected from users' fitness trackers to detect abnormal patterns. Also, determine users' emotional state from their text messages and generate appropriate health precautions."

[0757] A system configured in this way makes it possible to provide individually optimized preventive measures that comprehensively take into account the user's lifestyle habits and emotional state.

[0758] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0759] Step 1:

[0760] Data collection and transmission

[0761] Device:

[0762] A user's smartphone or wearable device collects lifestyle data such as step count, heart rate, and sleep patterns. This data collection is performed using sensors built into the smartphone or the wearable device. The user can also manually input dietary information using a smartphone application. The collected data is automatically sent to a remote server at regular intervals or at the end of the day. Specific input data include step count data, heart rate data, sleep data, and dietary information, and these are output data to the server.

[0763] Step 2:

[0764] Receiving and storing data

[0765] server:

[0766] The data sent from the device is received and stored in a database such as Amazon RDS or DynamoDB. At this time, the data is validated, and if missing data or outliers are detected, they are corrected using an automatic correction algorithm. For example, if the heart rate data contains an outlier, it is corrected using the average value of the heart rate data before and after. The input data is the collected lifestyle habit data, and the output data is the normalized data that has been validated and corrected.

[0767] Step 3:

[0768] Pre-disease sign detection and emotion analysis

[0769] server:

[0770] A machine learning model using Python (e.g., TensorFlow, scikit-learn) is applied to the saved normalized data. This detects abnormal patterns from step count data, heart rate data, etc. In addition, a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) is used to determine the user's emotional state from their text messages and feedback. The specific input data are the normalized lifestyle data and text messages, and the output data are the detected abnormal patterns and emotional state.

[0771] Step 4:

[0772] Preventive measures generation and notification

[0773] server:

[0774] Based on the detected abnormal patterns and emotional state, the system generates individually optimized preventive measures. Natural language generation technology (e.g., OpenAI GPT-3) is used to create messages that are easy for users to understand. The specific input data is the abnormal patterns and emotional state, and the output data is the preventive measure message. For example, a message may be generated that reads, "Your exercise volume has decreased recently. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0775] Device:

[0776] The generated preventive action message is sent to the user's device as a push notification. The user is expected to acknowledge the notification and take action through the application. The input data is the preventive action message, and the output data is the user's action or confirmation.

[0777] Step 5:

[0778] Gathering feedback and updating the model

[0779] User:

[0780] Feedback regarding the proposed preventive measures and the results of their implementation is entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided. The input data is the feedback information, and the output data is the feedback content.

[0781] Device:

[0782] The user's emotional state is also monitored in real time and sent to the server as emotional data as appropriate. A sudden increase in heart rate, for example, is sent as emotional analysis data. The input data is emotional state data such as heart rate data, and the output data is the sent emotional analysis data.

[0783] server:

[0784] It receives and analyzes feedback and sentiment data from users, which updates the machine learning model and further optimizes preventive measures for future visits. The input data is the feedback and sentiment data, and the output data is the updated machine learning model. For example, the model is updated weekly, and new suggestions are generated.

[0785] (Application example 2)

[0786] 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."

[0787] Conventional health management systems mainly monitor health status and suggest preventative measures based on users' lifestyle data, but do not provide precise health management that takes emotional states into account. Furthermore, particularly in security services, there is a lack of mechanisms for monitoring the health status of security guards in real time, who work long hours and in high-stress environments, and providing appropriate rest and support. This can lead to accumulated stress and overwork among security guards, potentially reducing work efficiency and safety.

[0788] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0789] In this invention, the server includes means for analyzing the user's emotional state, means for analyzing collected lifestyle habit data to detect signs of illness, means for combining the emotional state and lifestyle habit data to generate individually optimized preventive measures, and means for displaying the analysis results and preventive measures using a visual display device worn by the user. This makes it possible to monitor the user's health and emotional state in real time and provide appropriate rest and support.

[0790] "Lifestyle data" refers to data related to the user's daily activities, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[0791] "Server" refers to a computer system for receiving, storing, and analyzing collected data.

[0792] "Pre-illness signs" refer to the precursors and symptoms of illness, and are data patterns that indicate changes or abnormalities in health status.

[0793] "Preventive measures" are specific actions and initiatives suggested based on signs of illness, and are measures to maintain health.

[0794] "Feedback data" refers to information provided by users regarding their impressions of proposed preventive measures and the results of their implementation.

[0795] A "machine learning model" is an algorithmic model used to improve the accuracy of data analysis and predictions, learning from data and using it for analysis.

[0796] The "emotion analysis function" is a technology for analyzing a user's emotional state, recognizing emotions based on data such as text messages, tone of voice, and facial expressions.

[0797] A "visual display device" is a device worn by a user that has the function of visually displaying information, and includes, for example, a head-mounted display (HMD).

[0798] "Natural language generation technology" is a technology that allows a computer to generate sentences in natural language to create preventive measures and notifications in a form that is easy for users to understand.

[0799] The present invention is a system for managing health by collecting lifestyle habit data of a user and taking into consideration the user's emotional state. An embodiment of this system will be described in detail below.

[0800] Data collection and transmission

[0801] 1. Device:

[0802] The smartphones and wearable devices that users use daily use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications also allow users to manually input dietary information.

[0803] The collected data is sent to the server at regular intervals using the MQTT protocol.

[0804] Receiving and storing data

[0805] 2. Server:

[0806] The data sent from the device is received and stored in a database such as Amazon DynamoDB. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This organizes the data into one suitable for analysis.

[0807] Pre-disease sign detection and emotion analysis

[0808] 3. Server:

[0809] A machine learning model using TensorFlow is applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to find signs of illness.

[0810] It also uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data to recognize the current emotional state.

[0811] Preventive measures generation and notification

[0812] 4. Server:

[0813] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user, and uses natural language generation technology to create messages in a format that is easy for the user to understand.

[0814] For example, specific advice may be generated such as, "You've been getting less exercise lately. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0815] 5. Terminal:

[0816] The generated message is sent as a push notification to the user's visual display device, such as a head-mounted display (HMD), and the user is expected to check it and take action.

[0817] Gathering feedback and updating the model

[0818] 6. Users:

[0819] Feedback regarding the proposed preventive measures and the results of their implementation can be entered via the HMD. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided.

[0820] 7. Terminal:

[0821] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[0822] 8. Server:

[0823] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[0824] Specific examples and prompts for the generative AI model

[0825] Situation setting:

[0826] A security guard receives the following data from an HMD worn by the guard during nighttime security surveillance:

[0827] Heart rate: 150 BPM

[0828] Steps: 12,000

[0829] Body temperature: 38℃

[0830] Run prompt:

[0831] The text prompt looks like this:

[0832] The following data is received from the HMD worn by the user during the night shift:

[0833] Heart rate: 150 BPM

[0834] Steps: 12,000

[0835] Body temperature: 38℃

[0836] Based on this data, stress signs are detected. A notification message should be generated and sent to the HMD, stating "Your stress level is high, please take a 5-minute break."

[0837] In this way, a system that analyzes a user's daily lifestyle data and emotional state and provides appropriate preventive measures is expected to be very useful in managing health conditions in actual work.

[0838] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0839] Step 1:

[0840] Data collection

[0841] The smartphone or wearable device worn by the user uses sensors to collect lifestyle data (e.g., number of steps, heart rate, sleep patterns, etc.). During this process, the input data is biometric data from various sensors, and the output is the collected raw data. The device prepares to send this data to a server at regular intervals.

[0842] Step 2:

[0843] Data transmission

[0844] The device sends the collected lifestyle habit data to a server using the MQTT protocol. The input data is the collected lifestyle habit data, and the output is the data sent to the server. During data transfer, the device monitors whether the communication is stable.

[0845] Step 3:

[0846] Data reception and storage

[0847] The server receives the data sent from the device and stores it in a database such as Amazon DynamoDB. The input data is the lifestyle habit data received from the device, and the output is the data stored in the database. The received data is first checked for format consistency and missing parts, and if abnormal or missing values ​​are detected, correction procedures are carried out.

[0848] Step 4:

[0849] Detecting signs of pre-disease

[0850] The server applies machine learning models to the stored data using TensorFlow to detect signs of pre-disease. The input data is lifestyle data after validation, and the output is information on abnormal patterns and signs of pre-disease. The data is analyzed through the machine learning model, and any abnormal patterns are recorded as signs.

[0851] Step 5:

[0852] Emotion analysis

[0853] The server uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data (e.g., tone of voice and text messages) to recognize the user's emotional state. The input data is the collected emotional data, and the output is the emotional state information resulting from the analysis. The emotion engine analyzes text and voice data to detect the user's current emotional state.

[0854] Step 6:

[0855] Generate preventative measures

[0856] The server uses natural language generation technology to generate optimal preventive measures for each individual user based on their pre-illness signs and emotional state. The input data is information about pre-illness signs and emotional state, and the output is a generated preventive measure message. For example, the generated advice might be, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[0857] Step 7:

[0858] Preventive Measures Notice

[0859] The device displays the preventive measures message sent from the server as a push notification on a visual display device (e.g., a head-mounted display). The input data is the preventive measures message sent from the server, and the output is the notification displayed on the user's visual display device. The user is expected to confirm and implement the preventive measures through this.

[0860] Step 8:

[0861] Feedback collection

[0862] The user inputs feedback on the proposed preventive measures and the results of their implementation via a visual display device. The input data is the feedback information from the user, and the output is the feedback sent to the server. The user provides specific feedback, and the results are reflected in the next preventive measures.

[0863] Step 9:

[0864] Model Update

[0865] The server receives and analyzes user feedback and emotion data. The input data is the user feedback and emotion data, and the output is an updated machine learning model. This updates the machine learning model to reflect the next preventive action suggestion, allowing the system to continuously make suggestions adapted to the user's behavior and habits.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] [Third embodiment]

[0870] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0871] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0872] 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).

[0873] 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.

[0874] 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.

[0875] 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).

[0876] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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."

[0882] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of illness, and proposes individually optimized preventative measures. This system realizes effective health management by incorporating feedback into the data. Specific program processing is explained below in natural language.

[0883] Data collection and transmission

[0884] Terminal

[0885] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0886] Receiving and storing data

[0887] server

[0888] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[0889] Detecting signs of pre-disease

[0890] server

[0891] Machine learning models are applied to the stored data to detect abnormal patterns in step counts, heart rate, etc. A number of health indicators are calculated to detect signs of illness, such as a significant decrease in recent step counts compared to historical averages or an increase in heart rate variability.

[0892] Preventive measures generation and notification

[0893] server

[0894] Based on the detected signs of illness, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice such as "Your exercise volume has decreased recently. Try walking 30 minutes every day" is generated.

[0895] Terminal

[0896] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0897] Gathering feedback and updating the model

[0898] User

[0899] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0900] server

[0901] It receives and analyzes user feedback, which is then reflected in the next preventative measures suggested to the machine learning model, allowing the system to continually adapt its suggestions to the user's behavior and habits.

[0902] Specific examples

[0903] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. The server generates a preventive measure, suggesting, "Your physical activity has decreased, so try walking for 30 minutes on the weekend." and notifies the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server uses that feedback to update the model and provide a more optimized preventive measure next time.

[0904] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and supports continuous health management.

[0905] The processing flow will be explained below.

[0906] Step 1:

[0907] Device:

[0908] Smartphones and wearable devices use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications provide users with the option to manually input dietary information.

[0909] Step 2:

[0910] Device:

[0911] The collected lifestyle data is sent to the server at regular intervals (e.g., every hour or every day). If a network connection is unavailable, the data is sent in batches the next time a connection is made.

[0912] Step 3:

[0913] server:

[0914] It receives JSON format data sent from the device, records the received data in a log, and saves the data in a database for subsequent processing.

[0915] Step 4:

[0916] server:

[0917] Data validation is performed to detect missing data and outliers. Data correction is performed as necessary to ensure data quality. The corrected data is converted into a format for analysis.

[0918] Step 5:

[0919] server:

[0920] It uses machine learning models to analyze lifestyle data and detect signs of pre-disease, including abnormal patterns such as a sudden decrease in step count or increased heart rate variability.

[0921] Step 6:

[0922] server:

[0923] Based on the detected signs of illness, the system generates personalized and optimized preventive measures, and uses natural language generation (NLG) technology to create messages in a format that is easy for users to understand.

[0924] Step 7:

[0925] server:

[0926] The generated preventive action message is sent to the user's device in the form of a push notification, along with metadata (such as the importance of the preventive action and when it should be taken).

[0927] Step 8:

[0928] Device:

[0929] The received message will be displayed in the user interface, and the user will be prompted to review and take action on preventative measures through the application.

[0930] Step 9:

[0931] User:

[0932] Enter your feedback on the suggested preventative measures. The application asks a simple question (e.g., "Did this suggestion help you?") and collects your response.

[0933] Step 10:

[0934] Device:

[0935] User feedback data is sent to the server, including the usefulness of the proposal and the difficulty of its implementation.

[0936] Step 11:

[0937] server:

[0938] The received feedback data is analyzed and the machine learning model is updated, which makes the next preventative measures recommendations more accurate.

[0939] Step 12:

[0940] server:

[0941] It will continue to operate updated machine learning models and pre-disease sign detection algorithms, which will continuously monitor user data and provide individually optimized preventative measures in a timely manner.

[0942] Example 1

[0943] 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."

[0944] Conventional health management systems have struggled to effectively collect and analyze a user's lifestyle data and propose individually optimized preventive measures. Furthermore, it has been difficult to effectively collect feedback on the proposed preventive measures and reflect it in the system, resulting in insufficient continuous health management. The present invention aims to solve these problems by providing a system that achieves effective health management by performing detailed analysis and proposing preventive measures based on a user's lifestyle data and updating the model based on the feedback.

[0945] 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.

[0946] In this invention, the server includes a means for collecting data related to the user's health, a means for transmitting the collected health data to the communication device, and a means for analyzing the collected health data and detecting signs of pre-disease in the communication device. This makes it possible to effectively collect and analyze the user's lifestyle data, generate individually optimized preventive measures, and update the machine learning model based on the feedback.

[0947] "User" means an individual who utilizes the system to manage their health status and provide feedback.

[0948] "Health data" refers to information about a user's health and lifestyle, such as the number of steps taken, heart rate, sleep patterns, and dietary information.

[0949] "Means of collection" refers to the functions and processes that collect user health data using devices such as smartphones and wearable devices.

[0950] "Communication device" refers to a server or computer system that processes, stores, analyzes, and notifies data received from a user's device.

[0951] "Means of analysis" refers to the functions and processes that use machine learning models and statistical analysis techniques to evaluate collected data and detect signs of pre-disease.

[0952] "Pre-illness signs" are early symptoms or signs of abnormalities that appear before the user's health condition deteriorates.

[0953] "Individually optimized preventive measures" refer to preventive measures and advice that are optimal for each user, proposed based on the user's personal health data and analysis results.

[0954] "Generation means" refers to the function or process that uses natural language generation techniques or algorithms to generate preventative measures to notify users.

[0955] "Means of notification" refers to the function or process that sends the generated preventative measures to the user's device in the form of a push notification or alert.

[0956] "Feedback data" refers to information entered into the system by users regarding their impressions of proposed preventive measures and the results of their implementation.

[0957] "Means for updating machine learning models" refers to the functions and processes that optimize and improve the prevention generation algorithms and models based on feedback data collected from users.

[0958] MODE FOR CARRYING OUT THE INVENTION

[0959] This invention is a system that collects and analyzes lifestyle data from users to detect pre-disease symptoms and proposes individually optimized preventive measures. By incorporating feedback into the system, this system achieves effective health management.

[0960] Data collection and transmission

[0961] Device:

[0962] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[0963] As a specific example, if a user uses a smartphone and a wearable device, the device records data on the number of steps taken and heart rate in real time, and at night the smartphone automatically sends the data for the day to a server.

[0964] Receiving and storing data

[0965] server:

[0966] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected.

[0967] As a concrete example, we use a Python script on the server to format the data, run an outlier detection algorithm on it, and then store the formatted data in a database.

[0968] Detecting signs of pre-disease

[0969] server:

[0970] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to detect signs of illness.

[0971] As a concrete example, the server analyzes step count data from the past month using a machine learning library (e.g., scikit-learn) and detects that the average number of steps has decreased significantly in the last week.

[0972] Preventive measures generation and notification

[0973] server:

[0974] Based on the detected pre-disease signs, the system generates optimal preventive measures for each individual user, using natural language generation technology to create messages in a format that is easy for users to understand.

[0975] As a concrete example, a generative AI model is used to generate a message such as, "Your exercise volume has decreased recently. Try walking 30 minutes every day."

[0976] Device:

[0977] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[0978] Gathering feedback and updating the model

[0979] User:

[0980] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[0981] server:

[0982] It receives and analyzes user feedback, which is then used to update the machine learning model to reflect the feedback in the next preventative action recommendations.

[0983] As a specific example, when the server receives feedback data, it evaluates the feedback with analytical algorithms and adjusts the weights and parameters of the model.

[0984] Prompt Sentence Examples

[0985] "Your daily step count has decreased significantly compared to average. To increase your exercise, try walking 30 minutes every day. Even walking three times a week will be effective, so try to continue within your limits."

[0986] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle data and supports continuous health management.

[0987] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0988] Specific processing steps of the program

[0989] Step 1:

[0990] The device collects health data (such as the number of steps taken, heart rate, sleep patterns, and dietary information) from the user using a dedicated application or wearable device. Specifically, the device uses sensors to record data in real time, and the smartphone application allows the user to manually enter dietary information.

[0991] Input: User's health data

[0992] Output: A set of collected health data

[0993] Step 2:

[0994] The device sends the collected health data to a server at regular intervals via an internet connection. The specific data transmission operation involves the device automatically uploading data to the server at night or at a set time.

[0995] Input: A set of collected health data

[0996] Output: Data sent to the server

[0997] Step 3:

[0998] The server receives the health data sent from the device and stores it in a dedicated database. The specific operations of receiving and storing data involve the server first validating the data (e.g., detecting missing data and outliers), correcting it into an appropriate format, and then storing it in the database.

[0999] Input: Submitted health data

[1000] Output: Data stored in the database

[1001] Step 4:

[1002] The server applies machine learning models to the stored health data to detect signs of illness. This process involves using algorithms to calculate health indicators (e.g., steps taken, heart rate variability) and identify abnormal patterns. Specific operations include running analysis scripts using Python libraries.

[1003] Input: Data stored in a database

[1004] Output: Detected signs of pre-disease

[1005] Step 5:

[1006] The server generates individually optimized preventive measures based on the detected pre-disease signs. This generation utilizes a generative AI model and natural language generation technology. Specifically, the generative AI model generates a message that is easy for the user to understand.

[1007] Input: Detected signs of illness

[1008] Output: Generated preventative action message

[1009] Step 6:

[1010] The device notifies the user of the preventive measures message sent from the server. This can be done via push notification or in-app messaging. Specifically, the device receives the notification and displays details when the user opens the app.

[1011] Input: Generated precaution message

[1012] Output: Preventive measures communicated to the user

[1013] Step 7:

[1014] The user inputs feedback on the proposed preventive measures through the application. Specifically, a feedback form is displayed in the application for inputting impressions and effects.

[1015] Input: User feedback on preventative measures

[1016] Output: Collected feedback data

[1017] Step 8:

[1018] The server receives and analyzes feedback data from users. The specific operation of the feedback analysis is to evaluate their impressions and implementation results and update the machine learning model to reflect these in the next proposal.

[1019] Input: Collected feedback data

[1020] Output: Updated machine learning model

[1021] In this way, by explaining in detail the specific input, data processing, data calculation, and output that take place at each step, the processing flow of the entire system can be clearly understood.

[1022] (Application example 1)

[1023] 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."

[1024] Conventional health management systems are limited to detecting pre-disease signs and proposing preventive measures based solely on the user's lifestyle data, and do not achieve individual optimization that fully considers individual lifestyle patterns and economic activities (e.g., dietary content and use of fitness services).Therefore, there is a need for highly accurate detection of pre-disease signs and proposing preventive measures by including activity data that is closely related to the user's health condition.

[1025] 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.

[1026] In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to the server, means for collecting electronic payment data, means for analyzing the collected lifestyle habit data and electronic payment data in the server to detect pre-disease signs, means for generating individually optimized preventive measures based on the pre-disease signs, means for generating the preventive measures in natural language that is easy for the user to understand using a generative AI model and prompt sentences, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data. This enables highly accurate detection of pre-disease signs and provision of individually optimized preventive measures that take into account both the user's lifestyle habit data and electronic payment data.

[1027] "User" means an individual who uses the health care system.

[1028] "Lifestyle data" refers to data related to a user's daily health and behavior, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[1029] A "server" is a computer system that stores and analyzes collected data.

[1030] "Electronic payment data" refers to transaction data related to electronic payments made by users, and specifically includes health food purchase history and fitness service usage history.

[1031] "Pre-disease signs" are data patterns or indicators that indicate a user may be currently healthy but may develop illness in the future.

[1032] "Individually optimized preventive measures" are specific suggestions and measures for optimal health management and disease prevention for each individual user, based on the user's lifestyle and electronic payment data.

[1033] A "generative AI model" is an artificial intelligence model that uses natural language generation technology to automatically generate messages for users.

[1034] A "prompt sentence" is an input sentence that instructs the generative AI model to generate a message.

[1035] "Feedback data" refers to information provided by users about their impressions of preventive measures and the results of their implementation.

[1036] A "machine learning model" is an algorithm or data model used to improve the accuracy of analysis and preventative measures suggested based on collected data and feedback.

[1037] The present invention is a system that collects a user's lifestyle data and electronic payment data, analyzes them to detect signs of illness, and proposes individually optimized preventive measures. The following hardware and software are used to implement the present invention.

[1038] Hardware

[1039] Smartphone: Collects data on the user's daily habits (e.g., steps, heart rate, sleep patterns).

[1040] Server: Stores and analyzes collected data.

[1041] software

[1042] Requests library: Communicate with the API to obtain transaction data and feedback.

[1043] Pandas library: Used to read and manage data.

[1044] Scikit-learn library: Used for data normalization and outlier detection (Isolation Forest algorithm).

[1045] Overview of data processing and calculation

[1046] 1. Data collection (device side): Applications installed on smartphones collect lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Transaction data related to electronic payments made by users is also collected.

[1047] 2. Data transmission (from terminal to server): Collected lifestyle data and electronic payment data are sent to the server at regular intervals.

[1048] 3. Data storage and validation (server side): The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data.

[1049] 4. Pre-disease sign detection (server side): Using the validated data, the Isolation Forest algorithm is applied to detect abnormal patterns. Pre-disease signs are found based on step counts, heart rate, and transaction data.

[1050] 5. Generate personalized preventive measures (server-side): Based on the detected signs of illness, preventive measures are generated using generative AI models and prompts. The generated preventive measures are written for the user in natural language.

[1051] 6. Notification (from server to device): The generated preventive measures are notified to the user via push notifications on the smartphone.

[1052] 7. Feedback collection (terminal side): Users enter their thoughts on the proposed preventive measures and the results of their implementation as feedback through the application.

[1053] 8. Feedback analysis and model update (server side): Based on the collected feedback data, the machine learning model is updated and reflected in future preventive measures.

[1054] Specific examples

[1055] When a user uses a smartphone and a fitness tracker, the user's step count data and electronic payment data (e.g., food purchase history or fitness center usage history) are collected and sent to a server. The server compares this data with past data and detects a decrease in exercise volume. As a result, a preventive measure is generated, such as "Your exercise volume has decreased recently. Try walking every day," and a notification is sent to the user's device. After the user has completed the exercise, the user provides feedback, saying, "This amount of exercise was just right," and the server updates the model based on that feedback.

[1056] Prompt Sentence Examples

[1057] An example of a prompt sentence to be input to the generative AI model is, "Create an application that collects user transaction data, detects signs of pre-illness based on health indicators (number of steps, heart rate, sleep patterns), and suggests optimal preventive measures. Use the Isolation Forest algorithm to detect anomalies, and use natural language generation technology to generate a message that is easy for the user to understand. For example, a message such as, 'Your exercise volume has decreased recently. Try walking 30 minutes every day.'"

[1058] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1059] Step 1:

[1060] Data collection (terminal side)

[1061] An application installed on a smartphone uses sensors to collect lifestyle data (number of steps, heart rate, sleep patterns), and electronic payment data. This input data is then periodically organized and saved within the app.

[1062] Step 2:

[1063] Data transmission (from device to server)

[1064] The application periodically transmits the collected lifestyle and electronic payment data to a server. The transmission is via an internet connection and the data is encrypted, ensuring data security. The transmitted data also includes metadata such as collection timestamps and device identifiers.

[1065] Step 3:

[1066] Data storage and validation (server side)

[1067] The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data. This validation uses the Pandas library to shape and clean the data. For example, an anomaly detection algorithm using standard deviation is applied to detect outliers.

[1068] Step 4:

[1069] Detecting signs of illness (server side)

[1070] The server analyzes the validated data and uses the Isolation Forest algorithm to detect signs of pre-disease. Past lifestyle habits and electronic payment data are used as input data. The output is a list of data points containing abnormal patterns. The Scikit-learn library is used for the analysis.

[1071] Step 5:

[1072] Individually optimized preventive measures generation (server side)

[1073] The server generates preventive measures based on the detected signs of illness using a generative AI model and prompts. Natural language generation technology is used to generate messages in a format that is easy for users to understand. The generated messages are in natural language rather than JSON format, making them easy for users to understand.

[1074] Step 6:

[1075] Notification (from server to device)

[1076] The generated preventive measures are notified to the user via the smartphone's push notification function. The server selects notification recipients based on the user's identification information and sends the notification via API. The notification includes specific actions for the preventive measures (e.g., a suggestion to walk daily).

[1077] Step 7:

[1078] Feedback collection (device side)

[1079] Users can enter feedback on the proposed preventive measures through the application. The feedback includes the results of implementing the preventive measures and their impressions. This feedback data is temporarily stored on the device and sent to the server the next time data is transmitted.

[1080] Step 8:

[1081] Feedback analysis and model updates (server side)

[1082] The server analyzes the received feedback data and updates the machine learning model. Past feedback data is also used in the analysis, and adjustments are made to improve the accuracy of the model. For example, the hyperparameters of the anomaly detection algorithm are readjusted based on the feedback results. This allows for more personalized optimization of preventive measures proposed from the next time onwards.

[1083] 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.

[1084] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect pre-disease signs, and proposes individually optimized preventative measures. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it achieves more precise and effective health management. This system continues to achieve effective health management by incorporating user feedback. The specific program processing is explained below in natural language.

[1085] Data collection and transmission

[1086] Device:

[1087] The user's smartphone or wearable device uses sensors to collect daily lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[1088] Receiving and storing data

[1089] server:

[1090] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[1091] Pre-disease sign detection and emotion analysis

[1092] server:

[1093] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. Numerous health indicators are calculated to identify signs of illness. An emotion engine also analyzes user feedback and other emotional data (e.g., text messages and tone of voice) to recognize the user's current emotional state.

[1094] Preventive measures generation and notification

[1095] server:

[1096] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice is generated such as, "You've been getting less exercise lately. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1097] Device:

[1098] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[1099] Gathering feedback and updating the model

[1100] User:

[1101] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[1102] Device:

[1103] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[1104] server:

[1105] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[1106] Specific examples

[1107] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. Furthermore, the emotion engine analyzes the user's text messages for signs of stress. The server generates a preventive measure, suggesting, "Since your physical activity has decreased, try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine." The server then sends a notification to the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server updates the model based on that feedback and emotion data, and provides a more optimized preventive measure next time.

[1108] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and emotional state, and supports continuous health management.

[1109] The processing flow will be explained below.

[1110] Step 1:

[1111] Device:

[1112] The user's smartphone or wearable device uses sensors to collect lifestyle data such as steps taken, heart rate, and sleep patterns. The user can manually enter dietary information through a smartphone application. The device records the data at regular intervals.

[1113] Step 2:

[1114] Device:

[1115] The device sends the lifestyle data collected to the server at preset intervals. If the network connection is unstable, the data will be sent in batches the next time the device connects.

[1116] Step 3:

[1117] server:

[1118] The server receives the data sent from the terminal and stores it in a database. The received data is validated to detect missing data and abnormal values. This data is then corrected.

[1119] Step 4:

[1120] server:

[1121] Based on the saved data, a machine learning model is applied to analyze lifestyle data, using health indicators such as the number of steps taken, heart rate, and sleep patterns, and comparing them with past data to detect signs of illness.

[1122] Step 5:

[1123] server:

[1124] Once a pre-illness sign is detected, the emotion engine analyzes the user's emotional data, which is collected from feedback, text messages, voice data, etc. The emotion engine determines the user's current emotional state.

[1125] Step 6:

[1126] server:

[1127] It generates individually optimized preventive measures based on pre-disease signs and emotional state. It uses natural language generation technology to create messages in a format that is easy for users to understand. For example, it generates specific advice such as, "You've been getting less exercise lately. Try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine."

[1128] Step 7:

[1129] server:

[1130] The generated preventive action message is sent to the user's device as a push notification, along with metadata including the timing and severity of the preventive action.

[1131] Step 8:

[1132] Device:

[1133] The device will display the preventive measures message it receives on the user interface (UI). The user is prompted to acknowledge the notification and take action. The notification is displayed in the form of an alert, so users will not miss it.

[1134] Step 9:

[1135] User:

[1136] Users can then implement the suggested preventative measures and provide feedback about their results through the application, with options such as "helpful" or "difficult," or they can enter detailed thoughts in text format.

[1137] Step 10:

[1138] Device:

[1139] The device sends user feedback data, including the user's emotional state, to the server, which records how the user felt.

[1140] Step 11:

[1141] server:

[1142] The server analyzes the received feedback data and sentiment data, which are then used to update the machine learning model and sentiment engine, allowing the system to further optimize its next preventative action suggestions.

[1143] Step 12:

[1144] server:

[1145] Using updated machine learning models and an emotion engine, it continuously monitors users' lifestyle data and provides individually optimized preventative measures at the appropriate time.

[1146] In this way, the system analyzes the user's lifestyle data and emotional state in real time and continuously suggests optimized preventive measures, supporting effective health management.

[1147] Example 2

[1148] 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."

[1149] In recent years, the importance of health management has increased, with particular attention being paid to early detection and prevention of pre-disease. However, conventional systems have insufficient collection and analysis of users' lifestyle data, making it difficult to provide personalized preventative measures. Furthermore, health management often fails to take into account the user's emotional state, making it difficult to effectively incorporate user feedback. As a result, the preventative measures provided by the system do not match the user's actual needs, resulting in problems with insufficient continuous health management.

[1150] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to a remote server, means for analyzing the collected lifestyle habit data in the remote server to detect signs of abnormal health, means for generating individually optimized preventive measures based on the signs of abnormal health, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data and emotion analysis data. This makes it possible to provide individually optimized preventive measures that comprehensively consider the user's lifestyle habits and emotional state.

[1151] "User" refers to an individual who uses the health care system.

[1152] "Lifestyle data" refers to information about a user's daily activities and conditions, including the number of steps taken, heart rate, sleep patterns, and dietary information.

[1153] "Collection means" refers to the method of collecting user lifestyle data using sensors, applications, etc.

[1154] "Remote Server" refers to a computer system over a network that receives, stores, and analyzes collected data.

[1155] "Validation" refers to the process of checking the accuracy and completeness of collected data.

[1156] "Correction" refers to the process of correcting data that contains deficiencies or anomalies and preparing it in a format that can be analyzed.

[1157] "Signs of abnormal health" refers to indicators or patterns that are recognized as potential health problems based on a user's lifestyle data.

[1158] "Analysis tools" refers to algorithms and software tools used to detect signs of health abnormalities based on collected lifestyle data.

[1159] "Preventive measures" refer to specific actions or measures suggested to users to improve symptoms of an abnormal health condition.

[1160] "Generation means" refers to the method of creating preventive measures based on collected data and analysis results.

[1161] "Notification Method" refers to the communication method used to inform users of the created preventative measures, including push notifications, emails, and SMS.

[1162] "Feedback Data" refers to information provided by users, including their impressions of and results of implementing preventive measures.

[1163] "Emotional Analysis Data" refers to information representing a user's emotional state extracted from user feedback and other data.

[1164] A "machine learning model" refers to an algorithm that learns from collected data to optimize preventive measures and detect new anomalies.

[1165] This invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of health abnormalities, and proposes individually optimized preventative measures. Furthermore, by combining this with emotion analysis, more precise and effective health management is realized. This system incorporates user feedback to continuously provide effective health management.

[1166] The terminal collects lifestyle data using the user's smartphone or wearable device. The devices used include, for example, smartphones and wearable devices. Users can also manually enter dietary information through a smartphone application. This data is automatically sent to a server at regular intervals. Specifically, for example, a smartphone and fitness tracker are used to send data to the server every night at midnight.

[1167] The server receives the data sent from the device and stores it in a dedicated database (e.g., Amazon RDS, DynamoDB). The data is first validated, and if outliers or missing data are detected, they are corrected using a correction algorithm. For example, if there is an outlier in the heart rate data, the data before and after is referenced and corrected using the average value.

[1168] The server applies machine learning models (e.g., TensorFlow, scikit-learn) using programming languages ​​such as Python to the stored data to detect signs of abnormal health. It analyzes whether there are any abnormal patterns based on specific health indicators. It also uses a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) to analyze the emotional state from user feedback and text messages. For example, if a user's text messages contain many of the words "tired" and "stressed," it will recognize this as a state of stress.

[1169] The server generates personalized preventive measures based on the detected health symptoms and emotional state. It uses natural language generation technology (e.g., OpenAI GPT-3) to create a message that is easy for the user to understand. For example, it generates a message that reads, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try practicing deep breathing to relax."

[1170] The generated message is sent to the user's device as a push notification. The user is expected to check the notification through the application and take action. For example, the notification may say, "Your physical activity is decreasing. See details."

[1171] The user can provide feedback on the proposed preventive measures through the application, for example, by inputting their thoughts such as, "This amount of exercise was just right." The device then sends this feedback data to the server.

[1172] The server receives and analyzes feedback and emotion data from users. The machine learning model is updated based on the feedback and emotion data, allowing future preventive measures to be more optimized for each user.

[1173] Prompt Sentence Examples

[1174] "Analyze step count data collected from users' fitness trackers to detect abnormal patterns. Also, determine users' emotional state from their text messages and generate appropriate health precautions."

[1175] A system configured in this way makes it possible to provide individually optimized preventive measures that comprehensively take into account the user's lifestyle habits and emotional state.

[1176] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1177] Step 1:

[1178] Data collection and transmission

[1179] Device:

[1180] A user's smartphone or wearable device collects lifestyle data such as step count, heart rate, and sleep patterns. This data collection is performed using sensors built into the smartphone or the wearable device. The user can also manually input dietary information using a smartphone application. The collected data is automatically sent to a remote server at regular intervals or at the end of the day. Specific input data include step count data, heart rate data, sleep data, and dietary information, and these are output data to the server.

[1181] Step 2:

[1182] Receiving and storing data

[1183] server:

[1184] The data sent from the device is received and stored in a database such as Amazon RDS or DynamoDB. At this time, the data is validated, and if missing data or outliers are detected, they are corrected using an automatic correction algorithm. For example, if the heart rate data contains an outlier, it is corrected using the average value of the heart rate data before and after. The input data is the collected lifestyle habit data, and the output data is the normalized data that has been validated and corrected.

[1185] Step 3:

[1186] Pre-disease sign detection and emotion analysis

[1187] server:

[1188] A machine learning model using Python (e.g., TensorFlow, scikit-learn) is applied to the saved normalized data. This detects abnormal patterns from step count data, heart rate data, etc. In addition, a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) is used to determine the user's emotional state from their text messages and feedback. The specific input data are the normalized lifestyle data and text messages, and the output data are the detected abnormal patterns and emotional state.

[1189] Step 4:

[1190] Preventive measures generation and notification

[1191] server:

[1192] Based on the detected abnormal patterns and emotional state, the system generates individually optimized preventive measures. Natural language generation technology (e.g., OpenAI GPT-3) is used to create messages that are easy for users to understand. The specific input data is the abnormal patterns and emotional state, and the output data is the preventive measure message. For example, a message may be generated that reads, "Your exercise volume has decreased recently. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1193] Device:

[1194] The generated preventive action message is sent to the user's device as a push notification. The user is expected to acknowledge the notification and take action through the application. The input data is the preventive action message, and the output data is the user's action or confirmation.

[1195] Step 5:

[1196] Gathering feedback and updating the model

[1197] User:

[1198] Feedback regarding the proposed preventive measures and the results of their implementation is entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided. The input data is the feedback information, and the output data is the feedback content.

[1199] Device:

[1200] The user's emotional state is also monitored in real time and sent to the server as emotional data as appropriate. A sudden increase in heart rate, for example, is sent as emotional analysis data. The input data is emotional state data such as heart rate data, and the output data is the sent emotional analysis data.

[1201] server:

[1202] It receives and analyzes feedback and sentiment data from users, which updates the machine learning model and further optimizes preventive measures for future visits. The input data is the feedback and sentiment data, and the output data is the updated machine learning model. For example, the model is updated weekly, and new suggestions are generated.

[1203] (Application example 2)

[1204] 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."

[1205] Conventional health management systems mainly monitor health status and suggest preventative measures based on users' lifestyle data, but do not provide precise health management that takes emotional states into account. Furthermore, particularly in security services, there is a lack of mechanisms for monitoring the health status of security guards in real time, who work long hours and in high-stress environments, and providing appropriate rest and support. This can lead to accumulated stress and overwork among security guards, potentially reducing work efficiency and safety.

[1206] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1207] In this invention, the server includes means for analyzing the user's emotional state, means for analyzing collected lifestyle habit data to detect signs of illness, means for combining the emotional state and lifestyle habit data to generate individually optimized preventive measures, and means for displaying the analysis results and preventive measures using a visual display device worn by the user. This makes it possible to monitor the user's health and emotional state in real time and provide appropriate rest and support.

[1208] "Lifestyle data" refers to data related to the user's daily activities, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[1209] "Server" refers to a computer system for receiving, storing, and analyzing collected data.

[1210] "Pre-illness signs" refer to the precursors and symptoms of illness, and are data patterns that indicate changes or abnormalities in health status.

[1211] "Preventive measures" are specific actions and initiatives suggested based on signs of illness, and are measures to maintain health.

[1212] "Feedback data" refers to information provided by users regarding their impressions of proposed preventive measures and the results of their implementation.

[1213] A "machine learning model" is an algorithmic model used to improve the accuracy of data analysis and predictions, learning from data and using it for analysis.

[1214] The "emotion analysis function" is a technology for analyzing a user's emotional state, recognizing emotions based on data such as text messages, tone of voice, and facial expressions.

[1215] A "visual display device" is a device worn by a user that has the function of visually displaying information, and includes, for example, a head-mounted display (HMD).

[1216] "Natural language generation technology" is a technology that allows a computer to generate sentences in natural language to create preventive measures and notifications in a form that is easy for users to understand.

[1217] The present invention is a system for managing health by collecting lifestyle habit data of a user and taking into consideration the user's emotional state. An embodiment of this system will be described in detail below.

[1218] Data collection and transmission

[1219] 1. Device:

[1220] The smartphones and wearable devices that users use daily use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications also allow users to manually input dietary information.

[1221] The collected data is sent to the server at regular intervals using the MQTT protocol.

[1222] Receiving and storing data

[1223] 2. Server:

[1224] The data sent from the device is received and stored in a database such as Amazon DynamoDB. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This organizes the data into one suitable for analysis.

[1225] Pre-disease sign detection and emotion analysis

[1226] 3. Server:

[1227] A machine learning model using TensorFlow is applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to find signs of illness.

[1228] It also uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data to recognize the current emotional state.

[1229] Preventive measures generation and notification

[1230] 4. Server:

[1231] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user, and uses natural language generation technology to create messages in a format that is easy for the user to understand.

[1232] For example, specific advice may be generated such as, "You've been getting less exercise lately. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1233] 5. Terminal:

[1234] The generated message is sent as a push notification to the user's visual display device, such as a head-mounted display (HMD), and the user is expected to check it and take action.

[1235] Gathering feedback and updating the model

[1236] 6. Users:

[1237] Feedback regarding the proposed preventive measures and the results of their implementation can be entered via the HMD. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided.

[1238] 7. Terminal:

[1239] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[1240] 8. Server:

[1241] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[1242] Specific examples and prompts for the generative AI model

[1243] Situation setting:

[1244] A security guard receives the following data from an HMD worn by the guard during nighttime security surveillance:

[1245] Heart rate: 150 BPM

[1246] Steps: 12,000

[1247] Body temperature: 38℃

[1248] Run prompt:

[1249] The text prompt looks like this:

[1250] The following data is received from the HMD worn by the user during the night shift:

[1251] Heart rate: 150 BPM

[1252] Steps: 12,000

[1253] Body temperature: 38℃

[1254] Based on this data, stress signs are detected. A notification message should be generated and sent to the HMD, stating "Your stress level is high, please take a 5-minute break."

[1255] In this way, a system that analyzes a user's daily lifestyle data and emotional state and provides appropriate preventive measures is expected to be very useful in managing health conditions in actual work.

[1256] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1257] Step 1:

[1258] Data collection

[1259] The smartphone or wearable device worn by the user uses sensors to collect lifestyle data (e.g., number of steps, heart rate, sleep patterns, etc.). During this process, the input data is biometric data from various sensors, and the output is the collected raw data. The device prepares to send this data to a server at regular intervals.

[1260] Step 2:

[1261] Data transmission

[1262] The device sends the collected lifestyle habit data to a server using the MQTT protocol. The input data is the collected lifestyle habit data, and the output is the data sent to the server. During data transfer, the device monitors whether the communication is stable.

[1263] Step 3:

[1264] Data reception and storage

[1265] The server receives the data sent from the device and stores it in a database such as Amazon DynamoDB. The input data is the lifestyle habit data received from the device, and the output is the data stored in the database. The received data is first checked for format consistency and missing parts, and if abnormal or missing values ​​are detected, correction procedures are carried out.

[1266] Step 4:

[1267] Detecting signs of pre-disease

[1268] The server applies machine learning models to the stored data using TensorFlow to detect signs of pre-disease. The input data is lifestyle data after validation, and the output is information on abnormal patterns and signs of pre-disease. The data is analyzed through the machine learning model, and any abnormal patterns are recorded as signs.

[1269] Step 5:

[1270] Emotion analysis

[1271] The server uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data (e.g., tone of voice and text messages) to recognize the user's emotional state. The input data is the collected emotional data, and the output is the emotional state information resulting from the analysis. The emotion engine analyzes text and voice data to detect the user's current emotional state.

[1272] Step 6:

[1273] Generate preventative measures

[1274] The server uses natural language generation technology to generate optimal preventive measures for each individual user based on their pre-illness signs and emotional state. The input data is information about pre-illness signs and emotional state, and the output is a generated preventive measure message. For example, the generated advice might be, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1275] Step 7:

[1276] Preventive Measures Notice

[1277] The device displays the preventive measures message sent from the server as a push notification on a visual display device (e.g., a head-mounted display). The input data is the preventive measures message sent from the server, and the output is the notification displayed on the user's visual display device. The user is expected to confirm and implement the preventive measures through this.

[1278] Step 8:

[1279] Feedback collection

[1280] The user inputs feedback on the proposed preventive measures and the results of their implementation via a visual display device. The input data is the feedback information from the user, and the output is the feedback sent to the server. The user provides specific feedback, and the results are reflected in the next preventive measures.

[1281] Step 9:

[1282] Model Update

[1283] The server receives and analyzes user feedback and emotion data. The input data is the user feedback and emotion data, and the output is an updated machine learning model. This updates the machine learning model to reflect the next preventive action suggestion, allowing the system to continuously make suggestions adapted to the user's behavior and habits.

[1284] 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.

[1285] 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.

[1286] 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.

[1287] [Fourth embodiment]

[1288] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1289] 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.

[1290] 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).

[1291] 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.

[1292] 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.

[1293] 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).

[1294] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1295] 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.

[1296] 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.

[1297] 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.

[1298] 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.

[1299] 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.

[1300] 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."

[1301] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of illness, and proposes individually optimized preventative measures. This system realizes effective health management by incorporating feedback into the data. Specific program processing is explained below in natural language.

[1302] Data collection and transmission

[1303] Terminal

[1304] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[1305] Receiving and storing data

[1306] server

[1307] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[1308] Detecting signs of pre-disease

[1309] server

[1310] Machine learning models are applied to the stored data to detect abnormal patterns in step counts, heart rate, etc. A number of health indicators are calculated to detect signs of illness, such as a significant decrease in recent step counts compared to historical averages or an increase in heart rate variability.

[1311] Preventive measures generation and notification

[1312] server

[1313] Based on the detected signs of illness, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice such as "Your exercise volume has decreased recently. Try walking 30 minutes every day" is generated.

[1314] Terminal

[1315] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[1316] Gathering feedback and updating the model

[1317] User

[1318] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[1319] server

[1320] It receives and analyzes user feedback, which is then reflected in the next preventative measures suggested to the machine learning model, allowing the system to continually adapt its suggestions to the user's behavior and habits.

[1321] Specific examples

[1322] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. The server generates a preventive measure, suggesting, "Your physical activity has decreased, so try walking for 30 minutes on the weekend." and notifies the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server uses that feedback to update the model and provide a more optimized preventive measure next time.

[1323] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and supports continuous health management.

[1324] The processing flow will be explained below.

[1325] Step 1:

[1326] Device:

[1327] Smartphones and wearable devices use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications provide users with the option to manually input dietary information.

[1328] Step 2:

[1329] Device:

[1330] The collected lifestyle data is sent to the server at regular intervals (e.g., every hour or every day). If a network connection is unavailable, the data is sent in batches the next time a connection is made.

[1331] Step 3:

[1332] server:

[1333] It receives JSON format data sent from the device, records the received data in a log, and saves the data in a database for subsequent processing.

[1334] Step 4:

[1335] server:

[1336] Data validation is performed to detect missing data and outliers. Data correction is performed as necessary to ensure data quality. The corrected data is converted into a format for analysis.

[1337] Step 5:

[1338] server:

[1339] It uses machine learning models to analyze lifestyle data and detect signs of pre-disease, including abnormal patterns such as a sudden decrease in step count or increased heart rate variability.

[1340] Step 6:

[1341] server:

[1342] Based on the detected signs of illness, the system generates personalized and optimized preventive measures, and uses natural language generation (NLG) technology to create messages in a format that is easy for users to understand.

[1343] Step 7:

[1344] server:

[1345] The generated preventive action message is sent to the user's device in the form of a push notification, along with metadata (such as the importance of the preventive action and when it should be taken).

[1346] Step 8:

[1347] Device:

[1348] The received message will be displayed in the user interface, and the user will be prompted to review and take action on preventative measures through the application.

[1349] Step 9:

[1350] User:

[1351] Enter your feedback on the suggested preventative measures. The application asks a simple question (e.g., "Did this suggestion help you?") and collects your response.

[1352] Step 10:

[1353] Device:

[1354] User feedback data is sent to the server, including the usefulness of the proposal and the difficulty of its implementation.

[1355] Step 11:

[1356] server:

[1357] The received feedback data is analyzed and the machine learning model is updated, which makes the next preventative measures recommendations more accurate.

[1358] Step 12:

[1359] server:

[1360] It will continue to operate updated machine learning models and pre-disease sign detection algorithms, which will continuously monitor user data and provide individually optimized preventative measures in a timely manner.

[1361] Example 1

[1362] 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."

[1363] Conventional health management systems have struggled to effectively collect and analyze a user's lifestyle data and propose individually optimized preventive measures. Furthermore, it has been difficult to effectively collect feedback on the proposed preventive measures and reflect it in the system, resulting in insufficient continuous health management. The present invention aims to solve these problems by providing a system that achieves effective health management by performing detailed analysis and proposing preventive measures based on a user's lifestyle data and updating the model based on the feedback.

[1364] 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.

[1365] In this invention, the server includes a means for collecting data related to the user's health, a means for transmitting the collected health data to the communication device, and a means for analyzing the collected health data and detecting signs of pre-disease in the communication device. This makes it possible to effectively collect and analyze the user's lifestyle data, generate individually optimized preventive measures, and update the machine learning model based on the feedback.

[1366] "User" means an individual who utilizes the system to manage their health status and provide feedback.

[1367] "Health data" refers to information about a user's health and lifestyle, such as the number of steps taken, heart rate, sleep patterns, and dietary information.

[1368] "Means of collection" refers to the functions and processes that collect user health data using devices such as smartphones and wearable devices.

[1369] "Communication device" refers to a server or computer system that processes, stores, analyzes, and notifies data received from a user's device.

[1370] "Means of analysis" refers to the functions and processes that use machine learning models and statistical analysis techniques to evaluate collected data and detect signs of pre-disease.

[1371] "Pre-illness signs" are early symptoms or signs of abnormalities that appear before the user's health condition deteriorates.

[1372] "Individually optimized preventive measures" refer to preventive measures and advice that are optimal for each user, proposed based on the user's personal health data and analysis results.

[1373] "Generation means" refers to the function or process that uses natural language generation techniques or algorithms to generate preventative measures to notify users.

[1374] "Means of notification" refers to the function or process that sends the generated preventative measures to the user's device in the form of a push notification or alert.

[1375] "Feedback data" refers to information entered into the system by users regarding their impressions of proposed preventive measures and the results of their implementation.

[1376] "Means for updating machine learning models" refers to the functions and processes that optimize and improve the prevention generation algorithms and models based on feedback data collected from users.

[1377] MODE FOR CARRYING OUT THE INVENTION

[1378] This invention is a system that collects and analyzes lifestyle data from users to detect pre-disease symptoms and proposes individually optimized preventive measures. By incorporating feedback into the system, this system achieves effective health management.

[1379] Data collection and transmission

[1380] Device:

[1381] The user's smartphone or wearable device uses sensors to collect lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[1382] As a specific example, if a user uses a smartphone and a wearable device, the device records data on the number of steps taken and heart rate in real time, and at night the smartphone automatically sends the data for the day to a server.

[1383] Receiving and storing data

[1384] server:

[1385] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected.

[1386] As a concrete example, we use a Python script on the server to format the data, run an outlier detection algorithm on it, and then store the formatted data in a database.

[1387] Detecting signs of pre-disease

[1388] server:

[1389] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to detect signs of illness.

[1390] As a concrete example, the server analyzes step count data from the past month using a machine learning library (e.g., scikit-learn) and detects that the average number of steps has decreased significantly in the last week.

[1391] Preventive measures generation and notification

[1392] server:

[1393] Based on the detected pre-disease signs, the system generates optimal preventive measures for each individual user, using natural language generation technology to create messages in a format that is easy for users to understand.

[1394] As a concrete example, a generative AI model is used to generate a message such as, "Your exercise volume has decreased recently. Try walking 30 minutes every day."

[1395] Device:

[1396] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[1397] Gathering feedback and updating the model

[1398] User:

[1399] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[1400] server:

[1401] It receives and analyzes user feedback, which is then used to update the machine learning model to reflect the feedback in the next preventative action recommendations.

[1402] As a specific example, when the server receives feedback data, it evaluates the feedback with analytical algorithms and adjusts the weights and parameters of the model.

[1403] Prompt Sentence Examples

[1404] "Your daily step count has decreased significantly compared to average. To increase your exercise, try walking 30 minutes every day. Even walking three times a week will be effective, so try to continue within your limits."

[1405] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle data and supports continuous health management.

[1406] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1407] Specific processing steps of the program

[1408] Step 1:

[1409] The device collects health data (such as the number of steps taken, heart rate, sleep patterns, and dietary information) from the user using a dedicated application or wearable device. Specifically, the device uses sensors to record data in real time, and the smartphone application allows the user to manually enter dietary information.

[1410] Input: User's health data

[1411] Output: A set of collected health data

[1412] Step 2:

[1413] The device sends the collected health data to a server at regular intervals via an internet connection. The specific data transmission operation involves the device automatically uploading data to the server at night or at a set time.

[1414] Input: A set of collected health data

[1415] Output: Data sent to the server

[1416] Step 3:

[1417] The server receives the health data sent from the device and stores it in a dedicated database. The specific operations of receiving and storing data involve the server first validating the data (e.g., detecting missing data and outliers), correcting it into an appropriate format, and then storing it in the database.

[1418] Input: Submitted health data

[1419] Output: Data stored in the database

[1420] Step 4:

[1421] The server applies machine learning models to the stored health data to detect signs of illness. This process involves using algorithms to calculate health indicators (e.g., steps taken, heart rate variability) and identify abnormal patterns. Specific operations include running analysis scripts using Python libraries.

[1422] Input: Data stored in a database

[1423] Output: Detected signs of pre-disease

[1424] Step 5:

[1425] The server generates individually optimized preventive measures based on the detected pre-disease signs. This generation utilizes a generative AI model and natural language generation technology. Specifically, the generative AI model generates a message that is easy for the user to understand.

[1426] Input: Detected signs of illness

[1427] Output: Generated preventative action message

[1428] Step 6:

[1429] The device notifies the user of the preventive measures message sent from the server. This can be done via push notification or in-app messaging. Specifically, the device receives the notification and displays details when the user opens the app.

[1430] Input: Generated precaution message

[1431] Output: Preventive measures communicated to the user

[1432] Step 7:

[1433] The user inputs feedback on the proposed preventive measures through the application. Specifically, a feedback form is displayed in the application for inputting impressions and effects.

[1434] Input: User feedback on preventative measures

[1435] Output: Collected feedback data

[1436] Step 8:

[1437] The server receives and analyzes feedback data from users. The specific operation of the feedback analysis is to evaluate their impressions and implementation results and update the machine learning model to reflect these in the next proposal.

[1438] Input: Collected feedback data

[1439] Output: Updated machine learning model

[1440] In this way, by explaining in detail the specific input, data processing, data calculation, and output that take place at each step, the processing flow of the entire system can be clearly understood.

[1441] (Application example 1)

[1442] 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."

[1443] Conventional health management systems are limited to detecting pre-disease signs and proposing preventive measures based solely on the user's lifestyle data, and do not achieve individual optimization that fully considers individual lifestyle patterns and economic activities (e.g., dietary content and use of fitness services).Therefore, there is a need for highly accurate detection of pre-disease signs and proposing preventive measures by including activity data that is closely related to the user's health condition.

[1444] 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.

[1445] In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to the server, means for collecting electronic payment data, means for analyzing the collected lifestyle habit data and electronic payment data in the server to detect pre-disease signs, means for generating individually optimized preventive measures based on the pre-disease signs, means for generating the preventive measures in natural language that is easy for the user to understand using a generative AI model and prompt sentences, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data. This enables highly accurate detection of pre-disease signs and provision of individually optimized preventive measures that take into account both the user's lifestyle habit data and electronic payment data.

[1446] "User" means an individual who uses the health care system.

[1447] "Lifestyle data" refers to data related to a user's daily health and behavior, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[1448] A "server" is a computer system that stores and analyzes collected data.

[1449] "Electronic payment data" refers to transaction data related to electronic payments made by users, and specifically includes health food purchase history and fitness service usage history.

[1450] "Pre-disease signs" are data patterns or indicators that indicate a user may be currently healthy but may develop illness in the future.

[1451] "Individually optimized preventive measures" are specific suggestions and measures for optimal health management and disease prevention for each individual user, based on the user's lifestyle and electronic payment data.

[1452] A "generative AI model" is an artificial intelligence model that uses natural language generation technology to automatically generate messages for users.

[1453] A "prompt sentence" is an input sentence that instructs the generative AI model to generate a message.

[1454] "Feedback data" refers to information provided by users about their impressions of preventive measures and the results of their implementation.

[1455] A "machine learning model" is an algorithm or data model used to improve the accuracy of analysis and preventative measures suggested based on collected data and feedback.

[1456] The present invention is a system that collects a user's lifestyle data and electronic payment data, analyzes them to detect signs of illness, and proposes individually optimized preventive measures. The following hardware and software are used to implement the present invention.

[1457] Hardware

[1458] Smartphone: Collects data on the user's daily habits (e.g., steps, heart rate, sleep patterns).

[1459] Server: Stores and analyzes collected data.

[1460] software

[1461] Requests library: Communicate with the API to obtain transaction data and feedback.

[1462] Pandas library: Used to read and manage data.

[1463] Scikit-learn library: Used for data normalization and outlier detection (Isolation Forest algorithm).

[1464] Overview of data processing and calculation

[1465] 1. Data collection (device side): Applications installed on smartphones collect lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Transaction data related to electronic payments made by users is also collected.

[1466] 2. Data transmission (from terminal to server): Collected lifestyle data and electronic payment data are sent to the server at regular intervals.

[1467] 3. Data storage and validation (server side): The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data.

[1468] 4. Pre-disease sign detection (server side): Using the validated data, the Isolation Forest algorithm is applied to detect abnormal patterns. Pre-disease signs are found based on step counts, heart rate, and transaction data.

[1469] 5. Generate personalized preventive measures (server-side): Based on the detected signs of illness, preventive measures are generated using generative AI models and prompts. The generated preventive measures are written for the user in natural language.

[1470] 6. Notification (from server to device): The generated preventive measures are notified to the user via push notifications on the smartphone.

[1471] 7. Feedback collection (terminal side): Users enter their thoughts on the proposed preventive measures and the results of their implementation as feedback through the application.

[1472] 8. Feedback analysis and model update (server side): Based on the collected feedback data, the machine learning model is updated and reflected in future preventive measures.

[1473] Specific examples

[1474] When a user uses a smartphone and a fitness tracker, the user's step count data and electronic payment data (e.g., food purchase history or fitness center usage history) are collected and sent to a server. The server compares this data with past data and detects a decrease in exercise volume. As a result, a preventive measure is generated, such as "Your exercise volume has decreased recently. Try walking every day," and a notification is sent to the user's device. After the user has completed the exercise, the user provides feedback, saying, "This amount of exercise was just right," and the server updates the model based on that feedback.

[1475] Prompt Sentence Examples

[1476] An example of a prompt sentence to be input to the generative AI model is, "Create an application that collects user transaction data, detects signs of pre-illness based on health indicators (number of steps, heart rate, sleep patterns), and suggests optimal preventive measures. Use the Isolation Forest algorithm to detect anomalies, and use natural language generation technology to generate a message that is easy for the user to understand. For example, a message such as, 'Your exercise volume has decreased recently. Try walking 30 minutes every day.'"

[1477] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1478] Step 1:

[1479] Data collection (terminal side)

[1480] An application installed on a smartphone uses sensors to collect lifestyle data (number of steps, heart rate, sleep patterns), and electronic payment data. This input data is then periodically organized and saved within the app.

[1481] Step 2:

[1482] Data transmission (from device to server)

[1483] The application periodically transmits the collected lifestyle and electronic payment data to a server. The transmission is via an internet connection and the data is encrypted, ensuring data security. The transmitted data also includes metadata such as collection timestamps and device identifiers.

[1484] Step 3:

[1485] Data storage and validation (server side)

[1486] The server stores the received data in a database. The stored data is first validated to detect and correct outliers and missing data. This validation uses the Pandas library to shape and clean the data. For example, an anomaly detection algorithm using standard deviation is applied to detect outliers.

[1487] Step 4:

[1488] Detecting signs of illness (server side)

[1489] The server analyzes the validated data and uses the Isolation Forest algorithm to detect signs of pre-disease. Past lifestyle habits and electronic payment data are used as input data. The output is a list of data points containing abnormal patterns. The Scikit-learn library is used for the analysis.

[1490] Step 5:

[1491] Individually optimized preventive measures generation (server side)

[1492] The server generates preventive measures based on the detected signs of illness using a generative AI model and prompts. Natural language generation technology is used to generate messages in a format that is easy for users to understand. The generated messages are in natural language rather than JSON format, making them easy for users to understand.

[1493] Step 6:

[1494] Notification (from server to device)

[1495] The generated preventive measures are notified to the user via the smartphone's push notification function. The server selects notification recipients based on the user's identification information and sends the notification via API. The notification includes specific actions for the preventive measures (e.g., a suggestion to walk daily).

[1496] Step 7:

[1497] Feedback collection (device side)

[1498] Users can enter feedback on the proposed preventive measures through the application. The feedback includes the results of implementing the preventive measures and their impressions. This feedback data is temporarily stored on the device and sent to the server the next time data is transmitted.

[1499] Step 8:

[1500] Feedback analysis and model updates (server side)

[1501] The server analyzes the received feedback data and updates the machine learning model. Past feedback data is also used in the analysis, and adjustments are made to improve the accuracy of the model. For example, the hyperparameters of the anomaly detection algorithm are readjusted based on the feedback results. This allows for more personalized optimization of preventive measures proposed from the next time onwards.

[1502] 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.

[1503] The present invention is a system that collects a user's lifestyle data, analyzes that data to detect pre-disease signs, and proposes individually optimized preventative measures. Furthermore, by combining it with an emotion engine that recognizes the user's emotions, it achieves more precise and effective health management. This system continues to achieve effective health management by incorporating user feedback. The specific program processing is explained below in natural language.

[1504] Data collection and transmission

[1505] Device:

[1506] The user's smartphone or wearable device uses sensors to collect daily lifestyle data such as the number of steps taken, heart rate, and sleep patterns. The smartphone application also allows the user to manually enter dietary information. This data is automatically sent to a server at the end of each day or at regular intervals.

[1507] Receiving and storing data

[1508] server:

[1509] The system receives data sent from the device and stores it in a dedicated database. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This allows the data to be organized in a format suitable for analysis.

[1510] Pre-disease sign detection and emotion analysis

[1511] server:

[1512] Machine learning models are applied to the stored data to detect abnormal patterns in steps, heart rate, etc. Numerous health indicators are calculated to identify signs of illness. An emotion engine also analyzes user feedback and other emotional data (e.g., text messages and tone of voice) to recognize the user's current emotional state.

[1513] Preventive measures generation and notification

[1514] server:

[1515] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user. Natural language generation technology is used to create messages that are easy for users to understand. For example, specific advice is generated such as, "You've been getting less exercise lately. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1516] Device:

[1517] The generated message is sent to the user's device as a push notification, and the user is expected to check it and take action through the application.

[1518] Gathering feedback and updating the model

[1519] User:

[1520] Feedback about the proposed preventive measures and the results of their implementation can be entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise."

[1521] Device:

[1522] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[1523] server:

[1524] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[1525] Specific examples

[1526] Suppose a user uses a smartphone and a fitness tracker. The user's step count data is collected and sent to a server. The server compares it with past data and detects that the recent step count is below average. Furthermore, the emotion engine analyzes the user's text messages for signs of stress. The server generates a preventive measure, suggesting, "Since your physical activity has decreased, try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine." The server then sends a notification to the user's device. After the user completes this walk and provides feedback on whether it went well or poorly, the server updates the model based on that feedback and emotion data, and provides a more optimized preventive measure next time.

[1527] In this way, the present invention is a system that proposes individually optimized preventive measures based on the user's lifestyle habits and emotional state, and supports continuous health management.

[1528] The processing flow will be explained below.

[1529] Step 1:

[1530] Device:

[1531] The user's smartphone or wearable device uses sensors to collect lifestyle data such as steps taken, heart rate, and sleep patterns. The user can manually enter dietary information through a smartphone application. The device records the data at regular intervals.

[1532] Step 2:

[1533] Device:

[1534] The device sends the lifestyle data collected to the server at preset intervals. If the network connection is unstable, the data will be sent in batches the next time the device connects.

[1535] Step 3:

[1536] server:

[1537] The server receives the data sent from the terminal and stores it in a database. The received data is validated to detect missing data and abnormal values. This data is then corrected.

[1538] Step 4:

[1539] server:

[1540] Based on the saved data, a machine learning model is applied to analyze lifestyle data, using health indicators such as the number of steps taken, heart rate, and sleep patterns, and comparing them with past data to detect signs of illness.

[1541] Step 5:

[1542] server:

[1543] Once a pre-illness sign is detected, the emotion engine analyzes the user's emotional data, which is collected from feedback, text messages, voice data, etc. The emotion engine determines the user's current emotional state.

[1544] Step 6:

[1545] server:

[1546] It generates individually optimized preventive measures based on pre-disease signs and emotional state. It uses natural language generation technology to create messages in a format that is easy for users to understand. For example, it generates specific advice such as, "You've been getting less exercise lately. Try walking for 30 minutes on the weekend. Also, try incorporating deep breathing into your relaxation routine."

[1547] Step 7:

[1548] server:

[1549] The generated preventive action message is sent to the user's device as a push notification, along with metadata including the timing and severity of the preventive action.

[1550] Step 8:

[1551] Device:

[1552] The device will display the preventive measures message it receives on the user interface (UI). The user is prompted to acknowledge the notification and take action. The notification is displayed in the form of an alert, so users will not miss it.

[1553] Step 9:

[1554] User:

[1555] Users can then implement the suggested preventative measures and provide feedback about their results through the application, with options such as "helpful" or "difficult," or they can enter detailed thoughts in text format.

[1556] Step 10:

[1557] Device:

[1558] The device sends user feedback data, including the user's emotional state, to the server, which records how the user felt.

[1559] Step 11:

[1560] server:

[1561] The server analyzes the received feedback data and sentiment data, which are then used to update the machine learning model and sentiment engine, allowing the system to further optimize its next preventative action suggestions.

[1562] Step 12:

[1563] server:

[1564] Using updated machine learning models and an emotion engine, it continuously monitors users' lifestyle data and provides individually optimized preventative measures at the appropriate time.

[1565] In this way, the system analyzes the user's lifestyle data and emotional state in real time and continuously suggests optimized preventive measures, supporting effective health management.

[1566] Example 2

[1567] 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."

[1568] In recent years, the importance of health management has increased, with particular attention being paid to early detection and prevention of pre-disease. However, conventional systems have insufficient collection and analysis of users' lifestyle data, making it difficult to provide personalized preventative measures. Furthermore, health management often fails to take into account the user's emotional state, making it difficult to effectively incorporate user feedback. As a result, the preventative measures provided by the system do not match the user's actual needs, resulting in problems with insufficient continuous health management.

[1569] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting lifestyle habit data of a user, means for transmitting the collected lifestyle habit data to a remote server, means for analyzing the collected lifestyle habit data in the remote server to detect signs of abnormal health, means for generating individually optimized preventive measures based on the signs of abnormal health, means for notifying the user of the generated preventive measures, means for collecting feedback data from the user, and means for updating the machine learning model based on the collected feedback data and emotion analysis data. This makes it possible to provide individually optimized preventive measures that comprehensively consider the user's lifestyle habits and emotional state.

[1570] "User" refers to an individual who uses the health care system.

[1571] "Lifestyle data" refers to information about a user's daily activities and conditions, including the number of steps taken, heart rate, sleep patterns, and dietary information.

[1572] "Collection means" refers to the method of collecting user lifestyle data using sensors, applications, etc.

[1573] "Remote Server" refers to a computer system over a network that receives, stores, and analyzes collected data.

[1574] "Validation" refers to the process of checking the accuracy and completeness of collected data.

[1575] "Correction" refers to the process of correcting data that contains deficiencies or anomalies and preparing it in a format that can be analyzed.

[1576] "Signs of abnormal health" refers to indicators or patterns that are recognized as potential health problems based on a user's lifestyle data.

[1577] "Analysis tools" refers to algorithms and software tools used to detect signs of health abnormalities based on collected lifestyle data.

[1578] "Preventive measures" refer to specific actions or measures suggested to users to improve symptoms of an abnormal health condition.

[1579] "Generation means" refers to the method of creating preventive measures based on collected data and analysis results.

[1580] "Notification Method" refers to the communication method used to inform users of the created preventative measures, including push notifications, emails, and SMS.

[1581] "Feedback Data" refers to information provided by users, including their impressions of and results of implementing preventive measures.

[1582] "Emotional Analysis Data" refers to information representing a user's emotional state extracted from user feedback and other data.

[1583] A "machine learning model" refers to an algorithm that learns from collected data to optimize preventive measures and detect new anomalies.

[1584] This invention is a system that collects a user's lifestyle data, analyzes that data to detect signs of health abnormalities, and proposes individually optimized preventative measures. Furthermore, by combining this with emotion analysis, more precise and effective health management is realized. This system incorporates user feedback to continuously provide effective health management.

[1585] The terminal collects lifestyle data using the user's smartphone or wearable device. The devices used include, for example, smartphones and wearable devices. Users can also manually enter dietary information through a smartphone application. This data is automatically sent to a server at regular intervals. Specifically, for example, a smartphone and fitness tracker are used to send data to the server every night at midnight.

[1586] The server receives the data sent from the device and stores it in a dedicated database (e.g., Amazon RDS, DynamoDB). The data is first validated, and if outliers or missing data are detected, they are corrected using a correction algorithm. For example, if there is an outlier in the heart rate data, the data before and after is referenced and corrected using the average value.

[1587] The server applies machine learning models (e.g., TensorFlow, scikit-learn) using programming languages ​​such as Python to the stored data to detect signs of abnormal health. It analyzes whether there are any abnormal patterns based on specific health indicators. It also uses a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) to analyze the emotional state from user feedback and text messages. For example, if a user's text messages contain many of the words "tired" and "stressed," it will recognize this as a state of stress.

[1588] The server generates personalized preventive measures based on the detected health symptoms and emotional state. It uses natural language generation technology (e.g., OpenAI GPT-3) to create a message that is easy for the user to understand. For example, it generates a message that reads, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try practicing deep breathing to relax."

[1589] The generated message is sent to the user's device as a push notification. The user is expected to check the notification through the application and take action. For example, the notification may say, "Your physical activity is decreasing. See details."

[1590] The user can provide feedback on the proposed preventive measures through the application, for example, by inputting their thoughts such as, "This amount of exercise was just right." The device then sends this feedback data to the server.

[1591] The server receives and analyzes feedback and emotion data from users. The machine learning model is updated based on the feedback and emotion data, allowing future preventive measures to be more optimized for each user.

[1592] Prompt Sentence Examples

[1593] "Analyze step count data collected from users' fitness trackers to detect abnormal patterns. Also, determine users' emotional state from their text messages and generate appropriate health precautions."

[1594] A system configured in this way makes it possible to provide individually optimized preventive measures that comprehensively take into account the user's lifestyle habits and emotional state.

[1595] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1596] Step 1:

[1597] Data collection and transmission

[1598] Device:

[1599] A user's smartphone or wearable device collects lifestyle data such as step count, heart rate, and sleep patterns. This data collection is performed using sensors built into the smartphone or the wearable device. The user can also manually input dietary information using a smartphone application. The collected data is automatically sent to a remote server at regular intervals or at the end of the day. Specific input data include step count data, heart rate data, sleep data, and dietary information, and these are output data to the server.

[1600] Step 2:

[1601] Receiving and storing data

[1602] server:

[1603] The data sent from the device is received and stored in a database such as Amazon RDS or DynamoDB. At this time, the data is validated, and if missing data or outliers are detected, they are corrected using an automatic correction algorithm. For example, if the heart rate data contains an outlier, it is corrected using the average value of the heart rate data before and after. The input data is the collected lifestyle habit data, and the output data is the normalized data that has been validated and corrected.

[1604] Step 3:

[1605] Pre-disease sign detection and emotion analysis

[1606] server:

[1607] A machine learning model using Python (e.g., TensorFlow, scikit-learn) is applied to the saved normalized data. This detects abnormal patterns from step count data, heart rate data, etc. In addition, a sentiment analysis engine (e.g., IBM Watson's Natural Language Understanding API) is used to determine the user's emotional state from their text messages and feedback. The specific input data are the normalized lifestyle data and text messages, and the output data are the detected abnormal patterns and emotional state.

[1608] Step 4:

[1609] Preventive measures generation and notification

[1610] server:

[1611] Based on the detected abnormal patterns and emotional state, the system generates individually optimized preventive measures. Natural language generation technology (e.g., OpenAI GPT-3) is used to create messages that are easy for users to understand. The specific input data is the abnormal patterns and emotional state, and the output data is the preventive measure message. For example, a message may be generated that reads, "Your exercise volume has decreased recently. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1612] Device:

[1613] The generated preventive action message is sent to the user's device as a push notification. The user is expected to acknowledge the notification and take action through the application. The input data is the preventive action message, and the output data is the user's action or confirmation.

[1614] Step 5:

[1615] Gathering feedback and updating the model

[1616] User:

[1617] Feedback regarding the proposed preventive measures and the results of their implementation is entered through the application. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided. The input data is the feedback information, and the output data is the feedback content.

[1618] Device:

[1619] The user's emotional state is also monitored in real time and sent to the server as emotional data as appropriate. A sudden increase in heart rate, for example, is sent as emotional analysis data. The input data is emotional state data such as heart rate data, and the output data is the sent emotional analysis data.

[1620] server:

[1621] It receives and analyzes feedback and sentiment data from users, which updates the machine learning model and further optimizes preventive measures for future visits. The input data is the feedback and sentiment data, and the output data is the updated machine learning model. For example, the model is updated weekly, and new suggestions are generated.

[1622] (Application example 2)

[1623] 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."

[1624] Conventional health management systems mainly monitor health status and suggest preventative measures based on users' lifestyle data, but do not provide precise health management that takes emotional states into account. Furthermore, particularly in security services, there is a lack of mechanisms for monitoring the health status of security guards in real time, who work long hours and in high-stress environments, and providing appropriate rest and support. This can lead to accumulated stress and overwork among security guards, potentially reducing work efficiency and safety.

[1625] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1626] In this invention, the server includes means for analyzing the user's emotional state, means for analyzing collected lifestyle habit data to detect signs of illness, means for combining the emotional state and lifestyle habit data to generate individually optimized preventive measures, and means for displaying the analysis results and preventive measures using a visual display device worn by the user. This makes it possible to monitor the user's health and emotional state in real time and provide appropriate rest and support.

[1627] "Lifestyle data" refers to data related to the user's daily activities, including, for example, the number of steps taken, heart rate, sleep patterns, and dietary information.

[1628] "Server" refers to a computer system for receiving, storing, and analyzing collected data.

[1629] "Pre-illness signs" refer to the precursors and symptoms of illness, and are data patterns that indicate changes or abnormalities in health status.

[1630] "Preventive measures" are specific actions and initiatives suggested based on signs of illness, and are measures to maintain health.

[1631] "Feedback data" refers to information provided by users regarding their impressions of proposed preventive measures and the results of their implementation.

[1632] A "machine learning model" is an algorithmic model used to improve the accuracy of data analysis and predictions, learning from data and using it for analysis.

[1633] The "emotion analysis function" is a technology for analyzing a user's emotional state, recognizing emotions based on data such as text messages, tone of voice, and facial expressions.

[1634] A "visual display device" is a device worn by a user that has the function of visually displaying information, and includes, for example, a head-mounted display (HMD).

[1635] "Natural language generation technology" is a technology that allows a computer to generate sentences in natural language to create preventive measures and notifications in a form that is easy for users to understand.

[1636] The present invention is a system for managing health by collecting lifestyle habit data of a user and taking into consideration the user's emotional state. An embodiment of this system will be described in detail below.

[1637] Data collection and transmission

[1638] 1. Device:

[1639] The smartphones and wearable devices that users use daily use sensors to collect daily lifestyle data such as the number of steps taken, heart rate, sleep patterns, etc. Smartphone applications also allow users to manually input dietary information.

[1640] The collected data is sent to the server at regular intervals using the MQTT protocol.

[1641] Receiving and storing data

[1642] 2. Server:

[1643] The data sent from the device is received and stored in a database such as Amazon DynamoDB. The received data is first validated, and any missing data or abnormal values ​​detected are corrected. This organizes the data into one suitable for analysis.

[1644] Pre-disease sign detection and emotion analysis

[1645] 3. Server:

[1646] A machine learning model using TensorFlow is applied to the stored data to detect abnormal patterns in steps, heart rate, etc. A number of health indicators are calculated to find signs of illness.

[1647] It also uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data to recognize the current emotional state.

[1648] Preventive measures generation and notification

[1649] 4. Server:

[1650] Based on the detected pre-disease signs and emotional state, the system generates optimal preventive measures for each individual user, and uses natural language generation technology to create messages in a format that is easy for the user to understand.

[1651] For example, specific advice may be generated such as, "You've been getting less exercise lately. Try walking for 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1652] 5. Terminal:

[1653] The generated message is sent as a push notification to the user's visual display device, such as a head-mounted display (HMD), and the user is expected to check it and take action.

[1654] Gathering feedback and updating the model

[1655] 6. Users:

[1656] Feedback regarding the proposed preventive measures and the results of their implementation can be entered via the HMD. For example, feedback such as "This amount of exercise was just right" or "Please suggest an easier exercise" is provided.

[1657] 7. Terminal:

[1658] The user's emotional state is also monitored in real time and transmitted to the server as emotional data as appropriate.

[1659] 8. Server:

[1660] The system receives and analyzes user feedback and emotional data, which is then reflected in the machine learning model to improve the next preventative measures. This allows the system to continuously adapt its recommendations to the user's behavior and habits.

[1661] Specific examples and prompts for the generative AI model

[1662] Situation setting:

[1663] A security guard receives the following data from an HMD worn by the guard during nighttime security surveillance:

[1664] Heart rate: 150 BPM

[1665] Steps: 12,000

[1666] Body temperature: 38℃

[1667] Run prompt:

[1668] The text prompt looks like this:

[1669] The following data is received from the HMD worn by the user during the night shift:

[1670] Heart rate: 150 BPM

[1671] Steps: 12,000

[1672] Body temperature: 38℃

[1673] Based on this data, stress signs are detected. A notification message should be generated and sent to the HMD, stating "Your stress level is high, please take a 5-minute break."

[1674] In this way, a system that analyzes a user's daily lifestyle data and emotional state and provides appropriate preventive measures is expected to be very useful in managing health conditions in actual work.

[1675] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1676] Step 1:

[1677] Data collection

[1678] The smartphone or wearable device worn by the user uses sensors to collect lifestyle data (e.g., number of steps, heart rate, sleep patterns, etc.). During this process, the input data is biometric data from various sensors, and the output is the collected raw data. The device prepares to send this data to a server at regular intervals.

[1679] Step 2:

[1680] Data transmission

[1681] The device sends the collected lifestyle habit data to a server using the MQTT protocol. The input data is the collected lifestyle habit data, and the output is the data sent to the server. During data transfer, the device monitors whether the communication is stable.

[1682] Step 3:

[1683] Data reception and storage

[1684] The server receives the data sent from the device and stores it in a database such as Amazon DynamoDB. The input data is the lifestyle habit data received from the device, and the output is the data stored in the database. The received data is first checked for format consistency and missing parts, and if abnormal or missing values ​​are detected, correction procedures are carried out.

[1685] Step 4:

[1686] Detecting signs of pre-disease

[1687] The server applies machine learning models to the stored data using TensorFlow to detect signs of pre-disease. The input data is lifestyle data after validation, and the output is information on abnormal patterns and signs of pre-disease. The data is analyzed through the machine learning model, and any abnormal patterns are recorded as signs.

[1688] Step 5:

[1689] Emotion analysis

[1690] The server uses IBM Watson Emotion Analysis to analyze user feedback and other emotional data (e.g., tone of voice and text messages) to recognize the user's emotional state. The input data is the collected emotional data, and the output is the emotional state information resulting from the analysis. The emotion engine analyzes text and voice data to detect the user's current emotional state.

[1691] Step 6:

[1692] Generate preventative measures

[1693] The server uses natural language generation technology to generate optimal preventive measures for each individual user based on their pre-illness signs and emotional state. The input data is information about pre-illness signs and emotional state, and the output is a generated preventive measure message. For example, the generated advice might be, "Your exercise volume has decreased recently. Try walking 30 minutes every day. Also, try incorporating deep breathing into your relaxation routine."

[1694] Step 7:

[1695] Preventive Measures Notice

[1696] The device displays the preventive measures message sent from the server as a push notification on a visual display device (e.g., a head-mounted display). The input data is the preventive measures message sent from the server, and the output is the notification displayed on the user's visual display device. The user is expected to confirm and implement the preventive measures through this.

[1697] Step 8:

[1698] Feedback collection

[1699] The user inputs feedback on the proposed preventive measures and the results of their implementation via a visual display device. The input data is the feedback information from the user, and the output is the feedback sent to the server. The user provides specific feedback, and the results are reflected in the next preventive measures.

[1700] Step 9:

[1701] Model Update

[1702] The server receives and analyzes user feedback and emotion data. The input data is the user feedback and emotion data, and the output is an updated machine learning model. This updates the machine learning model to reflect the next preventive action suggestion, allowing the system to continuously make suggestions adapted to the user's behavior and habits.

[1703] 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.

[1704] 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.

[1705] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1706] 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.

[1707] 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.

[1708] 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.

[1709] 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).

[1710] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1711] 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."

[1712] 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.

[1713] 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).

[1714] 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.

[1715] 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.

[1716] 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.

[1717] 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.

[1718] 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.

[1719] 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.

[1720] 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.

[1721] 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.

[1722] 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.

[1723] 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.

[1724] The following is further disclosed regarding the above embodiment.

[1725] (Claim 1)

[1726] A means of collecting lifestyle data of users;

[1727] A means for transmitting the collected lifestyle habit data to a server;

[1728] A means for analyzing collected lifestyle habit data and detecting signs of pre-disease in the server;

[1729] A means for generating individually optimized preventive measures based on pre-disease signs;

[1730] a means for notifying the user of the generated preventative measures;

[1731] a means of collecting user feedback data;

[1732] means for updating the machine learning model based on the collected feedback data;

[1733] A system including:

[1734] (Claim 2)

[1735] 2. The system according to claim 1, wherein the server further comprises means for validating the collected lifestyle habit data and detecting and correcting outliers and missing data.

[1736] (Claim 3)

[1737] 10. The system of claim 1, wherein the server further comprises means for using natural language generation techniques to generate preventative measures in a natural language that is understandable to the user.

[1738] "Example 1"

[1739] (Claim 1)

[1740] means of collecting data about the user's health;

[1741] means for transmitting the collected health data to a communication device;

[1742] a means for analyzing the collected health data in the communication device to detect signs of pre-disease;

[1743] A means for generating individually optimized preventive measures based on pre-disease symptoms;

[1744] a means for notifying the user of the generated preventative measures;

[1745] a means of collecting user feedback data;

[1746] means for updating the machine learning model based on the collected feedback data;

[1747] A system including:

[1748] (Claim 2)

[1749] 10. The system of claim 1, wherein the communication device further comprises means for validating the collected health data and detecting and correcting outliers and missing data.

[1750] (Claim 3)

[1751] 10. The system of claim 1, wherein the communication device further comprises means for using natural language generation techniques to generate preventative measures in natural language that is understandable to the user.

[1752] "Application Example 1"

[1753] (Claim 1)

[1754] A means of collecting lifestyle data of users;

[1755] A means for transmitting the collected lifestyle habit data to a server;

[1756] a means for collecting electronic payment data;

[1757] A means for analyzing the collected lifestyle habit data and electronic payment data in the server to detect signs of pre-disease;

[1758] A means for generating individually optimized preventive measures based on pre-disease signs;

[1759] a means for notifying the user of the generated preventative measures;

[1760] a means of collecting user feedback data;

[1761] means for updating the machine learning model based on the collected feedback data;

[1762] A system including:

[1763] (Claim 2)

[1764] 2. The system according to claim 1, wherein the server further comprises means for validating the collected lifestyle habit data and electronic payment data, and detecting and correcting outliers and missing data.

[1765] (Claim 3)

[1766] 10. The system of claim 1, wherein the server further comprises means for using a generative AI model and prompt sentences to generate preventative measures in natural language that is understandable to a user.

[1767] "Example 2: Combining Emotion Engines"

[1768] (Claim 1)

[1769] A means of collecting lifestyle data of users;

[1770] means for transmitting the collected lifestyle habit data to a remote server;

[1771] a means for analyzing the collected lifestyle habit data in a remote server to detect signs of abnormal health;

[1772] A means for generating individually optimized preventive measures based on symptoms of health abnormalities;

[1773] a means for notifying the user of the generated preventative measures;

[1774] a means of collecting user feedback data;

[1775] a means for updating the machine learning model based on the collected feedback data and sentiment analysis data;

[1776] A system including:

[1777] (Claim 2)

[1778] 2. The system of claim 1, wherein the remote server further comprises means for validating the collected lifestyle data and detecting and correcting outliers and missing data.

[1779] (Claim 3)

[1780] 10. The system of claim 1, wherein the remote server further comprises means for using natural language generation techniques to generate preventative measures in a natural language that is understandable to the user.

[1781] "Application example 2 when combining emotion engines"

[1782] (Claim 1)

[1783] A means of collecting lifestyle data of users;

[1784] A means for transmitting the collected lifestyle habit data to a server;

[1785] A means for analyzing collected lifestyle habit data and detecting signs of pre-disease in the server;

[1786] A means for generating individually optimized preventive measures based on pre-disease signs;

[1787] a means for notifying the user of the generated preventative measures;

[1788] a means of collecting user feedback data;

[1789] means for updating the machine learning model based on the collected feedback data;

[1790] a means for analyzing the emotional state of a user using an emotion analysis function;

[1791] A means for combining emotional state and lifestyle data to generate individually optimized preventative measures;

[1792] means for displaying the analysis results and preventative measures using a user-worn visual display device;

[1793] A system including:

[1794] (Claim 2)

[1795] 2. The system according to claim 1, wherein the server further comprises means for validating the collected lifestyle habit data and detecting and correcting outliers and missing data.

[1796] (Claim 3)

[1797] 10. The system of claim 1, wherein the server further comprises means for using natural language generation techniques to generate preventative measures in a natural language that is understandable to the user. [Explanation of symbols]

[1798] 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. A means of collecting lifestyle data of users; A means for transmitting the collected lifestyle habit data to a server; A means for analyzing collected lifestyle habit data and detecting signs of pre-disease in the server; A means for generating individually optimized preventive measures based on pre-disease signs; a means for notifying the user of the generated preventative measures; a means of collecting user feedback data; means for updating the machine learning model based on the collected feedback data; A system including:

2. The system according to claim 1 , wherein the server further comprises means for validating the collected lifestyle habit data and detecting and correcting outliers and missing data.

3. 10. The system of claim 1, wherein the server further comprises means for using natural language generation techniques to generate preventative measures in a natural language that is understandable to the user.

Images